Retention Re-engineering: Random to Recurring Revenues (Part 1)

Reinvention

Retention and growth of existing customers should be the top priorities for modern marketers. However, over the past decade, the focus has shifted disproportionately towards new customer acquisition and reacquisition of lapsed customers. This shift has led to an explosion in marketing budgets, driven by relentless bidding wars on adtech platforms. Today, adtech (customer acquisition) spending accounts for over 80% of marketing budgets, with a meagre 10% allocated to martech (customer engagement) and the remaining 10% to branding.

The hidden truth is that nearly half of the adtech budget is wasted due to misguided acquisition and reacquisition efforts. Marketers need to strike a balance between adtech and martech spending, but the lack of innovation in communication channels and martech platforms has perpetuated the skew towards adtech. Adtech is seen as a more reliable driver of consistent revenue growth compared to martech. This imbalance has resulted in low customer lifetime value (LTV) coupled with high customer acquisition costs (CAC), creating a profit squeeze for digital businesses. The promise of retention and growth marketing to enhance profitability has remained largely unfulfilled—until now.

Five groundbreaking innovations promise to revolutionise retention. These innovations go beyond traditional marketing; they will fundamentally re-engineer how marketers approach and implement retention strategies, and break the barriers between brands and their customers.

  1. Agentic AI and the Co-Marketer: Agentic AI will power a marketer’s companion, the Co-Marketer, transforming how marketing tasks are executed. The Co-Marketer can create personalised content at scale, driving engagement and retention like never before.
  2. Digital Twins for Segments and Individuals: Digital twins will enable marketers to simulate and predict customer behaviour, facilitating better next-best actions and enhancing customer experiences.
  3. AI-Powered Large Customer Models: Customer Data Platforms (CDPs) will evolve into AI-powered Large Customer Models, integrating data from both the brand’s own properties and external sources. This holistic view will drive more accurate and personalised marketing efforts.
  4. Epps (Email Apps) and ActionAds: Epps will transform passive, one-way emails into interactive, two-way communication channels, facilitating in-channel conversions and eliminating the friction of redirecting customers out of their inboxes. ActionAds will unlock new revenue streams by embedding actionable elements directly within the email, resulting in higher response rates.
  5. Bundled Kaizen Services: Martech platforms will evolve to offer “service as software,” where human expertise and AI collaborate to deliver continuous improvements. This approach will bridge the gap between platform capabilities and marketer usage, ensuring that marketing strategies are always at the cutting edge of innovation.

These innovations will help marketers anticipate customer intent with N=1 hyper-personalisation and influence actions through effective engagement strategies. They will address the challenge of attention recession by establishing direct communication hotlines with customers, thereby maximising customer LTV and reducing AdWaste. The combined effect of increasing LTV and decreasing CAC will significantly enhance profitability.

Marketers will finally be able to achieve their dream of converting sporadic, random purchases into predictable, recurring revenues. Digital twins for every customer will guide marketers on emerging interests and demands, while the Co-Marketer will craft custom content for persuasion at scale. Agentic AI will enable a “department of one” to cater to a “segment of one,” making hyper-personalised marketing and constantly adapting “generative journeys” a reality.

This next-generation martech, combined with innovative email strategies and advanced services, will equip marketers with the tools to drastically reduce AdWaste and embark on a Profipoly Quest – achieving exponential forever profitable growth. This will mark the most significant shift in marketing since the advent of adtech. Retention marketing – retention re-engineering – will finally claim its rightful place at the forefront of marketing strategies.

These are themes I have discussed in my previous marketing essays. In this essay, I will discuss the evolution of retention marketing and provide a roadmap to re-engineering it for the future.

Thinks 1324

NYTimes: “Peering into their computer screens in California last year, the data crunchers watched a subterranean fortune come into focus. What they saw transported them 10,000 miles across the world, to Zambia, and then one more mile straight down into the Earth. A rich lode of copper, deep in the bedrock, appeared before them, its contours revealed by a complex A.I.-driven technology they’d been painstakingly building for years…Their company, KoBold Metals, informed its business partners that their find is likely the largest copper discovery in more than a decade. According to their estimates, reviewed by The New York Times, the mine would produce at least 300,000 tons of copper a month once fully operational. That corresponds to a value of billions of dollars a year, for decades.”

: “Innovation is fundamentally incompatible with industrial policy, which involves government promotion — using subsidies and tariffs — of particular industries or technologies. It is planning based on what already exists, what is already known, and what government officials can conceive. By necessity, it excludes genuine innovation because innovation is creative. Innovation creates possibilities that didn’t previously exist. Future innovations, therefore, can’t possibly be part of today’s industrial-policy plan.”

WSJ: “When China launched its one-child policy more than four decades ago, it sped up an evolution toward smaller family sizes that would have happened more gradually. The policy supercharged the country’s workforce: By caring for fewer children, young people could be more productive and put aside more money. For years, just as China was opening its economy, the share of working-age Chinese grew faster than the parts of the population that didn’t work. That was a big factor in China’s economic miracle. There was a price and China is now paying it. Limiting births then means fewer workers now, and fewer women to give birth. A United Nations forecast published [recently] shows how quickly China is aging, a demographic crunch that the U.N. predicts will cut China’s population by more than half by the end of the century.” Business Standard: “India has only 38 years before its population starts shrinking.”

FT on AI: “There’s a paradox here common to all new tech platforms. As the cost of using the new technology plunges, customers could theoretically get away with buying less. But rapidly falling costs usually lead to new uses being found, and demand instead soars. As with everything to do with generative AI, this is happening at warp speed, and it is hard to tell how closely this will mirror other disruptive tech cycles. At some point, of course, all of this investment has to earn a return. If not, then the chief executives who have been pushed by their boards and by fear of competition to demand their companies find uses for generative AI will eventually lose patience and move on. But all indications are that we’re not at that point yet.”

The Crossing: When Digital Twins and Email Apps Meet

Published August 16, 2024

1

M3 and E3 – 1

Two themes I have covered in the past few months have been a new vision for AI-first marketing (Agentic AI, Large Customer Models, Co-Marketer, Digital Twins, Generative Journeys, Adtech-Martech integration [see Part 4], Commerce Metaverse) and AMP-powered email (Email Apps, Action Ads). Together, they offer solutions to solving the low LTV (lifetime value) and high CAC (customer acquisition cost) problems which hurt profitability. By anticipating intent via better use of data for personalisation and influencing actions via creating hotlines, these new ideas in marketing and email (what I have termed M3 and E3, respectively) can power the Profipoly Quest of companies.

Here is a short summary of these ideas (written with the help of Claude).

Agentic AI represents the next evolution in AI, characterised by autonomous and intelligent agents capable of performing complex tasks, making decisions, and learning from their environment. In marketing, Agentic AI powers systems like Co-Marketers and Digital Twins, enabling real-time personalisation, predictive analytics, and automated decision-making. It can process vast amounts of customer data, extract meaningful insights, and drive marketing strategies autonomously. Agentic AI promises to transform customer relationships by enabling hyper-personalisation and more efficient, data-driven marketing approaches.

Large Customer Models (LCMs) are advanced AI models that serve as the foundation for AI-first marketing strategies. Built on extensive customer data, LCMs create dynamic, real-time evolving profiles of customers. They consist of three layers: generic foundational models (like ChatGPT), a marketing-specific foundational model (combining intelligence for both adtech and martech channels), and an enterprise-specific model incorporating PII data. By leveraging the “5 Cs” of customer data (Customers, Channels, Cohorts, Catalog, and Conversations), LCMs enable deeper personalisation, precise targeting, and more effective marketing strategies across all customer touchpoints.

A Co-Marketer is an AI-powered marketing assistant that collaborates with human marketers to optimise various aspects of marketing strategies. It leverages Agentic AI to perform tasks such as segmentation, campaign planning, content creation, and journey optimization. Co-Marketers can aggregate and analyse vast amounts of data, predict customer behaviour, generate personalised content, and execute marketing campaigns autonomously. They provide real-time optimisation recommendations and engage in interactive dialogues with human marketers. For CMOs, Co-Marketers offer enhanced efficiency, improved personalisation, strategic insights, and scalable solutions. They represent the future of marketing, promising a “Department of One” for a “Segment of One” approach.

Digital Twins in marketing are AI-powered virtual representations of customers or customer segments. There are two types: Segment Twins, representing groups with similar behaviours and preferences, and Singular Twins, replicating individual customers. These twins provide comprehensive insights into customer behaviours, preferences, and interactions. They enable marketers to simulate scenarios, test strategies, and deliver highly personalised experiences. Digital Twins interact with Co-Marketers in a “mirror world” to identify optimal engagement strategies. By facilitating true 1:1 personalisation and enabling precise targeting of customer groups, Digital Twins transform marketing from broad approaches to highly tailored strategies.

2

M3 and E3 – 2

Generative Journeys represent an advanced approach to customer experience, leveraging AI to create dynamic, personalised paths for each customer. Unlike predefined customer journeys, generative journeys use AI to analyse customer behaviour in real-time and generate the next best action or message. They integrate insights from Large Customer Models, Digital Twins, and Co-Marketers to accelerate “transaction moments” in a customer lifecycle. Generative journeys continuously refine and personalise each step based on real-time feedback and predictive analytics. This approach enables unparalleled customer engagement, conversion, and retention by ensuring that every interaction is tailored to the individual’s evolving needs and preferences.

Adtech-Martech integration, sometimes referred to as “Madtech,” represents the convergence of content and data from the acquisition of new customers and retargeting of existing customers (adtech), and the engagement and retention of existing customers (martech). This integration creates a seamless ecosystem where data from both advertising and marketing efforts can flow freely, enhancing the accuracy and relevance of customer profiles. It enables marketers to leverage insights from advertising platforms (like Google and Meta) and social platforms (Facebook, Instagram, Snap, TikTok) alongside zero-party and first-party data from marketing automation tools and interaction on owned channels (email, SMS, RCS, WhatsApp, push notifications). The integration is crucial for creating a unified view of the customer journey, from initial awareness to conversion and loyalty. It supports more precise targeting, personalisation, and measurement across the entire customer lifecycle.”

The Commerce Metaverse represents a new paradigm in digital marketing and customer engagement, inspired by the Industrial Metaverse but focused on commerce and marketing interactions. It’s a virtual environment (“mirror world”) where AI-powered entities like Co-Marketers and Digital Twins (both Segment and Singular) interact to create hyper-personalised customer experiences. Unlike the consumer-focused metaverse, the Commerce Metaverse emphasises business outcomes, enabling marketers to simulate customer interactions, test strategies, and optimise journeys in a risk-free environment. By leveraging technologies like Agentic AI and Large Customer Models, the Commerce Metaverse aims to revolutionise how brands understand, engage with, and serve their customers, ultimately driving higher conversion rates and customer lifetime value.

Email Apps (Epps) represent the next evolution in email engagement, leveraging AMP technology to create interactive, app-like experiences within emails. Epps are multi-screen implementations that interact with backend databases and update in real-time when opened. They are self-contained, eliminating the need for external websites or apps. Epps can include features like interactive product catalogs and in-email transactions. By transforming emails into dynamic platforms for engagement and conversion, Epps aim to solve the email open problem, increase user interaction, and provide a seamless experience for activities ranging from shopping to customer support.

Action Ads are a new format of interactive advertisements embedded within emails, leveraging AMP technology and Atomic Rewards. These ads enable users to complete actions such as form fills, purchases, or subscriptions directly within the email, without clicking through to external landing pages. Action Ads are characterised by four key attributes (4 Ps): they are linked to PII for targeted messaging, delivered via push channels, allow in-place actions, and can support payments. By reducing friction in the customer journey and enabling immediate engagement, Action Ads aim to improve conversion rates, enhance user experience, and create new revenue streams for brands and email platforms.

So far, the two worlds of M3 and E3 have been largely independent. What would happen if digital twins and email apps went beyond co-existence and “crossed”? In this series, we will explore possible ideas and futures.

3

The Crossing

In Michael Connelly’s book “The Crossing”, former LAPD detective Harry Bosch reluctantly agrees over to work with his half-brother, defence attorney Mickey Haller, to investigate a murder case. Bosch, known for his dedication to putting criminals behind bars, finds himself in unfamiliar territory as he seeks to prove the innocence of Haller’s client.

In the book, the “crossing” has multiple meanings. Firstly, it refers to the professional and ethical shift of Bosch, as he transitions from being a police detective to working as a defence investigator. This change forces him to grapple with his principles and the complexities of the legal system from a new perspective. Secondly, the “crossing” also symbolises the moment when the paths of the murderer and the victim intersect, marking the critical point in the narrative where the crime occurs. This intersection is pivotal to the storyline, as it sets off the chain of events that Bosch investigates, uncovering deeper layers of the case and ultimately leading to the resolution of the mystery. This second interpretation is what I want to discuss further.

When I read the book (and I don’t miss any of Connelly’s Bosch or Haller books), I was fascinated by this excerpt: “In a case like this, where the victim appeared to be chosen at random, there is always a crossing point. The place where the predator first encounters his prey. The job of the investigators is to find the crossing, the place where the circle of the victim’s life overlaps the circle of the predator.”

The concept of “crossings” extends far beyond fictional narratives, playing a pivotal role in our daily lives and broader societal patterns. In the real world, crossings occur when the circles of different individuals’ lives intersect, often leading to significant events or changes. These intersections can happen in various contexts – a chance encounter at a coffee shop that leads to a lifelong friendship, a serendipitous meeting at a conference that sparks a groundbreaking collaboration, or even a random interaction on social media that results in a business partnership. Crossings can also be more structured, like joining a new workplace or moving to a new neighbourhood, where multiple life circles suddenly overlap. These moments of intersection are often catalysts for change, innovation, and personal growth. They remind us of the interconnectedness of human experiences and the potential for transformation that lies in these points of convergence. Understanding and leveraging these crossings can be crucial in fields ranging from social sciences to business strategy, as they represent opportunities for meaningful connections and impactful outcomes.

In a similar vein, the worlds of M3 (Agentic AI and digital twins) and E3 (email apps and ads) may seem distinct, but their intersection holds transformative potential. Imagine a “crossing” where every email becomes a dynamic, personalised touchpoint in a customer’s AI-driven journey. What if Agentic AI could power Epps, creating interactive experiences that adapt in real-time? Consider digital twins constructed from cross-brand email behaviours, informing hyper-targeted Action Ads. This convergence could revolutionise email marketing, potentially achieving near-perfect open rates and engagement. The email footer might evolve into a key element of generative journeys, offering personalised, cross-brand experiences. This “crossing” between M3 and E3 promises to redefine customer engagement, merging the predictive power of AI with the ubiquity and intimacy of email communication.

4

CAC and LTV

Before delving deeper into the “crossing” between M3 and E3, it’s crucial to step back and examine the fundamental challenges that marketers face in today’s digital landscape.

As highlighted in numerous essays, B2C and D2C brands grapple with a significant issue: approximately half of their marketing budget is squandered on ineffective acquisition and reacquisition efforts. This phenomenon, termed “AdWaste,” represents a substantial barrier between businesses and their profitability goals. Eliminating this waste is not just about turning a profit-less venture into a profitable one; it’s also about transforming a profitable business into a “profipoly” – a profit monopoly that stands head and shoulders above its competitors.

The key to this transformation lies in growing Customer Lifetime Value (LTV). This focus on LTV is critical because optimising Customer Acquisition Cost (CAC) and Return on Ad Spend (ROAS) has become increasingly challenging in the fiercely competitive bidding markets that characterise the world of adtech. As these costs continue to rise, the most viable path to improved profitability is through enhancing the value derived from existing customers.

To grow LTV, marketers primarily leverage two assets: their properties (websites and apps) and their channels (email, SMS, WhatsApp, and others). In an ideal scenario, customers would engage with every marketing message, opening emails and clicking through to websites or apps. However, the reality we face as consumers paints a starkly different picture. We often ignore most marketing messages, a phenomenon known as “attention recession.” This widespread disengagement makes it exceptionally difficult for marketers to establish reliable, responsive communication channels – or “hotlines” – with their customers.

The absence of effective engagement with existing customers forces marketers into a costly cycle. They find themselves compelled to increase spending on continually acquiring new customers, even when many of these “new” acquisitions may actually be past customers who have become inactive or churned. This reliance on adtech spending, coupled with aggressive discounting strategies, erodes profitability and creates an unsustainable business model.

However, a paradigm shift is on the horizon. For the first time, marketers have access to solutions that can significantly boost LTV while simultaneously reducing CAC, thereby enhancing overall profitability. This is where the worlds of M3 (Marketing’s AI Triad) and E3 (Email’s New Triad) come into play.

M3 revolutionises conversion and retention strategies by providing an enhanced, 360-degree understanding of both customer clusters and individual customers. This comprehensive insight enables better matching of products to customers, reminiscent of how Large Language Models (LLMs) match words in natural language processing. The result is more precise targeting, personalised offerings, and improved customer experiences.

Complementing this, E3 ensures that push messages are not only more relevant but also facilitate in-channel conversion. This means that customers can engage and complete transactions without leaving the inbox, thus reducing friction and increasing conversion rates.

Together, M3 and E3 address the three primary profit killers that have long plagued marketers: poor data quality, funnel frictions, and AdWaste. By providing rich, actionable customer insights and streamlining the path to purchase, these innovative approaches pave the way for more efficient and effective marketing strategies.

The true power of M3 and E3 lies in their ability to shift focus from constant acquisition to retention and maximisation of customer LTV. Every dollar redirected from the leaky bucket of AdWaste directly contributes to improved profitability. While M3 and E3 are powerful in their own right, their “crossing” – the point where these two innovative approaches intersect and interact – holds the potential for truly transformative results.

Fusing the concepts of M3 and E3 can lead to a plethora of innovative ideas that can emerge from their intersection and power the profitability march for businesses. We will discuss four of them: Email Language Model, Email Twin, Epps Footer Containers, and Email Minis.

5

Email Language Model

Email stands out as a specialised communication channel with unique complexities. Unlike simpler formats such as SMS, WhatsApp, or RCS, an email comprises multiple distinct elements: a subject line to capture attention, a hero image or message to make an immediate impact, the main body to convey detailed information, and a footer for additional context or calls-to-action. This multi-faceted structure demands significant effort and expertise to create effectively.

The introduction of AMP in email has further elevated the complexity of email creation, necessitating collaboration between coders, creative designers, and content specialists to produce the final, interactive email. This intricate process, while potentially powerful, can be time-consuming and resource-intensive.

Enter ELM, the Email (Small) Language Model, a specialised AI model designed to streamline the email creation process. By leveraging the collective wisdom from tens of thousands of email creatives and incorporating brand-specific performance data, the Email SLM creates a fine-tuned model tailored for email marketing excellence.

While LLMs excel at broad language understanding and generation, SLMs are fine-tuned on domain-specific data, making them more precise and effective for targeted applications. In the context of email marketing, an SLM can be trained on vast datasets of successful email campaigns, industry-specific language, and brand-particular communications. This focused training allows the SLM to capture nuances of email marketing that a general-purpose LLM might miss, such as optimal subject line structures, effective call-to-action phrases, or industry-specific jargon. Moreover, SLMs are more computationally efficient, allowing for faster processing and real-time applications. They can be more easily updated with the latest marketing trends and company-specific data, ensuring that the model’s outputs remain current and relevant. Additionally, SLMs can be designed to adhere strictly to brand guidelines and regulatory requirements specific to email marketing, reducing the risk of off-brand or non-compliant content generation. This specialised focus makes SLMs a more reliable and effective tool for email marketers, offering tailored, high-quality outputs that are directly applicable to their specific needs and challenges.

Key features and benefits of ELM include:

  1. Automated Content Generation: ELM can generate compelling subject lines, body copy, and calls-to-action based on campaign objectives and brand voice.
  2. Performance-Driven Optimisation: By analysing historical data on email performance, ELM can suggest improvements and predict the effectiveness of new content.
  3. AMP Integration: The model can assist in creating AMP-powered interactive elements, bridging the gap between design and coding.
  4. Personalisation at Scale: ELMs can generate personalised content for different customer segments or even individual recipients, enhancing relevance and engagement.
  5. A/B Testing Recommendations: ELM can propose variations for A/B testing, accelerating the optimization process.
  6. Cross-Channel Consistency: By understanding brand guidelines and messaging across channels, ELM ensures consistency while adapting content for email’s unique format.
  7. Regulatory Compliance: The model can be trained to adhere to email marketing regulations and best practices, reducing legal risks.

By simplifying the email creation process, ELM not only saves time and resources but also enhances the quality and effectiveness of email marketing campaigns. This AI-powered tool represents a significant step forward in the intersection of M3 and E3, combining the power of machine learning with the specificity of email marketing to drive better results and streamline workflows.

6

Email Twin

Consumer behaviours are notably diverse across different communication channels, but nowhere is this diversity more pronounced than in email interactions. Email, as a medium, presents a unique set of decision points for consumers, each of which offers valuable insights into individual preferences and behaviours. These decision points create a complex web of user interactions that can be leveraged to create highly personalized experiences.

The journey of email engagement begins with the initial decision to open an email, a choice heavily influenced by the subject line and the snippet preview. This crucial first step determines whether the content even has a chance to reach the recipient. Once opened, the consumer then decides whether to scroll through the entire email or abandon it partway. If they continue, they face the choice of clicking through to a landing page or not, and ultimately, whether to maintain their subscription or opt out.

Each of these decision points represents a wealth of data that, when properly analysed, can provide deep insights into individual consumer preferences and behaviours. This is where the concept of an “Email Twin” comes into play. By collaborating closely, brands and email service providers can harness this rich data to create a digital doppelganger for each customer, specifically tailored to their email interaction patterns.

An Email Twin would be a comprehensive digital representation (like an “email DNA”) of an individual’s email behaviour and preferences. It would encompass a wide range of factors, including:

  1. Optimal Email Timing: Identifying the days and times when a particular user is most likely to open and engage with emails.
  2. Content Preferences: Determining whether the user responds better to text-heavy emails or image-rich designs.
  3. Subject Line Effectiveness: Analysing which types of subject lines resonate most with the individual.
  4. Colour Schemes: Identifying colour preferences that lead to higher engagement rates.
  5. Email Length: Determining the ideal email length for maximum readership.
  6. Interactive Element Preferences: Understanding which interactive elements (e.g., polls, quizzes, videos) drive the most engagement.
  7. Device Usage: Knowing whether the user primarily checks email on mobile or desktop, and optimising accordingly.
  8. Frequency Tolerance: Gauging how often a user is willing to receive emails before considering unsubscribing.
  9. Click Behaviour: Analysing which parts of the email (top, middle, bottom) generate the most clicks.
  10. Language and Tone: Identifying the communication style that resonates best with the individual.

By amalgamating these data points, an Email Twin would provide a nuanced understanding of each customer’s email consumption habits. This digital replica would enable marketers to tailor every aspect of their email communications to align perfectly with individual preferences.

Imagine the possibilities: An email campaign could be dynamically adjusted for each recipient from the primary template. For one user, it might be a short, text-based email sent on a Tuesday morning with a straightforward subject line. For another, it could be an image-rich newsletter delivered on a Sunday evening with an intriguing, question-based subject line. The same core message could be presented in myriad ways, each optimised for its specific recipient.

The synergy between the Co-Marketer, Digital Twin, and Email Twin represents a powerful trifecta in personalised marketing. While the Digital Twin provides a comprehensive view of the customer’s overall behaviour and preferences across various touchpoints, the Email Twin offers specialised insights into the customer’s email interaction patterns. The Co-Marketer, as an AI-powered marketing assistant, would leverage both these twins to craft highly optimised email communications. It would consult the Digital Twin for broad customer insights, such as purchase history, product preferences, and general engagement patterns. Simultaneously, it would tap into the Email Twin for email-specific behaviours like preferred send times, subject line preferences, and content format choices. By integrating these two data sources, the Co-Marketer can create email messages that are not only personalised in terms of content and offers but also optimised for email-specific engagement. For instance, it might use the Digital Twin’s data to select products for a promotional email, while relying on the Email Twin’s insights to determine the best time to send it, craft an appealing subject line, and structure the email layout for maximum impact. This multi-faceted approach ensures that each email is tailored not just to the customer’s general preferences, but also to their unique email consumption habits, significantly enhancing the likelihood of engagement and conversion.

The creation of Email Twins represents a significant leap forward in the personalisation of email marketing. It moves beyond simple segmentation to true N=1 individualisation, treating each recipient as a unique entity with distinct preferences and behaviours. This level of personalisation has the potential to dramatically increase email engagement rates, reduce unsubscribes, and ultimately drive higher conversion rates.

Moreover, as these Email Twins evolve and learn from ongoing interactions, they would become increasingly accurate representations of user behaviour. This continuous refinement would allow for ever-more sophisticated and effective email marketing strategies, creating a virtuous cycle of improved engagement and customer satisfaction.

In essence, the Email Twin concept promises to transform email from a one-size-fits-most channel to a highly personalised, individual-centric communication medium. It represents the convergence of big data, artificial intelligence, and marketing strategy, pointing the way toward the future of digital customer engagement.

7

Epps Footer Containers

I have previously discussed how email footers can be transformed: Reimagining the Email Footer and Dynamic Engaging Footers: Email 2.0’s Silver Bullet. The concept of transforming email footers into dynamic, interactive spaces represents a significant leap forward in email marketing, perfectly aligning with the innovative principles of M3 and E3. This reimagined footer, powered by Epps (Email Apps), has the potential to transform how brands engage with their customers through email.

The traditional email footer, often relegated to compliance information and an unsubscribe link, is evolving into a powerful engagement tool. By leveraging Epps, marketers can create a multi-faceted “container” within the footer, housing various AMPlets (AMP-powered elements) that work together to form a cohesive, interactive experience. This approach transforms the footer from a passive element to an active, value-adding component of every email.

Key components of this enhanced footer could include:

  1. Feedback Container: This section could host interactive NPS (Net Promoter Score) surveys along with more detailed feedback forms. The ability to collect real-time feedback within the email itself not only increases response rates but also provides immediate insights for brands to act upon.
  2. Data Container: Leveraging the concept of zero-party data collection, this area could feature quick surveys or “hot or not” style interactions. These engaging micro-interactions encourage users to voluntarily share preferences and interests, enriching the brand’s understanding of each customer.
  3. Games/Quiz Container: By incorporating brand-relevant games or quizzes, marketers can create a fun, educational experience that increases engagement time and reinforces brand messaging in an entertaining way.
  4. Personalised Offers Container: Based on the customer’s Digital Twin data, this section could display tailored product recommendations or exclusive offers.
  5. Content Discovery Container: This could showcase personalised content recommendations, encouraging further engagement with the brand’s ecosystem.

The beauty of these Epps Footer Containers lies in their dynamic nature. Controlled from the server, the content within these containers can be updated in real-time, ensuring that each email open delivers a fresh and relevant experience. This capability addresses one of the longstanding challenges in email marketing: maintaining engagement with emails over time.

The integration of M3 elements – particularly the insights derived from Digital Twins and Large Customer Models – allows for hyper-personalisation of these footer containers. For instance, understanding where a customer is in their buying journey enables the creation of subtle, timely nudges towards conversion. The Co-Marketer AI (along with the Email Twin) could dynamically adjust the content and timing of these nudges based on real-time interaction data and predicted customer behaviour.

Furthermore, the in-place interactivity of these footer containers aligns perfectly with the E3 concept. By eliminating the need for clickthroughs to external landing pages, marketers can maintain the user’s attention and engagement within the email environment. This seamless experience not only improves user engagement but also provides a continuous stream of valuable interaction data.

The Epps Footer Containers become an integral part of the E3 wrapper, driving email opens and sustained engagement. As users interact with these dynamic elements, they create a virtuous cycle of engagement and personalisation. Each interaction provides more data for the M3 systems to refine their understanding of the customer, which in turn allows for even more targeted and effective future communications.

Moreover, these enhanced footers open up new possibilities for email monetisation through Action Ads. Advertisers could leverage these interactive spaces to create engaging, non-intrusive ad experiences that feel native to the email environment.

In conclusion, the transformation of email footers through Epps represents a convergence of M3 and E3 principles, creating a powerful new channel for customer engagement. By turning every email into a dynamic, interactive experience, brands can significantly increase the value and effectiveness of their email marketing efforts. This innovation not only enhances customer engagement and data collection but also paves the way for new revenue streams and more sophisticated, AI-driven marketing strategies.

8

Email Minis – 1

The fourth and final idea is the idea of short-targeted email subscriptions. Think of them as “Email Minis.” This builds on the microns (micro-newsletters) idea I have previously discussed. [See Microns and Brands: Made for Each Other and Micron-verse: The New World of Brand-Customer Communications.]

Email Minis transform the traditional open-ended email subscription model into a more dynamic, time-bound engagement strategy. Instead of the conventional “till death (or unsubscribe) do us apart” approach, these short-term subscriptions provide a clear duration, creating a sense of exclusivity and urgency that can drive higher engagement rates.

The power of Email Minis lies in their ability to deliver focused, timely content. For instance, an apparel brand could offer a weeklong Email Mini during summer, providing daily fashion recommendations. This approach allows brands to create concentrated bursts of engagement around specific themes, seasons, or events, keeping content fresh and relevant.

Leveraging the M3 system, these Email Minis can be crafted with unprecedented personalisation. The insights gleaned from Large Customer Models, Digital Twins, and Co-Marketers can inform the content, timing, and targeting of these mini-subscriptions. This ensures that each Email Mini is not just a generic campaign, but a highly tailored experience for each subscriber.

The subscription process for Email Minis can be seamlessly integrated into the existing email ecosystem. Utilising Epps Footer Containers or Action Ads, customers can subscribe with a single tap, eliminating friction and increasing the likelihood of opt-ins. This ease of subscription, combined with the clear, limited-time commitment, can make Email Minis an attractive option for consumers who might be hesitant to commit to indefinite subscriptions.

One of the most compelling aspects of Email Minis is their potential to create non-linear customer journeys. Traditional email marketing often follows a linear path, but Email Minis allow for a more branched, exploratory approach. A bookstore, for example, could offer a 7-day Email Mini on a new book release. Based on the subscriber’s engagement with this mini-series, the brand could then recommend similar titles or even more targeted Email Minis, creating a personalised content discovery journey.

The interactive nature of Email Minis, especially when crafted as Epps, provides a rich source of engagement data. Every interaction within these mini-series feeds back into the M3 system, continuously enhancing the Digital Twin profile of each customer. This creates a virtuous cycle of increasingly personalized and relevant content.

Email Minis also excel in post-purchase scenarios, offering an effective way to onboard new customers and help them maximise the value of their purchases. A series of Email Minis could guide customers through product features, offer usage tips, or suggest complementary products, enhancing customer satisfaction and potentially driving additional sales.

The scalability of Email Minis is significantly enhanced by the capabilities of the Co-Marketer. This AI-powered assistant can help craft content for numerous Email Minis, enabling brands to create a diverse array of targeted mini-series without overwhelming their marketing teams.

Moreover, Email Minis provide an excellent opportunity for zero-party data collection. Each mini-series can include interactive elements that encourage subscribers to share their preferences, interests, and feedback. This valuable data can then be used to refine future Email Minis and overall marketing strategies.

In conclusion, Email Minis represent a powerful evolution in email marketing, combining the precision of M3 insights with the interactive capabilities of E3. By offering focused, time-bound content experiences, brands can create more engaging, relevant, and effective email campaigns. As consumers increasingly value personalised, bite-sized content, Email Minis can become a key tool in the modern marketer’s arsenal, driving engagement, fostering customer loyalty, and unlocking new avenues for personalised marketing at scale.

9

Email Minis – 2

I asked Claude for more ideas for Email Minis. (Think of each of these emails as Epps – interactive, dynamic, and where needed, self-contained.)

  1. Retail Fashion:
    • “7 Days of Summer Styles”: Daily outfit inspirations with mix-and-match suggestions
    • “Color of the Week”: A 5-day series exploring different ways to incorporate a trendy color into outfits
  2. Travel and Hospitality:
    • “Destination Discovery”: 10-day series showcasing different aspects of a travel destination
    • “Foodie’s Guide”: 5-day culinary tour of a city’s best restaurants and local cuisines
  3. Finance and Banking:
    • “Investing 101”: 2-week crash course on investment basics for beginners
    • “Budgeting Bootcamp”: 7-day series with daily budgeting tips and interactive expense tracking
  4. Health and Wellness:
    • “30-Day Fitness Challenge”: Daily workout routines with progress tracking
    • “Mindfulness Week”: 7 days of guided meditation and mindfulness exercises
  5. Technology:
    • “Tech Tip of the Day”: 10-day series featuring daily productivity hacks for popular software
    • “Cybersecurity Awareness”: 5-day course on protecting personal data online
  6. Education:
    • “Language Learning Sprint”: 2-week intensive course with daily vocabulary and grammar lessons
    • “Exam Prep Countdown”: 10-day series with study tips and practice questions leading up to an exam
  7. Food and Cooking:
    • “Weeknight Dinner Ideas”: 5-day series with quick and easy recipes
    • “Baking Basics”: 7-day introduction to essential baking techniques
  8. Entertainment:
    • “Film Festival Highlights”: Daily updates and reviews during a week-long film festival
    • “Artist Spotlight”: 5-day deep dive into a musician’s career, culminating in a new album release
  9. Home Improvement:
    • “Spring Cleaning Challenge”: 7-day series with daily decluttering and organizing tasks
    • “DIY Weekend Project”: 3-day guide to completing a home improvement project
  10. Automotive:
    • “Car Maintenance 101”: 5-day course on essential car care tips
    • “EV Exploration”: 7-day series introducing different aspects of electric vehicles
  11. Beauty and Skincare:
    • “Skincare Routine Builder”: 7-day guide to creating a personalized skincare regimen
    • “Makeup Masterclass”: 5-day series featuring different makeup techniques
  12. Professional Development:
    • “Networking Ninja”: 5-day challenge to expand professional networks
    • “Public Speaking Bootcamp”: 7-day course to improve presentation skills

**

The convergence of M3 and E3 at their “crossing” point heralds a new era in digital marketing, particularly in the realm of email engagement. This intersection is brought to life through four innovative concepts: ELM (Email Language Model), Email Twin, Epps Footer Containers, and Email Minis. Together, these ideas leverage the predictive power of AI and the ubiquity of email to create hyper-personalised, interactive, and highly engaging customer experiences. ELM streamlines content creation, while Email Twins enable precise targeting. Epps Footer Containers transform every email into a dynamic engagement platform, and Email Minis offer focused, time-bound content experiences. This synergy between AI-driven insights and interactive email capabilities not only enhances customer engagement but also provides a continuous feedback loop, constantly refining our understanding of each customer. As we stand at this crossing, this “fusion of futures” between M3 and E3 can help us unlock unprecedented levels of marketing effectiveness, driving higher conversion rates, customer loyalty, and ultimately, profitable growth.

10

More Ideas

I asked Claude and ChatGPT and Claude to suggest more ideas at the “crossing” of M3 and E3.

Claude

Journey Compass is an AI-powered navigation system that dynamically adjusts email content based on the recipient’s position in their customer journey. By combining the predictive capabilities of M3’s Digital Twins with E3’s interactive email features, Journey Compass creates a personalized map for each customer. It analyzes past interactions, current context, and predicted future behaviors to determine the most relevant content, offers, and calls-to-action for each email. This system ensures that every email sent is not just a message, but a strategic step in guiding the customer towards their next best action, whether it’s making a purchase, upgrading a service, or engaging with new content.

Sentiment Sync is an emotional intelligence layer that adapts email content based on the recipient’s current emotional state and preferences. This system combines natural language processing from M3 with E3’s real-time content adaptation capabilities. By analyzing recent customer interactions across all touchpoints, social media sentiment, and even external factors like local events or weather, Sentiment Sync adjusts the tone, imagery, and messaging of emails to resonate with the recipient’s emotional context. This could mean sending a more empathetic message during challenging times or an upbeat, celebratory email when the customer has recently had a positive experience with the brand.

Micro-Moment Maximizer capitalizes on brief windows of high engagement potential identified by M3’s predictive analytics. This system triggers instant, highly personalized micro-emails or in-email notifications at precisely the right moment. For example, if a customer is predicted to be in a purchase-ready state for a specific product category, the Micro-Moment Maximizer could instantly deploy a targeted offer or product recommendation. These micro-interactions, delivered through E3’s dynamic email capabilities, are designed to capture attention and drive action during fleeting moments of peak relevance.

Adaptive Learning Loop (ALL) creates a continuous feedback system between email interactions and M3’s AI models. Every email interaction, from opens and clicks to hover times and scroll depth, is instantly fed back into the AI system. This real-time data updates the customer’s Digital Twin, refines the Large Customer Model, and informs the Co-Marketer’s strategies. The ALL system then immediately applies these learnings to optimize subsequent emails, creating a virtuous cycle of ever-improving personalization. This could manifest as real-time adjustments to email content, send times, or even triggering follow-up emails based on how a recipient interacts with a message.

ChatGPT

Real-Time Engagement Epps combine the predictive power of M3’s Large Customer Models with the interactive capabilities of E3. These Epps can dynamically update content based on real-time data and customer interactions. For instance, during a live event or flash sale, the Epp could provide up-to-the-minute updates, exclusive offers, or limited-time deals directly within the email. By leveraging real-time data, brands can create a sense of urgency and exclusivity, driving higher engagement and conversion rates. This fusion of real-time analytics and interactive email content ensures that every email is contextually relevant and timely, enhancing customer experience and loyalty.

Journey Mapper Epps utilize Generative Journeys from M3 to create dynamic, personalized customer journeys within emails. These Epps can adapt the email content based on the customer’s behavior and preferences, guiding them through a tailored experience. For example, a new customer might receive a welcome series with introductory offers, while a returning customer might see personalized product recommendations or loyalty rewards. By mapping out these individualized journeys, brands can ensure that each email interaction is meaningful and drives the customer further along the purchase path, ultimately increasing LTV and retention.

Feedback Loop Epps integrate zero-party data collection and analysis into the email experience. By embedding interactive surveys, polls, and feedback forms within Epps, brands can gather valuable customer insights directly from their inbox. The data collected is fed back into the Large Customer Models, refining the customer profiles and enabling more precise targeting and personalization. This continuous feedback loop not only enhances customer engagement but also ensures that the brand’s messaging remains relevant and effective. The seamless integration of feedback mechanisms within emails makes it easy for customers to share their opinions, fostering a sense of involvement and loyalty.

Predictive Action Epps harness the power of Agentic AI to anticipate customer needs and suggest the next best actions within emails. By analyzing historical data and real-time interactions, these Epps can predict what a customer might be interested in or ready to purchase next. For example, if a customer frequently buys sports gear, the Epp might suggest new arrivals in that category or related accessories. By offering highly relevant and timely suggestions, Predictive Action Epps can drive immediate action and boost conversion rates. This proactive approach to customer engagement ensures that every email is a step towards a sale or a deeper relationship.

Cross-Channel Sync Epps ensure that the messaging and experience within an email are consistent with other marketing channels like SMS, social media, and web. By integrating Adtech-Martech data, these Epps can deliver a unified customer experience across all touchpoints. For instance, a customer who clicks on a product ad on social media might receive a follow-up email with additional information, reviews, and a special discount. This synchronization ensures that the customer journey is seamless and coherent, enhancing brand trust and driving higher engagement across multiple channels.

Interactive Storytelling Epps leverage AMP technology and Generative Journeys to create engaging, narrative-driven email experiences. These Epps can guide customers through a story, with each interaction revealing new content, products, or offers. For example, a travel brand could create an Epp that takes customers on a virtual tour of a destination, with embedded videos, quizzes, and booking options along the way. By combining storytelling with interactivity, brands can create immersive experiences that capture attention and drive deeper engagement, making the email more than just a communication tool but an experience in itself.

Thinks 1323

NYTimes: “In [Akira Kurosawa’s] “Seven Samurai,” a village regularly plundered by brigands seeks protection, hiring a group of masterless samurai, who are professional killers willing to work for a daily portion of rice and their own code of honor. The film has three movements: the leisurely gathering of the samurai, the painstaking organization of the village and the convulsive final battle. The battle is an astonishing example of ensemble orchestration and percussive editing, but Kurosawa’s artistry is sensational throughout the movie. The film is a seamless synthesis of Hollywood naturalism, Soviet montage and stylized acting, verging on Kabuki, most evident in the outlandish physicality of Toshiro Mifune’s performance as the most obstreperous of the Seven. (His bongo-bassoon theme is only one of the bravura musical touches by the composer Fumio Hayasaka.)”

WSJ reviews “Superconvergence”: ““Our world today is more livable for more of us than at any point in human history,” Mr. [Jamie] Metzl asserts. In the words of a 2013 Oxford report that he cites: “Now is the best time in history to be alive.” What’s more, humanity is just getting going. Revolutions in genetics, biotechnology and artificial intelligence are amplifying one another—and converging. Some may worry about the dangers of interfering with nature, but Mr. Metzl, a former White House fellow and science autodidact, thinks that such worry is misplaced. We’ve been “meddling with living systems over tens of thousands of years,” he writes, and the effort has worked out pretty well for our species. Now he foresees exponential progress. It is possible, he says, to imagine scientists “unleashing the miracle of human innovation on a planetary level,” giving us the capacity to “redirect evolution and recast life in all its dimensions.” Propelling Mr. Metzl’s breathless narrative is the conviction (shared by many “exponential” thinkers in Silicon Valley) that we’re not just getting better but getting better faster, in part because of global interconnectivity.”

FT: “Ceteris paribus — all else being equal — is a popular principle in the study of social science. By assessing the partial impact of one variable upon another, practitioners can develop causal theories. Sometimes, however, this can encourage blinkered thinking. The appeal of causal models lies in their simplicity. Rule of thumb is often preferred to convoluted explanations. Emphasis is placed on theories that pitch schools of thought against one another, Keynesianism versus Monetarism, for example. But the real world is a complex system full of feedback loops, reverse causality and tipping points. Ceteris paribus is an essential tool for controlled studies, but in an evolving economic, technological or social environment, following the principle of mutatis mutandis — changing what needs to be changed — is essential.”

Edmund Phelps: “My focus is on grassroots innovation – ordinary people, as I call them, participating in the economy, using their imagination to create new products and new methods of production. My indigenous theory differs sharply from Schumpeter’s theory in which innovation is exogenous coming mostly from scientists and navigators outside of the economy. Western societies are rife with dissatisfaction and despair. For some time I have been pointing to the loss of modern values – mainly individualism (not to be confused with selfishness), vitalism, and the desire for self-expression –  as a major cause of the loss of dynamism, thus the slowdown of innovation and economic growth. This is not to say there is no innovation happening. We’ve still got a few geniuses out there, some of whom have new ideas of immense commercial value. But we’re not going to get anywhere close to the mass of innovation that we had from the 1880s until about 1970 until a more fundamental shift in societal values occurs. With the vast and ever widening rift between the political left and right, I find it hard to imagine that the needed changes will occur soon.”

Commerce Metaverse: Shaping Marketing’s Future with Agentic AI and Digital Twins

Published August 15, 2024

1

Metaverse Redux

The metaverse, once a buzzword that dominated tech conversations and corporate strategies, seems to have faded from the spotlight as quickly as it emerged. Just a couple of years ago, every business conference featured sessions on metaverse strategies, and companies scrambled to establish their presence in this new digital frontier. The opening keynote at a Chicago eCommerce event I attended was entirely focused on the metaverse, reflecting its perceived importance in shaping the future of digital interactions. However, as with many hyped technologies, the initial excitement has waned, and discussions about the metaverse in business circles have become increasingly rare.

Yet, as is often the case in the ever-evolving world of technology, we find ourselves on the cusp of a metaverse renaissance – a metaverse redux in the form of the Commerce Metaverse. This new iteration, however, promises to be fundamentally different from its predecessor (the Consumer Metaverse). Instead of focusing on gaming experiences or creating a ‘second life’, this emerging metaverse is poised to revolutionise the relationship between marketers and their customers, and therefore (e)commerce itself. At its core will be the interaction between AI-powered digital twins, ushering in a new era of personalised, efficient, and effective marketing.

In this human-centric metaverse, the key players will be the Co-Marketer and Customer Twins. These AI-driven entities will form the backbone of future ecommerce strategies, creating a sophisticated ‘mirror world’ that reflects and anticipates customer behaviours, preferences, and needs. This Commerce Metaverse will serve as a transformative force, reshaping how businesses engage with their customers, dramatically reducing AdWaste, and propelling companies towards their “Profipoly Quest” – the pursuit of exponential forever profitable growth in an increasingly competitive digital landscape.

Imagine a world where marketers can engage in meaningful conversations with Segment Twins, AI representations of specific customer clusters. These interactions will provide unprecedented insights into customer likes, dislikes, and behaviours, allowing for the refinement of marketing communications to levels of personalisation previously unattainable. Gone will be the days of broad, untargeted messaging; instead, each communication will be tailored to resonate with its intended audience.

Furthermore, the collaboration between marketers and Singular Twins – AI replicas of individual customers – will revolutionise the concept of N=1 hyper-personalisation. This partnership will eliminate wasteful marketing efforts by ensuring that each customer receives only the most relevant and appealing offers. The result of this targeted messaging will be a marketing ecosystem that is not only more effective but also more respectful of the customer’s time and attention.

The Commerce Metaverse represents more than just a technological advancement; it signifies a fundamental shift in how we conceptualise and execute marketing strategies. By creating a virtual environment where AI-powered entities can interact, test scenarios, and generate insights, we’re entering an era of marketing that is simultaneously more data-driven and more human-centric.

In this series, we’ll explore the intricacies of this new Commerce Metaverse, building upon the foundation laid in previous discussions about AI-powered Digital Twins. We’ll examine how this mirror world of customer twins will function, the technologies that will drive it, and the implications it holds for the future of marketing, customer relationships, and business growth.

Drawing parallels between technology domains, we will explore the “Industrial Metaverse’” – where digital twins have revolutionized manufacturing and supply chain management. By examining how these virtual representations optimize machine performance and predict maintenance needs, we’ll uncover valuable insights applicable to the marketing realm. This cross-pollination of ideas will reveal how the precision and predictive power achieved in industrial applications can be harnessed to create more efficient, responsive, and personalised marketing strategies. Just as digital twins in industry have led to smarter factories and more resilient supply chains, their marketing counterparts promise to usher in an era of hyper-personalised customer experiences and data-driven decision making.

2

Metaverse – 1

Wikipedia provides an overview of the metaverse: “The metaverse is a loosely defined term referring to virtual worlds in which users represented by avatars interact, usually in 3D and focused on social and economic connection. The term metaverse originated in the 1992 science fiction novel Snow Crash as a portmanteau of “meta” and “universe”. In Snow Crash, the metaverse is envisioned as a hypothetical iteration of the Internet as a single, universal, and immersive virtual world that is facilitated by the use of virtual reality (VR) and augmented reality (AR) headsets.”

Wired adds: “To help you get a sense of how vague the term “the metaverse” can be, here’s an exercise: Mentally replace the phrase “the metaverse” in a sentence with “cyberspace.” Ninety percent of the time, the meaning won’t substantially change. That’s because the term doesn’t really refer to any one specific type of technology, but rather a broad (and often speculative) shift in how we interact with technology. And it’s entirely possible that the term itself will eventually become just as antiquated, even as the specific technology it once described becomes commonplace. Broadly speaking, the technologies companies refer to when they talk about “the metaverse” can include virtual reality—characterized by persistent virtual worlds that continue to exist even when you’re not playing—as well as augmented reality that combines aspects of the digital and physical worlds. However, it doesn’t require that those spaces be exclusively accessed via VR or AR. Virtual worlds—such as aspects of Fortnite that can be accessed through PCs, game consoles, and even phones—have started referring to themselves as “the metaverse.””

TechTarget writes: “The metaverse reached the peak of hype and has been left for dead, but make no mistake, the technologies that will power this 3D internet are firing on all cylinders… Today, companies use the term metaverse to refer to many different types of enhanced online environments. These range from online video games like Fortnite to virtual workplaces like Microsoft Mesh or Meta’s Horizon Workrooms to virtual dressing rooms and virtual operating rooms. Rather than a single shared virtual space, the current version of the metaverse is indeed shaping up as a multitude of metaverses with limited interoperability as companies jockey for position. The combination of uncritical enthusiasm for the metaverse and uncertainty about how it will pan out has some industry watchers questioning if the metaverse will ultimately be much different from the digital experiences we have today — or, if it is, whether the masses will be willing to spend hours a day in a headset navigating digital space… What will the metaverse mean for the average user?…On the positive side, an immersive metaverse enables humans to go where they were never able to go before, including outer space. Online social connections can also become much richer. On the other hand, the bad behavior witnessed on social platforms has the potential to be magnified in a virtual world, and metaverse usage could be addictive to some people.”

3

Metaverse – 2

I asked Claude for a history and current state of the metaverse:

  1. Origins and Early Concepts:
  • The term “metaverse” was coined by Neal Stephenson in his 1992 science fiction novel “Snow Crash”
  • Early virtual worlds like Second Life (launched 2003) provided a basic framework for shared online spaces
  1. Gaming Industry Developments:
  • Massively multiplayer online games (MMOs) like World of Warcraft (2004) popularized persistent online worlds
  • Fortnite (2017) introduced live events and concerts within a game environment, expanding the concept of virtual shared experiences
  1. Technological Advancements:
  • Virtual Reality (VR) and Augmented Reality (AR) technologies improved significantly in the 2010s
  • Oculus Rift (2016) and subsequent VR headsets made immersive experiences more accessible
  1. Corporate Interest and Investment:
  • Facebook rebranded as Meta in 2021, signaling a major push towards metaverse development
  • Other tech giants like Microsoft, Google, and Apple increased investments in metaverse-related technologies
  1. Current State:
  • The metaverse remains largely conceptual, with no single, unified virtual world
  • Multiple platforms offer metaverse-like experiences (e.g., Roblox, Decentraland, The Sandbox)
  • Initial hype has cooled, but development continues across various sectors
  • Focus has shifted from consumer applications to enterprise solutions and industrial use cases
  • Challenges remain in areas of interoperability, user adoption, and creating compelling long-term engagement
  1. Emerging Trends:
  • Increased focus on practical applications in fields like education, healthcare, and remote work
  • Growing interest in decentralized metaverse concepts, often incorporating blockchain and cryptocurrency elements
  • Exploration of AI integration to create more dynamic and responsive virtual environments
  1. Future Outlook:
  • The metaverse concept is evolving towards more practical and focused applications
  • Full realization of a comprehensive, interconnected metaverse is likely still years away
  • Continued technological advancements in AR, VR, and AI will shape its development

I then asked Claude for an analysis of why the metaverse failed as a commercial platform and what could potentially revive it:

3 Reasons the Metaverse Failed as a Commercial Platform

  1. Lack of Compelling Use Cases:
    • The metaverse struggled to provide clear, practical value for everyday users beyond novelty experiences.
    • Many applications felt forced or unnecessary, failing to solve real-world problems or enhance daily life significantly.
  2. Technical Limitations and User Experience Issues:
    • High-quality VR hardware remained expensive and cumbersome for many users.
    • Issues like motion sickness, eye strain, and the isolating nature of VR headsets hindered widespread adoption.
    • The graphical quality and interactivity often fell short of user expectations set by traditional gaming and online experiences.
  3. Fragmentation and Lack of Interoperability:
    • Multiple competing platforms created a fragmented ecosystem, with no single, unified metaverse emerging.
    • Lack of standardization made it difficult for users to move assets or identities between different metaverse platforms.
    • This fragmentation also made it challenging for businesses to invest in and develop for the metaverse confidently.

3 Things That Could Revive the Metaverse

  1. Focus on Practical, Value-Driven Applications:
    • Shift towards solving real-world problems in areas like remote work, education, and professional training.
    • Develop applications that provide tangible benefits in productivity, collaboration, or skill development.
    • Create experiences that seamlessly blend with and enhance daily life rather than trying to replace it entirely.
  2. Technological Advancements and Improved Accessibility:
    • Develop more comfortable, affordable, and user-friendly VR/AR devices.
    • Improve graphics, haptic feedback, and overall immersion to create more compelling experiences.
    • Leverage AI to create more dynamic, responsive, and personalized metaverse environments.
  3. Standardization and Interoperability:
    • Establish industry-wide standards for metaverse development, allowing for easier integration between platforms.
    • Create systems for portable digital identities and assets that can move seamlessly across different metaverse spaces.
    • Foster collaboration between major tech companies and platforms to create a more unified metaverse ecosystem.

Could AI-powered Digital Twins be the future of the new Commerce Metaverse? Imagine a metaverse populated not just by avatars, but by sophisticated digital replicas of individuals and businesses (co-marketers), each powered by Agentic AI. These Digital Twins could interact, learn, and evolve in real-time, creating a dynamic and responsive virtual environment that mirrors and enhances our physical world. From personalised shopping experiences to virtual business negotiations, AI-powered Digital Twins could transform the metaverse from a mere digital playground into a powerful tool for commerce, education, and social interaction. This convergence of AI and the metaverse might just be the key to unlocking its true potential and widespread adoption.

The world of machines as manifested in the Industrial Metaverse is where we can learn from.

4

Industrial Metaverse – 1

A variant of the Consumer Metaverse is the “Industrial Metaverse.” Here is a summary of what’s been written about it.

Siemens: “The industrial metaverse is the concept of a digital world to mirror and simulate real machines and factories, buildings and cities, grids and transportation systems. By seamlessly integrating technologies like cloud and edge computing, industrial AI and digital twins, the industrial metaverse can optimize processes and drive sustainable practices, ultimately shaping the future beyond simulation… It will be a world which is always on (persistent), allows for the interaction of an infinite number of people and assets (concurrent), and offers the full immersion into a physics-based, photo-realistic and real-time simulation. In this digital environment people can break the barriers of distance and work together across countries and continents, enabling a whole new level of collaboration.”

Deloitte: “The industrial metaverse is the convergence of individual technologies that, when used in combination, can create an immersive three-dimensional virtual or virtual/physical industrial environment. As technology evolves, the industrial metaverse will likely allow access to these immersive 3D environments from any internet-connected device, including virtual reality (VR) and augmented reality (AR) devices, as well as smartphones, tablets, laptops, and equipment, from anywhere in the world. The manufacturing industry appears well-positioned for the adoption of the industrial metaverse. Given their continued focus on digital transformation and their journey toward the smart factory, the majority of companies surveyed have made significant investments and are already using the foundational technologies that power the industrial metaverse. Companies are generally either implementing technologies like data analytics, cloud computing, artificial intelligence (AI), 5G, and the Internet of Things technologies across multiple projects and processes, or they are currently experimenting with one-off projects. The same is true for digital twins, 3D modeling, and 3D scanning, which can all serve as building blocks for the immersive 3D environments of the industrial metaverse.”

Here are some of the use cases.

World Economic Forum published a briefing paper on the Industrial Metaverse. I asked ChatGPT to summarise its key points: “The industrial metaverse represents the next evolution of digital twin technology, extending beyond mere replicas of machinery or manufacturing plants to create a persistent 3D platform integrated across an organization’s entire value chain and product lifecycle. Enabled by technologies like extended reality (XR), robotics, IoT, AI, blockchain, and advanced computing and connectivity, this metaverse allows a bi-directional flow between real and virtual worlds. Key use cases in the industrial metaverse include virtual design, testing, production planning, operations monitoring, and maintenance. Companies are currently exploring initial proofs-of-concept, such as VR safety training and MR showrooms, with the vision of integrating these into comprehensive platforms.”

Here are two charts from the report about the future:

5

Industrial Metaverse – 2

Technology Review: “While definitions abound and it remains to be seen how the industrial metaverse will fully unfold, digital twins are increasingly viewed as one of its key applications. Used for everything from creating ecosystems when planning a new city to working out iterations of manufacturing processes, digital twins were first proposed in 2002 and later became a vital technology when the fourth industrial revolution accelerated automation and digitization across industries. Simply put, a digital twin is a virtual replica of a product or process used to predict how the physical entity will perform throughout its lifecycle…Thierry Klein, president of Bell Labs Solutions Research at Nokia [says]: “The industrial metaverse combines physical-digital fusion and human augmentation for industrial applications and contains digital representations of physical industrial environments, systems, assets and spaces that people can control, communicate, and interact with.”…Creating digital twins is just one of the many advantages of the industrial metaverse. Klein says the industrial metaverse can reach “a much larger scale with increasing complexity by creating digital twins of entire systems such as factories, airports, cargo terminals, or cities—not just digital twins of individual machines or devices that we have seen so far.””

Nokia: “Digital twins are one of the most promising applications of the early industrial metaverse. These virtual replicas of physical objects (for example, a jet engine, car or wind turbine) are already helping private and public organizations plan faster, improve processes, optimize operations and much more. As the industrial metaverse starts to take hold, its scale and complexity will increase exponentially. Enterprises and public sector agencies will be able to: create digital twins of entire environments, such as power grids, rail yards or even whole cities, use rich, real-time data to gain unparalleled operational insights, and not just experience the physical world in a virtual space, but actually control it.”

Capgemini: “Digital twins are virtual representations of real-life objects, processes, systems, and their interconnections. Employees are already using twins in enterprises to perform practical tasks, such as system simulation, monitoring, and maintenance – and all without having to interact with real-world objects. The industrial metaverse will take digital twins to a new level. This shift will become manifest via a progression from the Internet of Things, where data is exchanged between sensors in physical objects over networks, to the “Internet of Twins,” where an interconnection between digital objects and information flows creates an added dimension. In this Internet of Twins, workplace users will carry out co-design and co-simulate processes at scale. For example, we envisage a factory in which equipment, products, and people are all connected. And the way these elements operate – and their associated behaviors – could be simulated in a dynamic, virtual experience. Employees will encounter richer representations of the situations they encounter. Unlike in static consumer metaverses, these dynamic industrial metaverses will involve collaboration between different digital twins and their associated simulations. By working together, employees will use this dynamic space of systems and data to create solutions to the problems they find. This dynamic metaverse of interconnected machines and humans will form the basis for a new era, which we refer to as the “Internet of Experiences.””

Siemens’ Pham Thai Lai: “Digital twins and the industrial metaverse are closely intertwined. Digital twins serve as the foundation of the industrial metaverse, enhancing decision-making, enabling real-time replication and simulation, promoting interconnectivity and efficiency, and facilitating immersive experiences. This convergence between digital twins and the metaverse brings significant value to businesses by eliminating the limitations and risks inherent in the physical world, thereby unlocking new opportunities…[An] example is Siemens’ Digital Native Factory in Nanjing of China. The entire factory was simulated with a digital twin, which optimised the building, and detected and mitigated potential problems at an early stage. Planning errors, both small and big, which in the past would cost a lot of money and a lot of time, were completely avoided. And we continue to use the power of simulation during operations. The true benefit of this digital plant: manufacturing capacity increased by 200 per cent and productivity by 20 per cent.”

6

Industrial Metaverse – 3

This is from a conversation with Claude. I began by asking how digital twins help with the industrial metaverse.

Digital twins play a pivotal role in the development and functionality of the industrial metaverse. A digital twin is a virtual replica of a physical object, process, or system that allows for real-time monitoring and simulation. In the context of the industrial metaverse, digital twins extend beyond individual assets to encompass entire processes, production lines, and even factories, integrating seamlessly into the larger metaverse environment.

  1. Enhanced Monitoring and Maintenance: Digital twins enable continuous monitoring of physical assets, providing real-time data on performance, usage, and potential issues. This data helps in predictive maintenance, reducing downtime, and optimizing the operational efficiency of machinery and equipment. For example, sensors on a physical machine feed data to its digital twin, which then analyzes this data to predict when maintenance is required, preventing unexpected breakdowns.
  2. Simulation and Testing: Digital twins allow for the simulation of different scenarios without disrupting actual operations. This is crucial for testing new processes, equipment, or modifications in a risk-free virtual environment. Manufacturers can simulate the impact of changes on production lines, helping to identify potential problems and optimize configurations before implementation.
  3. Training and Skill Development: Digital twins provide a realistic and interactive environment for training employees. Workers can interact with virtual replicas of machinery and systems, gaining hands-on experience without the risks associated with live training on physical equipment. This is particularly useful for complex or hazardous operations, where safety is a major concern.
  4. Design and Development: In the design phase, digital twins enable virtual prototyping, allowing engineers to create and test digital models before physical prototypes are built. This accelerates the design process, reduces costs, and improves the quality of the final product. Virtual models can be adjusted and optimized iteratively, ensuring that the final design meets all specifications and requirements.
  5. Optimizing Production Processes: Digital twins integrate with IoT devices to collect and analyze data across the production lifecycle. This helps in optimizing workflows, improving resource allocation, and enhancing overall productivity. For instance, a digital twin of a production line can identify bottlenecks and suggest process improvements, leading to more efficient operations.
  6. Collaboration and Innovation: The industrial metaverse, powered by digital twins, fosters collaboration across different teams and locations. Engineers, designers, and operators can work together in a shared virtual environment, making real-time adjustments and innovations. This collaborative approach accelerates problem-solving and drives innovation by bringing together diverse perspectives and expertise.

I then asked about the future of the industrial metaverse, and the breakthrough technologies that can make it even bigger.

Future Vision of the Industrial Metaverse

  1. Seamless Integration: The industrial metaverse will evolve into a unified platform where digital twins, IoT, AI, and extended reality (XR) seamlessly integrate. This platform will enable real-time data sharing and collaboration across different stages of the production lifecycle, from design and testing to production and maintenance.
  2. Advanced Automation: With AI and machine learning at its core, the industrial metaverse will see increased automation in production processes. AI will enhance decision-making, optimize operations, and enable predictive maintenance, reducing downtime and improving efficiency.
  3. Enhanced Collaboration: Virtual environments will facilitate global collaboration, allowing teams from different locations to work together in real-time. This will drive innovation, streamline workflows, and reduce the time-to-market for new products.
  4. Sustainable Practices: The industrial metaverse will support sustainability by optimizing resource use, reducing waste, and enabling more efficient energy management. Virtual simulations will allow for testing of eco-friendly practices before implementation.

Breakthrough Technologies

  1. Extended Reality (XR): XR technologies, including virtual reality (VR), augmented reality (AR), and mixed reality (MR), will provide immersive and interactive experiences. These technologies will be crucial for training, remote maintenance, and virtual prototyping, making interactions with the digital twin more intuitive and realistic.
  2. Artificial Intelligence (AI) and Machine Learning (ML): AI and ML will enhance predictive analytics, autonomous decision-making, and process optimization. These technologies will enable more sophisticated simulations, real-time monitoring, and adaptive control systems within the industrial metaverse.
  3. Internet of Things (IoT): IoT devices will continue to proliferate, collecting vast amounts of data from physical assets. This data will feed into digital twins, providing real-time insights and enabling more accurate simulations and predictive maintenance.
  4. 5G and Advanced Connectivity: High-speed, low-latency 5G networks will be essential for the real-time data transmission required in the industrial metaverse. Improved connectivity will support remote operations, real-time collaboration, and seamless integration of various digital tools.
  5. Blockchain and Distributed Ledger Technologies: Blockchain will enhance security, transparency, and traceability in the industrial metaverse. It will enable secure data sharing, protect intellectual property, and ensure the integrity of transactions and communications.
  6. Edge and Cloud Computing: These technologies will provide the computational power needed for processing large datasets and running complex simulations. Edge computing will bring processing closer to the data source, reducing latency and enhancing real-time capabilities.
  7. Advanced Robotics and Automation: Robotics will become more integrated with AI and IoT, enabling smarter and more autonomous machines. These robots will collaborate with humans, perform complex tasks, and adapt to changing environments within the industrial metaverse.

I then asked about the use of Agentic AI in the industrial metaverse.

Agentic AI, characterized by autonomous and intelligent agents that can perform tasks, make decisions, and learn from their environment, has significant potential to transform the industrial metaverse. These AI agents can enhance various aspects of industrial operations, leading to increased efficiency, innovation, and adaptability. Here are some ways Agentic AI can be integrated into the industrial metaverse:

  1. Autonomous Operations and Decision-Making: Agentic AI can automate routine and complex decision-making processes, allowing for real-time adjustments and optimization of industrial operations. For instance, AI agents can autonomously manage production schedules, adjust machinery settings, and predict maintenance needs, reducing downtime and improving productivity.
  2. Predictive Maintenance and Fault Detection: AI agents can continuously monitor equipment and systems using data from IoT sensors. They can predict potential failures before they occur and schedule maintenance activities proactively. This predictive maintenance minimizes unplanned downtime, extends equipment life, and reduces maintenance costs.
  3. Real-Time Process Optimization: Agentic AI can analyze vast amounts of data from various stages of production in real-time, identifying inefficiencies and suggesting optimizations. For example, AI agents can adjust production parameters to optimize energy consumption, reduce waste, and enhance product quality.
  4. Enhanced Human-Machine Collaboration: In the industrial metaverse, AI agents can work alongside human operators, providing real-time assistance, guidance, and decision support. For instance, during complex assembly processes, AI agents can offer step-by-step instructions, detect errors, and suggest corrections, enhancing human performance and reducing errors.
  5. Supply Chain Management: AI agents can optimize supply chain operations by predicting demand, managing inventory levels, and coordinating logistics. They can autonomously negotiate with suppliers, manage procurement processes, and ensure timely delivery of materials, enhancing supply chain efficiency and resilience.
  6. Virtual Training and Skill Development: Agentic AI can create dynamic and interactive training environments within the industrial metaverse. AI-driven virtual trainers can adapt training programs based on individual learner performance, providing personalized feedback and simulating real-world scenarios for hands-on experience.
  7. Innovation and Product Development: AI agents can accelerate innovation by simulating product designs, testing prototypes, and analyzing performance data. They can explore a vast design space, identify optimal configurations, and predict the impact of design changes, significantly speeding up the product development cycle.
  8. Data Analysis and Insights: Agentic AI can process and analyze large datasets generated within the industrial metaverse, extracting valuable insights and trends. These insights can inform strategic decisions, improve operational efficiency, and drive continuous improvement across the organization.
  9. Security and Risk Management: AI agents can enhance cybersecurity within the industrial metaverse by monitoring network traffic, detecting anomalies, and responding to threats in real-time. They can also assess operational risks, predict potential disruptions, and implement mitigation strategies to ensure business continuity.

So, what can the Industrial Metaverse teach the Commerce Metaverse?

7

Wow!

Here is quick recap from my essay on Digital Twins in marketing, as written by Claude.

  1. Digital Twins in Marketing: The essay introduces the concept of AI-powered Digital Twins as a transformative force in marketing. These twins are dynamic, AI-driven virtual representations of individual customers or customer segments that continuously evolve based on real-time data and interactions.
  2. Types of Digital Twins: Two main types are discussed – Segment Twins (representing groups of customers with similar behaviors) and Singular Twins (representing individual customers). These twins enable marketers to achieve hyper-personalization (N=1) in their strategies.
  3. Integration of Martech and Adtech: The essay emphasizes the importance of integrating martech and adtech to create a seamless ecosystem for digital twins. This integration enhances the accuracy and relevance of customer profiles.
  4. AI-First Marketing Stack: A comprehensive stack is outlined, including foundational Large Language Models, a Foundational Marketing Model, a Fine-Tuned Enterprise Model, a Co-Marketer, and Digital Twins. This stack enables the creation of highly personalized marketing experiences.
  5. Co-Marketer Concept: The essay introduces the idea of a Co-Marketer, an AI-powered marketing assistant that interacts with digital twins to optimize strategies and ensure every customer touchpoint is personalized and effective.
  6. Benefits of Digital Twins: Key advantages include hyper-personalization, optimized customer journeys, implementation of generative journeys, enhanced customer lifetime value (LTV), and reduced customer acquisition costs (CAC).
  7. Real-World Applications: The essay provides examples of how digital twins can be used in various aspects of marketing, including customer support, dynamic pricing, product development, cross-selling, customer retention, and enhanced analytics.

Think of the Commerce Metaverse as a Mirror World where the Co-Marketer can interact with Digital Twins of personas (Segment Twins) and persons (Singular Twins). Let’s consider some use cases and scenarios.

  1. Personalised Product Recommendations: In this Commerce Metaverse, the Co-Marketer interacts with a Singular Twin of a customer named Arun. By analysing Arun’s past purchases, browsing history, and current life events (e.g., recent move to a new city), the Co-Marketer and Singular Twin collaborate to curate a personalised list of book recommendations. This could include a mix of his favourite genres, guides about his new city, and new releases that align with his evolving interests. This list is built via collaboratively through a conversation with the digital twins (Co-Marketer and Arun).
  2. Targeted Marketing Campaigns: The Co-Marketer engages with a Segment Twin representing “Young Urban Professionals”. Through this interaction, it gains insights into the segment’s current trends, pain points, and aspirations. Based on this, the Co-Marketer designs a marketing campaign for a new line of productivity and self-improvement books, tailoring the messaging, visuals, and channel strategy to resonate specifically with this segment.
  3. Dynamic Pricing Strategy: In the Commerce Metaverse, the Co-Marketer simulates interactions with multiple Singular Twins to test various pricing strategies for a highly anticipated new release. By observing how different customer profiles react to various price points and bundle offers, the Co-Marketer can recommend an optimal pricing strategy that maximises both sales and customer satisfaction.
  4. Predictive Customer Service: The Co-Marketer regularly interacts with Singular Twins to identify potential customer service issues before they arise. For instance, it might notice that a customer’s Singular Twin shows a pattern of abandoning e-book downloads midway. The Co-Marketer can then proactively reach out to the real customer with troubleshooting tips or offer assistance, preventing frustration and potential churn.
  5. Community Building and Event Planning: In the Commerce Metaverse, the Co-Marketer interacts with multiple Segment Twins representing different reader communities (e.g., “Mystery Lovers”, “Sci-Fi Enthusiasts”, “Cooking Aficionados”). Through these interactions, it identifies common interests, preferred event formats, and optimal timing. Based on these insights, the Co-Marketer plans a series of virtual author meet-and-greets and book club events, tailored to each community’s preferences, significantly boosting engagement and fostering a sense of belonging among customers.

This is no longer in the realm of science-fiction. The Age of Agentic AI is dawning, bringing these new interactions to life. As the Internet of Things connects physical devices, the Interaction of Twins will create a dynamic ecosystem of virtual entities, revolutionising how businesses understand and engage with their customers. This new paradigm promises unprecedented levels of personalisation and predictive capability in marketing and customer relationships, creating for “Wow” moments and experiences.

8

Parallels

I asked ChatGPT and Claude to imagine the future of the Commerce Metaverse, with learnings from the Industrial Metaverse.

ChatGPT

Digital Twins

  • Industrial Metaverse:
    • Role: Digital twins represent machines, production lines, and entire factories, enabling real-time monitoring, simulation, and optimization.
    • Benefits: Enhance operational efficiency, predictive maintenance, and process optimization.
  • Commerce Metaverse:
    • Role: Digital twins represent customer segments (Segment Twins) and individual customers (Singular Twins), providing detailed insights into behaviors and preferences.
    • Benefits: Enable hyper-personalization, targeted marketing, and improved customer experience.
  1. Agentic AI
  • Industrial Metaverse:
    • Role: Autonomous AI agents manage production schedules, optimize processes, and predict maintenance needs.
    • Benefits: Reduce downtime, enhance productivity, and automate decision-making.
  • Commerce Metaverse:
    • Role: Co-Marketers, powered by AI, interact with digital twins to personalize recommendations, manage dynamic pricing, and enhance customer service.
    • Benefits: Optimize marketing strategies, reduce ad waste, and provide predictive customer service.
  1. Extended Reality (XR)
  • Industrial Metaverse:
    • Role: XR technologies (VR, AR, MR) provide immersive training environments, virtual prototyping, and remote maintenance support.
    • Benefits: Improve training effectiveness, reduce prototyping costs, and enable remote operations.
  • Commerce Metaverse:
    • Role: XR technologies create virtual shopping environments, interactive product demonstrations, and engaging marketing campaigns.
    • Benefits: Enhance customer engagement, provide immersive experiences, and facilitate virtual events.
  1. Internet of Things (IoT)
  • Industrial Metaverse:
    • Role: IoT devices collect data from physical assets, feeding into digital twins for real-time monitoring and analysis.
    • Benefits: Enable predictive maintenance, optimize resource use, and enhance operational visibility.
  • Commerce Metaverse:
    • Role: IoT devices collect data from various touchpoints, providing insights into customer interactions and behaviors.
    • Benefits: Enable real-time personalization, improve customer insights, and optimize marketing efforts.
  1. Data Integration and Analytics
  • Industrial Metaverse:
    • Role: Integrates data across production processes, enabling comprehensive analysis and real-time decision-making.
    • Benefits: Improve process optimization, enhance decision-making, and drive continuous improvement.
  • Commerce Metaverse:
    • Role: Integrates customer data across touchpoints, enabling detailed customer profiling and predictive analytics.
    • Benefits: Enhance personalization, improve marketing effectiveness, and provide actionable insights.
  1. Blockchain and Security
  • Industrial Metaverse:
    • Role: Blockchain ensures data security, transparency, and traceability in industrial operations.
    • Benefits: Protects data integrity, secures transactions, and enhances trust.
  • Commerce Metaverse:
    • Role: Blockchain secures customer data, protects digital identities, and ensures the integrity of transactions.
    • Benefits: Enhances data privacy, builds customer trust, and secures marketing operations.
  1. Edge and Cloud Computing
  • Industrial Metaverse:
    • Role: Provides the computational power for processing large datasets and running complex simulations.
    • Benefits: Reduces latency, enhances real-time capabilities, and supports advanced analytics.
  • Commerce Metaverse:
    • Role: Supports real-time data processing, enabling timely insights and responsive marketing actions.
    • Benefits: Enhances real-time personalization, supports complex analytics, and improves customer interaction.
  1. Advanced Robotics and Automation
  • Industrial Metaverse:
    • Role: Integrates robotics with AI and IoT, enabling autonomous operations and human-robot collaboration.
    • Benefits: Increases operational efficiency, enhances safety, and supports complex tasks.
  • Commerce Metaverse:
    • Role: Uses AI to automate customer interactions, manage campaigns, and optimize marketing processes.
    • Benefits: Reduces manual effort, enhances campaign effectiveness, and improves customer satisfaction.

By drawing parallels between the Industrial Metaverse and the Commerce Metaverse, it becomes evident that advanced technologies like digital twins, Agentic AI, XR, IoT, and blockchain play a crucial role in transforming both sectors. These technologies enable real-time insights, enhanced personalization, and optimized operations, leading to more efficient, responsive, and customer-centric marketing strategies. The integration of these technologies will create a dynamic ecosystem where businesses can better understand and engage with their customers, ultimately driving growth and innovation in the digital age.

Claude

  1. Digital Twins:
    • Industrial: Digital replicas of physical assets, machines, and processes
    • Commerce: Digital replicas of individual consumers (Singular Twins) and market segments (Segment Twins)
  2. Real-time Monitoring:
    • Industrial: Continuous monitoring of equipment performance and production processes
    • Commerce: Real-time tracking of consumer behavior, preferences, and interactions across touchpoints
  3. Predictive Maintenance:
    • Industrial: Anticipating equipment failures and scheduling proactive maintenance
    • Commerce: Predicting customer churn and proactively addressing issues to maintain customer relationships
  4. Simulation and Testing:
    • Industrial: Virtual testing of new manufacturing processes or equipment configurations
    • Commerce: Simulating consumer responses to new products, services, or marketing campaigns
  5. Optimization:
    • Industrial: Optimizing production processes for efficiency and output
    • Commerce: Optimizing marketing strategies, customer journeys, and personalization for maximum engagement and conversion
  6. Training and Skill Development:
    • Industrial: Virtual training environments for workers
    • Commerce: AI-powered learning systems for marketers to improve skills and test strategies
  7. Collaboration:
    • Industrial: Cross-functional teams working together in virtual environments
    • Commerce: Marketers collaborating with AI Co-Marketers and interacting with Digital Twins
  8. Data Integration:
    • Industrial: Combining data from various sensors and systems
    • Commerce: Integrating data from multiple channels, CRM systems, and external sources
  9. Sustainability:
    • Industrial: Optimizing resource use and reducing waste
    • Commerce: Personalizing experiences to reduce marketing waste and improve efficiency
  10. AI and Machine Learning:
    • Industrial: AI-driven automation and decision-making in manufacturing
    • Commerce: AI-powered personalization, predictive analytics, and automated campaign optimization

By leveraging these parallels, the Commerce Metaverse can adopt and adapt the successful strategies and technologies from the Industrial Metaverse to create a more efficient, personalized, and effective marketing ecosystem.

**

[Rajesh] The Commerce Metaverse, powered by Agentic AI and Digital Twins, stands poised to revolutionise marketing and customer engagement. By drawing inspiration from the Industrial Metaverse, it promises to create a dynamic, responsive ecosystem where businesses can understand and interact with their customers at unprecedented levels of personalisation and efficiency. As we stand on the brink of this new era, the convergence of AI, digital twins, and metaverse technologies offers exciting possibilities for creating meaningful connections, driving innovation, and delivering value. The future of marketing lies not just in selling products, but in crafting unique, personalised experiences that resonate with each customer, ushering in a new age of commerce where every interaction has the potential to be a “Wow” moment. The Commerce Metaverse is the key to unlock the Profipoly future.

Thinks 1322

Technology Review: “Etienne Boulter walked into his lab at the Université Côte d’Azur in Nice, France, one morning with a Lego Technic excavator set tucked under his arm. His plan was simple yet ambitious: to use the pieces of the set to build a mechanical cell stretcher. Boulter and his colleagues study mechanobiology—the way mechanical forces, such as stretching and compression, affect cells—and this piece of equipment is essential for his research. Commercial cell stretchers cost over $50,000. But one day, after playing with the Lego set, Boulter and his colleagues found a way to build one out of its components for only a little over $200. Their Lego system stretches a silicone plate where cells are growing. This process causes the cells to deform and mimics how our own skin cells stretch. Sets like these are ideal to repurpose, says Boulter: “If you go to Lego Technic, you have the motors, you have the wheels, you have the axles—you have everything you need to build such a system.” Their model was so successful that 10 different labs around the world contacted him for the plans to build their own low-cost Lego stretchers. Boulter is one of many researchers turning to Lego components to build inexpensive yet extremely effective lab equipment.”

FT: “In The Anxious Generation, published this spring, American social psychologist Jonathan Haidt confirms many fears for those children who have transitioned from a “play-based” childhood to a “phone-based” childhood in a phenomenon he calls “The Great Rewiring” — one that he associates with a range of mental health issues. Haidt suggests simple but radical reforms including no smartphones before high school, no social media before the age of 16, and more time spent on unsupervised play. That, to my mind, is also a call for a return to reading, not as a niche activity, but as an essential part of growing up. If access to books is increasingly limited, with library closures widening the equality gap, the single biggest challenge for parents, librarians and schools is this: how do you make reading attractive to children?”

Freya India: “And so, many of us don’t have friends anymore; we have followers. We don’t deeply care about each other’s lives; we consume them as content. We don’t have people we can be vulnerable with; we have people who view our Stories. It’s hard to tell if we have loyalty, or just people hoping we like their photo back. Nowadays we meet someone new and immediately exchange socials and end up committing to scrolling and skipping through each other’s lives, forever. Friends are for keeping up Snapstreaks. Friends are for forwarding each other memes that our algorithms sent us first. Friends are numbers. Sometimes it feels like the only one left asking us “What’s on your mind?” is Facebook.” [via Arnold Kling]

W.H. Hutt: “The consumer is sovereign when, in his role of citizen, he has not delegated to political institutions for authoritarian use the power which he can exercise socially through his power to demand (or to refrain from demanding).” [via Art Carden]

AI-Powered Digital Twins: Marketing’s Marvel

Published August 14, 2024

1

Past Writings – 1

Digital Twins will transform marketing. Powered by AI, Segment Twins and Singular Twins these twins will help marketers bridge the ga between adtech and martech, achieve the twin objectives of increasing customer LTV (lifetime value) lowering CAC (customer acquisition cost), and help with profitable growth. Let’s begin by reviewing some of my recent writings on Digital Twins.

How Agentic AI will Transform Digital Marketing:

The advent of Agentic AI is poised to revolutionise the way businesses approach customer relationships and lifetime value maximisation. At the core of this transformation lies the concept of “Digital Twins” – AI-driven virtual representations of individual customers that possess a profound understanding of their behaviours, preferences, and interactions.

Digital Twins are not mere static customer profiles; they are dynamic, continuously evolving models that mirror the real-world customer’s journey with a brand. Powered by ML algorithms, large customer models (LCMs), and vast troves of customer data, Digital Twins become living embodiments of the customer experience.

The creation of these Digital Twins begins with the aggregation and analysis of data from various sources, including CRM systems, purchase histories, browsing patterns, social media interactions, and demographic information. This could even be augmented with real-world news and events which could impact shopping behaviour. This data is then fed into sophisticated LCMs, akin to the large language models used in natural language processing, enabling them to learn and adapt to the unique characteristics of each customer.

As customers interact with a brand across various touchpoints, their Digital Twins continuously analyse and incorporate these interactions, refining their understanding of the customer’s preferences, needs gaps, pain points, and potential future actions. This deep, personalised understanding empowers Digital Twins to anticipate customer needs, make tailored recommendations, and guide the customer journey, thus enabling brands to maximising their lifetime value.

By leveraging the insights and recommendations provided by Digital Twins, brands can create highly targeted and effective marketing campaigns, offering products and services that resonate deeply with each customer’s unique needs and preferences. This level of hyper-personalisation (N=1) not only drives increased sales and customer loyalty but also fosters a sense of trust and connection between the brand and its customers.

Furthermore, Digital Twins empower brands to optimise customer journeys, ensuring that every touchpoint is tailored to the individual’s preferences and needs. From personalised content and messaging to dynamic promotions and predictive recommendations, Digital Twins enable brands to deliver a truly seamless and engaging customer experience.

The integration of Digital Twins and Agentic AI into marketing strategies represents a significant step towards realizing the true potential of customer relationships and maximizing lifetime value. By continuously updating customer profiles in real-time and providing actionable insights, Digital Twins ensure that every marketing message is highly personalized and timed to perfection, improving customer satisfaction, and enhancing the efficiency of marketing spend.

Generative Journeys: Digital Marketing’s New Core: Digital Twins in marketing create detailed virtual models of individual customers, allowing for highly personalised marketing strategies. By understanding and predicting customer behaviour, Digital Twins enable marketers to tailor their approach to each customer’s preferences and behaviours, enhancing engagement and maximising the customer lifetime value. Digital Twins have two interfaces – to a Co-Marketer and the real customers whom they is modelled on. They empower hyper-personalised marketing (N=1) by predicting needs, recommending relevant products, and optimising individual customer journeys. They operate in real-time, updating with each brand interaction to ensure perfectly timed, relevant communications and experiences. Within simulated “mirror world” environments, Digital Twins interact with Co-Marketers to test and identify winning strategies for each customer. By unlocking this granular, AI-powered understanding of customers, Digital Twins also enhance loyalty and trust. They herald a new era of truly customer-centric, profitable marketing.”

2

Past Writings – 2

CEO Memo: How Agentic AI can Power the Profipoly Quest: “Start by imagining what this future can be for your customers. For eCommerce, imagine every shopper’s digital twin interacting with a Co-Marketer to eliminate the tyranny of irrelevant messages and offers to get the right product recommendations at the right time. For a stock broking business, imagine a Co-Broker who can assimilate all the incoming news, distil trends, and then make portfolio suggestions. For a travel business, imagine a travel assistant for every customer being their advisor during the decision-making process and a guide during the actual travel. What’s common to these scenarios are three things: N=1 Hyper-personalisation, which ensures that the recommendations and pathways are unique for every customer; Agent-to-Agent interaction, which creates efficiency in the engagement process, by focusing on the best options and filtering out the irrelevant; Value-maximising journeys, which are composable, omnichannel, generative, shoppable, to ensure faster conversion… As your Large Customer Model learns from real-world interactions (and events), your Mirror World simulations become more accurate. As your Digital Twins interact with your Co-Marketer, they uncover new insights and strategies. And as you deploy Generative Journeys, you’re continuously learning and adapting to each customer’s evolving needs… With Agentic AI, engagement isn’t just about sending the right message at the right time. It’s about creating a seamless, adaptive, and value-adding experience across every touchpoint. Your Co-Marketer tests messages with the customer’s Digital Twin, and then engages the real customer with the right content and recommendations to create a “hotline” where no message from your brand is ignored.”

Email, CPaaS, and Martech: New Profit Pools: “Martech companies can significantly enhance customer Lifetime Value (LTV) by evolving from predictive and generative AI to agentic AI. This advanced approach involves transforming the Customer Data Platform (CDP) into a Large Customer Model (LCM), enabling the creation of digital twins and a co-marketer. These components can work together in a “mirror world” to drive “generative journeys,” resulting in N=1 hyper-personalisation for every customer. This next-generation software platform provides a competitive edge, allowing martech companies to deliver unprecedented engagement, conversion, and retention – thus eventually reducing the need for wasteful adtech spending, and enabling brands on their “profipoly quest.””

Martech’s 10+1 Foundations in the AI Age: “With the Unistack and Unichannel foundation in place, martech companies will need to rebuild their stack for AI. This will mean moving from predictive and generative AI to “Agentic AI.” This new stack will comprise five layers: Large Customer Models (LCMs), Digital Twins, Co-Marketer, Mirror World, and Generative Journeys…These AI-powered replicas of individual customers predicting needs and actions for 1:1 personalisation at scale. With Digital Twins, AI agents can simulate millions of individualised interactions, tailoring pitches and follow-ups to each customer’s preferences. This approach scales personalised engagement, creating virtual sales companions that provide bespoke experiences, effectively merging sales and marketing into a seamless, white-glove service.”

Large Customer Model: Foundation for AI-first Martech: “In the Mirror World, Digital Twins (virtual replicas of individual customers) interact with a Co-Marketer (an AI-powered marketing assistant) to identify the most effective strategies and personalized experiences for each customer… Large Customer Models,  along with their applications in Generative Journeys, Co-Marketers, and Digital Twins, herald a new era of AI-driven, customer-centric marketing that fosters stronger, more meaningful connections between brands and their customers, driving long-term growth and competitive advantage.”

Marketing’s AI Triad: Large Customer Model, Digital Twins, Co-Marketer:

The Large Customer Model allows for the creation of two types of digital twins: Segment Twins and Singular Twins.

Segment Twins are AI-powered models representing groups of customers who share similar behaviours, preferences, and demographic characteristics. By leveraging data from various sources such as customer data platforms (CDPs), marketing automation tools, and adtech platforms, Segment Twins analyse vast amounts of behavioural and interaction data. This includes interests, engagement patterns, and demographic details from platforms like Google, Meta, Instagram, and TikTok. These twins provide a comprehensive view of customer segments, enabling marketers to tailor strategies more effectively. By simulating these segments, brands can craft targeted and impactful marketing campaigns, ensuring higher relevance and engagement. More interestingly, marketers can converse with these twins to better understand the mindset. [See this post by Gautam Mehra.]

Singular Twins are AI-powered replicas of individual customers, capturing detailed insights into their preferences, behaviours, and interactions. These dynamic models continuously evolve, reflecting real-time customer journeys. By aggregating data from sources like CRM systems, purchase histories, browsing patterns, social media interactions, and demographic information, Singular Twins provide a comprehensive understanding of each customer. Operating within a simulated environment, or “mirror world,” Singular Twins interact with the brand’s Co-Marketer, an AI-powered assistant, to test various scenarios and identify optimal engagement strategies. This facilitates true 1:1 personalisation, allowing brands to deliver highly targeted and effective marketing campaigns by anticipating next actions. The integration of Singular Twins enables brands to anticipate customer needs, make tailored recommendations, and optimise customer journeys, ensuring every touchpoint is personalised.

The integration of AI-powered Segment Twins and Singular Twins will revolutionise marketing by providing unparalleled insights and personalisation. Segment Twins enable marketers to understand and target customer groups with precision, crafting campaigns that resonate deeply with specific demographics. Singular Twins, on the other hand, offer a granular view of individual customers, allowing for real-time, 1:1 personalised interactions. Together, these digital twins transform marketing from a broad, impersonal approach to a highly tailored strategy, driving engagement, customer satisfaction, and ultimately, higher conversion rates and loyalty. This shift not only enhances marketing efficiency but also fosters stronger, more meaningful customer relationships, positioning brands for sustained success in the AI era.

3

More – 1

Digital Twins have a long history and widespread use across industries. Here is some background and recent news on Digital Twins.

Digital Twin Consortium defines a digital twin: “A digital twin is a virtual representation of real-world entities and processes, synchronized at a specified frequency and fidelity. Digital twin systems transform business by accelerating holistic understanding, optimal decision-making, and effective action. Digital twins use real-time and historical data to represent the past and present and simulate predicted futures. Digital twins are motivated by outcomes, tailored to use cases, powered by integration, built on data, guided by domain knowledge, and implemented in IT/OT systems.”

Technology Review: “The concept of digital twins was introduced in 2002 by Michael Grieves, a researcher whose work focused on business and manufacturing. He suggested that a digital model of a product, constantly updated with information from the real world, should accompany the physical item through its development. But the term “digital twin” actually came from a NASA employee named John Vickers, who first used it in 2010 as part of a technology road map report for the space agency…Since those early days, technology has advanced, as it is wont to do. The Internet of Things has proliferated, hooking real-world sensors stuck to physical objects into the ethereal internet. Today, those devices number more than 15 billion, compared with mere millions in 2010. Computing power has continued to increase, and the cloud—more popular and powerful than it was in the previous decade—allows the makers of digital twins to scale their models up or down, or create more clones for experimentation, without investing in obscene amounts of hardware. Now, too, digital twins can incorporate artificial intelligence and machine learning to help make sense of the deluge of data points pouring in every second.”

Celonis: “Digital twin technologies began life in manufacturing. The digital representation of a physical object, product, or component has allowed manufacturers and product developers to assess the suitability of designs and any areas for optimization, as well as gauge resource demands and construction requirements. This can all happen before production begins, but even after production is underway digital twins can be used to improve the manufacturing process. They can even be used to decide what to do with products when they reach the end of their lifecycle…Digital twin technology can be applied to more than just a physical asset. Businesses are using process mining to construct a digital twin model of the processes that support their entire organization, using tasks, activities, and transactions drawn from system data (in much the same way a physical digital twin uses sensor data). This process digital twin, or Digital Twin of an Organization, is a living, breathing virtual replica, fed with real-time data, that businesses can use to explore and scrutinize processes at a granular and high-level view. Everything from bottlenecks to duplicated processes and disconnects can be inspected, diagnosed, and triaged.”

The Verge: “[Zoom founder] Eric ]Yuan] really wants you to stop having to attend Zoom meetings yourself…He thinks one of the big benefits of AI at work will be letting us all create something he calls a “digital twin” — essentially a deepfake avatar of yourself that can go to Zoom meetings on your behalf and even make decisions for you while you spend your time on more important things, like your family.” Eric: “Your digital twins, multiple digital twins, are different based on your training. One digital twin is really more like a sales expert; another digital twin of yourself is more like an engineering expert. Again, you manage that. Whenever you send a digital twin of yourself to join any other meetings, any other digital context, we know that they’ll be authentic given AI-based authentication.”

4

More – 2

Solutions Review: “Digital Twins use realistic representations of physical objects to help businesses better understand the behavior of real-world assets, systems, and processes. By collecting vast amounts of real-world data, often in real-time, organizations can model the behavior of industrial machines to study the precise conditions under which they’re likely to fail. They can simulate physical assets like wind turbines and aircraft engines to identify minute inefficiencies. They can analyze complex systems to identify opportunities to lower costs, improve quality, and proactively prevent problems…A Digital Twin is a virtual replica of a physical object or system that’s designed to mirror its real-world counterpart as closely as possible. Digital Twins typically start with a conceptual model, such as one generated from computer-assisted design (CAD), building information modeling (BIM), or geographic information system (GIS) tools. Rather than staying static, however, this model continually evolves as organizations collect data about their physical counterparts from sensors, real-time data streams, or any other data source. They can then apply insights gleaned from the Digital Twin back to the physical world in a continuous feedback loop—such as recalibrating robots on an assembly line to improve quality or rerouting traffic in a Smart City.”

Bloomberg: “Digital twins have been used for decades in industrial sectors such as aerospace engineering and more recently in car manufacturing. With blueprints and real-time data from sensors, engineers can approximate performance in extreme conditions — a jet engine in severe weather, for example — and predict maintenance needs. Though definitions are evolving, digital twins typically require a two-way flow of information: Real-world data from a physical object goes into a model, then the model forecasts outcomes for the real-world object.” The article discusses a very specific application: “Glioblastoma is one of the most common, aggressive and deadly forms of brain cancer. The prognosis — with median survival of 15 to 18 months after diagnosis — hasn’t changed in more than half a century. A major challenge in treating glioblastoma is that tumors vary widely among patients and the cells within them aren’t uniform. Too often, selecting the right combination of invasive surgeries, radiation and chemotherapy amounts to high-stakes guesswork. A “digital twin” of the brain tumor could help. Thanks to the leaps forward in artificial intelligence and mathematical modeling over the past decade, doctors can now create a virtual copy of the affected area in a specific patient using genetic information, medical records, blood tests and scans. With a digital twin, doctors can detect abnormalities before physical symptoms emerge, project how tumors will develop, and determine which combination of surgeries and treatments will deliver the best outcomes.”

Wall Street Journal: “The U.S. Air Force announced [recently] its latest initiative to unleash the power of “digital twins”—computerized simulators that mimic real-world systems with almost perfect accuracy. This bold effort, dubbed Model One, integrates 50 top military simulations into a unified system to adapt to the ever-evolving landscape of digital warfare… The rise of virtual technology, including digital twins, hasn’t been as flashy as videogaming’s virtual realities, but it’s quietly reshaping how industries conceive physical technology, from race cars to artificial hearts. As accurate simulations become stand-ins for physical testing, innovation becomes faster and less expensive. According to a recent Allied Market Research report, the global digital-twin industry is projected to grow 20-fold, from $6.5 billion in 2021 to $125.7 billion by 2030. Some pundits predict it will spark a new industrial revolution… Imagine billions of future technologies being digitally designed, tested, even certified each year…all without the time, cost, and environmental degradation of physical innovation. Now, picture AI learning to improve these designs, operate them, and even train humans. Then the hoped-for future of personalized medicine, sustainable energy, abundant agriculture and space colonization may become attainable.”

5

Fusion Strategy

A seminal book that discusses digital twins (among other things) is “Fusion Strategy: How Real-Time Data and AI Will Power the Industrial Future ”  by Vijay Govindarajan and Venkat Venkatraman. Here are a few excepts from the book:

It all starts with data, the crux of fusion. Not just any data, but real-time data on products in use. By systematically accumulating such data, companies can develop datagraphs, which capture the relationships, links, and interrelationships between a company and its customers through product-in-use data and are the fundamental building blocks of the fusion strategies… The concept of the datagraph is inspired by social networks and graph theory, and powered by AI and machine learning (ML). Datagraphs are derived from data network effects, which are triggered when a company’s product gets smarter as it gathers more data from users of the product.

…Industrial companies typically use one or more of three types of digital twins. A product twin represents the product in a virtual environment during the design and development stage (product as designed). A process twin is a digital representation of the end-to-end manufacturing process, including the role of suppliers and distributors (product as manufactured). And a more recent version, the performance twin, digitally represents the product in use to track and collect data on the factors that impact how the product performs in the field (product as deployed).

Often, industrials use digital twins in separate functions, delegating product twins to R&D units and design groups, assigning process twins to supply chain and operations teams, and leaving performance twins to the marketing and service functions. The benefits accrue along narrowly defined metrics if the twins are proposed, funded, and operated independently with boundaries. Industrial data network effects are created by linking the three digital twins: design, manufacturing, and deployment. We refer to this as a tripartite digital twin, or a tripartite twin for short.

The book discusses how Tesla uses digital twins: “Tesla has created a performance twin of every car it has made, not just a digital twin of every model as it was designed or a twin of the assembly line that created it. The sensors in each car provide data in real time about how the vehicle is performing on the road; the company’s AI/ML systems study the data in real time; and Tesla uses the most relevant data-driven insights to continuously improve all its cars’ autonomous driving systems. Moreover, the AI interprets the data and determines whether a vehicle works as intended or needs maintenance. With many issues, Tesla’s digital experts ensure that problems can be fixed with software updates; for instance, they can adjust the regenerative braking levels to reduce collision risks and adjust door rattling via over-the-air software updates. On average, it issues a major software update once every month. The company’s tripartite twins help it optimize future products with generative design, the emerging technology that applies AI to optimize designs. By aggregating real-time data from thousands of products in the field, the digital twins simulate the performance and conditions faced by the fusion product over its lifetime. Armed with this data, generative design software tweaks Tesla’s product designs and simulates performance in real-world situations until it arrives at a solution that satisfies the company’s goals.”

6

More Books

The Digital Twin by Noel Crespi, Adam T. Drobot, and Roberto Minerva (Editors): “Imagine the future of the global economy: imagine factories that produce experiences, with data flows replacing part supply. Imagine being able to represent and cure a human body as efficiently as we model and test a plane or a car. Imagine a clinical trial involving virtual patients and being evaluated using an AI engine. Digital twins – or virtual twin experiences as I rather name them – are unparalleled catalysts and enablers of this global transformation of the economy. Digital twins are representations of the world that combine modeling, simulation, and real-world evidence: in other words, they make it possible to understand the past while navigating the future… As they provide a multi-scale, multi-discipline, generative, holistic, and inclusive approach to innovation, virtual twin experiences based on collaborative platforms provide an inspiration for new offerings. Improving global health requires an inclusive perspective across cities, food, and education. Developing global wealth in a sustainable manner involves new synergies between data and territories. Digital twins make it possible to collaborate at scale through immersive virtual reality. They provide a continuum across disciplines and organizations. They connect biology, material sciences, mechanics, electronics, and chemistry. They allow to improve use through data intelligence. This translates into continuous improvements towards more sustainable industrial processes, enhanced and customized treatments, and the development of new services from the lab to the hospital nearby or the street downstairs. Combining the real and the virtual world thus leads to new ways of inventing, producing, treating, and learning.”

Digital Twins: Internet of Things, Machine Learning, and Smart Manufacturing by Yogini Borole, Pradnya Borkar, Roshani Raut, Vijaya Parag Balpande, and Prasenjit Chatterjee:

Digital twins come in a variety of forms depending on how magnified the product is. These twins most significantly diverge in the area of application. It is typical for various kinds of digital twins to coexist in a system or process.

Component twins or parts twins: Component twins are the core unit of a digital twin and the most basic representation of a functioning component. Parts twins are virtually the same thing as identical parts, despite the fact that they refer to far less important parts.

Asset twins: An asset is formed when two or more components perform well together. Asset twins allow you to investigate the interactions between these factors, generating a wealth of performance data that can be analysed and turned into insightful information.

System or unit twins: System or unit twins, which show how diverse assets work together to form a complete, usable system, are the next degree of magnification. System twins offer visibility into how assets interact and may make performance suggestions.

Process twins: Process twins describe how several systems interact to construct an entire production plant. Are all of those systems coordinated for maximum efficiency, or will delays in one system affect others? The specific timing schemes that eventually affect overall efficiency can be found with the use of process twins.

Artificial Intelligence-Augmented Digital Twins by Abdalmuttaleb M. A. Musleh Al-Sartawi, Anas Ali Al-Qudah, and Fadi Shihadeh (Editors): “Digital Twinning (DTW) aims to create a highly accurate virtual model of a physical system or process to simulate system behavior, condition monitoring, detection of abnormal patterns or errors, a reflection of system performance, and future trend prediction, which is highly beneficial for various sectors such as finance, banking, accounting, manufacturing, agriculture, and healthcare. Moreover, it helps to map between virtual and real-world resources, which can in turn support to identifying known unknowns as well as also help to discover unknowns. More specifically, advancements in Artificial Intelligence are transforming what they can do in the fields of accounting, finance, and banking. DTW is also made increasingly more intelligent by AI agents, to the point where it can prescribe actions in the physical world, so that banks and other financial institutions can change, in real-time, with fact-based choices, alternate processes to prevent bottlenecking issues for example. By deploying both AI and DTW, banks and accounting firms can obtain insights into their operations, allowing them to achieve significant benefits such as improved efficiency, cost savings, and enhanced sustainable development efforts. Therefore, DTWs are not only helping these firms to optimize operations and decision-making; they also play a critical role in enabling them to realize their ESG roles…By replicating the physical world, digital twins can support companies to better utilize resources, optimize supply and logistics networks, reduce carbon emissions, and improve employee safety.”

Handbook of Digital Twins by Zhihan Lyu (Editor): “A personal digital twin has been defined as a virtual version of an individual that is built from her digital footprint. Slightly different flavors of personal digital twin can be distinguished from different disciplines: in healthcare, the personal digital twin is steered toward a merger of all health data, supported by live sensor devices. The resulting human digital twin can be applied to visualization, simulation, and prediction. The approach in retail, digital marketing, and e-commerce is similar: by accumulating data from consumer behavior, a digital twin of the customer can be built and applied to produce better-targeted recommendations.”

7

In Marketing

Digital Twins, initially conceived for industrial applications and manufacturing, are now poised to revolutionise marketing. With the convergence of artificial intelligence (AI), big data, and advanced analytics, the marketing industry stands on the cusp of a transformative era. Here’s why now is the right time for digital twins in marketing and how marketers can harness this groundbreaking technology.

Why Now?

  1. Data Proliferation: The explosion of data from various sources – social media, CRM systems, purchase histories, browsing patterns, and IoT devices – provides a rich foundation for creating detailed digital twins (and also the “datagraphs”) of customers. This wealth of data enables marketers to build comprehensive, dynamic models that mirror real-world customer behaviours and preferences.
  2. Advancements in AI-ML: AI-ML technologies have matured significantly, allowing for the development of sophisticated algorithms that can process and analyse vast amounts of data. These advancements enable digital twins to evolve continuously, learning and adapting to each customer’s unique characteristics and interactions in real-time.
  3. Integration of Martech and Adtech: The integration of martech and adtech creates a seamless ecosystem where digital twins can thrive. This integration facilitates the flow of data across platforms, enhancing the accuracy and relevance of customer profiles. Customer segments can be enriched with data from adtech to create better content and campaigns.
  4. Rise of Agentic AI: The era of Agentic AI is upon us, characterisd by intelligent agents capable of interacting autonomously with other agents. This advancement will empower a Co-Marketer to engage in dynamic dialogues with digital twins, allowing for the continuous refinement of strategies and next-best actions. This interactive capability ensures that marketing efforts are not only highly personalised but also adaptive to real-time changes in customer behaviour and preferences, significantly enhancing the effectiveness and efficiency of marketing campaigns.

How Marketers Can Leverage Digital Twins

  • Building Detailed Customer Profiles: The first step in leveraging digital twins is to aggregate and analyse data from various sources to create detailed customer profiles (at individual level or for customer clusters). This involves collecting data from multiple touchpoints into a Large Customer Model (LCM). AI algorithms then process this data to construct dynamic, evolving models of individual customers.
  • Hyper-Personalisation: Digital twins enable marketers to achieve N=1 hyper-personalisation, tailoring marketing strategies to the unique needs and preferences of each customer. By understanding individual behaviours and predicting future actions, digital twins can recommend personalised products, services, and content, driving increased engagement and loyalty.
  • Optimising Customer Journeys: With digital twins, marketers can optimise customer journeys by ensuring that every touchpoint is tailored to the individual’s preferences and driven by their actions. From personalised content and messaging to dynamic promotions and predictive recommendations, digital twins enable brands to deliver a seamless and engaging customer experience.
  • Implementing Generative Journeys: Digital twins can interact within simulated “mirror world” environments, testing various strategies and scenarios to identify the most effective approaches for each customer. This process of generative journeys allows marketers to continuously learn and adapt to evolving customer needs, ensuring that marketing efforts are always relevant and impactful.
  • Enhancing LTV and Reducing CAC: By leveraging the insights provided by digital twins, brands can drive increased sales and customer loyalty, and also improve marketing efficiency. Consequently, brands can maximise customer lifetime value (LTV) while minimising customer acquisition cost (CAC).

The Path Forward

To successfully implement digital twins in marketing, brands need to invest in AI (predictive, generative, and agentic) technologies, integrate their martech and adtech platforms, and build a robust data infrastructure. Collaboration between data scientists, marketers, and technologists is crucial to develop and maintain accurate and dynamic digital twins.

8

AI-First Marketing

By creating AI-powered virtual representations of customers, businesses can unlock unprecedented levels of personalisation, efficiency, and engagement. Let’s explore the stack that underpins the implementation of digital twins in marketing.

  • Foundational Large Language Models (LLMs): At the base of the stack are Foundational Large Language Models (LLMs) such as ChatGPT, Gemini, and Claude. These models are the building blocks for understanding and generating human-like text based on vast datasets. LLMs facilitate natural language processing, enabling the creation of detailed customer profiles from various data sources. By interpreting customer interactions and behaviors, LLMs provide the initial insights needed to build accurate digital twins. But they are not customised for marketing.
  • Foundational Marketing Model (Martech+Adtech): The next layer integrates martech and adtech, creating a cohesive ecosystem that spans multiple channels. This foundational marketing model includes channel-specific SLMs (small language models) for email, SMS, WhatsApp (WA), and offsite platforms such as Facebook, Google Ads, and Instagram. With training data from these diverse sources, marketers can create better messages on channels..
  • Fine-Tuned Enterprise Model: Building on the foundational marketing model is the a layer which acts as an enhanced Customer Data Platform (CDP) enriched with Personally Identifiable Information (PII) about customers. This model aggregates data across properties, products, channels, and performance metrics from the different channels, thus enabling the model training programme to incorporate real-world feedback on content. This layer completes the Large Customer Model, bringing together customer data, channel content and performance, clusters (segments), catalog (product information), and conversations (from social media).
  • Co-Marketer: At the heart of the stack is the Co-Marketer, an AI-powered marketing assistant that leverages insights from digital twins to enhance creatives, messaging, campaigns, and offers. The Co-Marketer can be considered a marketer’s digital twin, a co-intelligence of sorts. It interacts with digital twins to test and fine-tune strategies, ensuring that every customer touchpoint is optimised. This agentic AI capability allows for dynamic, real-time adjustments to marketing efforts, leading to more effective and engaging campaigns.
  • Digital Twins: At the pinnacle of the stack are the AI-powered Digital Twins, which come in two forms: Segment Twins (N=M(any)) and Singular Twins (N=1). Segment Twins represent customer groups with shared behaviours and preferences, enabling marketers to craft targeted content and strategies for specific segments. Marketers can also have conversations with personas representing each of the segments. For example, a segment twin could be asked to rank email creatives in terms of likely performance. Singular Twins, on the other hand, are individual customer replicas that provide personalised recommendations and guide customer journeys. They become more powerful with accumulation of individual data (both first- and zero-party, and derived attributes) and the progression of journeys in the lifecycle. These twins continuously evolve, integrating new data and interactions to remain current and accurate.

The integration of these layers creates a seamless pathway from raw data and generic experiences to highly personalised marketing experiences. By continuously refining strategies based on real-time insights, businesses can achieve N=1 hyper-personalisation, delivering tailored experiences that drive engagement and loyalty. In the words of Jack Carr quoting a quantum computer (almost an “artificial general intelligence”) named Alice in “Red Sky Mourning”, the Digital Twins can “in real-time, analyse the past and evaluate the present to predict the future.”

This is the coming world of AI-powered Digital Twins, which I think of as “marketing’s marvel.” How does it look like?

9

Story – 1

I gave ChatGPT and Claude the following prompt: “Write a story describing this world. You can call the marketer as Maya and take the example of a company called A1Books, an omnichannel book seller.” Here is ChatGPT.

Maya is the Chief Marketing Officer at A1Books, an omnichannel book seller renowned for its personalized customer experiences. Her day begins with a fresh cup of coffee and a glance at her dashboard, powered by the latest advancements in digital twin technology.

The Foundation: Large Language Models

At the core of A1Books’ marketing stack are Foundational Large Language Models (LLMs) like ChatGPT, Gemini, and Claude. These models process and interpret vast amounts of customer data, ranging from purchase histories to social media interactions. As Maya reviews the latest customer insights generated by these LLMs, she appreciates how they transform raw data into actionable insights, enabling a deeper understanding of A1Books’ diverse customer base.

Integrating Martech and Adtech

Maya’s next task involves leveraging the Foundational Marketing Model, which integrates martech and adtech data across multiple channels such as email, SMS, WhatsApp, and social media platforms like Facebook and Instagram. This integration ensures a seamless flow of data, enhancing the accuracy of customer profiles. Today, Maya notices a trend: customers who engage with A1Books’ Instagram ads are more likely to purchase non-fiction titles. She decides to refine the ad campaigns accordingly.

Enhancing with Fine-Tuned Enterprise Model

With a solid foundation in place, Maya turns her attention to the Fine-Tuned Enterprise Model, an enhanced Customer Data Platform (CDP) enriched with Personally Identifiable Information (PII). This layer aggregates data from various properties, products, channels, and performance metrics. By incorporating real-world feedback, Maya can see how different campaigns are performing across segments. She notes that personalized email campaigns featuring exclusive author interviews are generating higher engagement and decides to expand this initiative.

The Co-Marketer: Maya’s Digital Twin

One of Maya’s most powerful tools is the Co-Marketer, an AI-powered assistant that interacts with digital twins to optimize strategies. Today, the Co-Marketer suggests a new campaign focusing on a recently released fantasy series. By conversing with the Segment Twins, Maya’s Co-Marketer fine-tunes the campaign to target specific customer groups who have shown an interest in similar genres. The Co-Marketer’s ability to dynamically adjust messaging ensures that each interaction is perfectly timed and highly relevant.

AI-Powered Digital Twins

At the pinnacle of A1Books’ stack are the AI-powered Digital Twins. Segment Twins represent groups of customers with shared behaviors and preferences, while Singular Twins are detailed replicas of individual customers. Maya reviews the recommendations generated by these digital twins, noting that a customer, Alex, frequently browses fantasy novels but hasn’t made a purchase recently. The Singular Twin suggests a personalized offer on a new fantasy release, anticipating Alex’s interest.

Optimizing Customer Journeys

Maya implements the personalized offer through a generative journey, where the Singular Twin tests various scenarios within a simulated environment. The twin interacts with the Co-Marketer to identify the most effective approach, ensuring that Alex receives a timely and relevant recommendation. This level of personalization not only enhances customer satisfaction but also drives engagement and loyalty.

Real-Time Adjustments and Insights

As the day progresses, Maya continuously monitors the performance of various campaigns. The digital twins evolve with each customer interaction, integrating new data to remain accurate and up-to-date. Maya appreciates how these twins enable real-time adjustments to marketing strategies, ensuring that A1Books can respond swiftly to changing customer behaviors and preferences.

The Future of Marketing

Maya reflects on the transformation digital twins have brought to A1Books. By integrating advanced AI technologies with a robust data infrastructure, A1Books can deliver hyper-personalized experiences at scale. The seamless interaction between Segment Twins, Singular Twins, and the Co-Marketer has revolutionized their marketing approach, driving profitable growth and customer loyalty.

As she wraps up her day, Maya envisions the future possibilities of digital twins in marketing. The continuous refinement of strategies, real-time personalization, and dynamic customer engagement are just the beginning. With AI-powered digital twins, the world of marketing is set to achieve new heights, creating deeper, more meaningful connections between brands and their customers.

In the world of A1Books, every customer interaction is a step towards a more personalized, engaging, and satisfying experience, thanks to the marvel of AI-powered digital twins.

10

Story – 2

Here is Claude’s story.

Maya leaned back in her chair, her eyes fixed on the holographic display hovering above her desk. As the lead digital strategist for A1Books, she was examining the latest insights from the company’s AI-powered marketing system.

“Co-Marketer, show me the performance of our latest campaign for mystery novels,” Maya commanded.

Instantly, a friendly voice responded, “Certainly, Maya. The mystery novel campaign has seen a 15% increase in engagement across all channels. Would you like me to break down the performance by segment?”

“Yes, please. And let’s focus on the ‘Thriller Enthusiasts’ segment,” Maya replied.

The display shifted, revealing a detailed breakdown of how the campaign resonated with different customer groups. Maya’s attention was drawn to a pulsing icon representing the Segment Twin for Thriller Enthusiasts.

“Interesting,” Maya mused. “Co-Marketer, can you ask the Thriller Enthusiasts Twin to rank our top three email creatives for the upcoming summer reading promotion?”

“Of course,” the Co-Marketer replied. After a brief pause, it continued, “The Thriller Enthusiasts Twin has ranked the creatives. Would you like me to display the results and explain the reasoning?”

“Yes, go ahead,” Maya nodded.

As the Co-Marketer began explaining the twin’s analysis, Maya marveled at how far marketing technology had come. Just a few years ago, this level of insight and personalization seemed like science fiction. Now, it was her daily reality at A1Books.

Suddenly, an alert flashed on her screen. “Maya, I’ve detected an unusual pattern in customer behavior for user ID 78291,” the Co-Marketer announced. “This customer’s Singular Twin is showing a 78% probability of churning in the next 30 days. Would you like me to generate a personalized retention strategy?”

Maya sat up straight, her interest piqued. “Absolutely. What can you tell me about this customer?”

The Co-Marketer quickly pulled up a detailed profile. “User 78291, Sarah Thompson, is a 32-year-old professional who typically purchases business and self-help books. However, her recent browsing history shows an increased interest in travel guides. Based on her Singular Twin’s analysis, I believe she may be planning a career break to travel, which could explain the potential churn.”

Maya nodded, impressed by the depth of insight. “Alright, let’s craft a personalized offer for Sarah. Maybe a bundle of travel guides with a loyalty discount?”

“Excellent suggestion, Maya,” the Co-Marketer responded. “I’ll create a few options for you to review, optimized for Sarah’s preferences and past behavior.”

As Maya reviewed the proposed strategies, she couldn’t help but reflect on how digital twins had transformed A1Books’ approach to customer engagement. The ability to understand and anticipate customer needs with such precision had not only boosted sales but had also fostered a deeper connection with their audience.

“Co-Marketer,” Maya said, a new idea forming, “let’s simulate how our top 1000 customers would respond to a new ‘Personalized Reading Journey’ feature. Use the Singular Twins to predict engagement and potential revenue impact.”

“Certainly, Maya. I’ll run the simulation in our Mirror World environment and have the results for you shortly,” the Co-Marketer replied.

As the simulation began, Maya smiled. With AI-powered digital twins at her fingertips, she felt like she had a superpower – the ability to understand and serve A1Books’ customers better than ever before. The future of marketing, she thought, was not just about selling books; it was about creating unique, personalized experiences for every reader, one digital twin at a time.

11

Additional Ideas

I asked ChatGPT and Claude and Gemini for additional ideas to what I had written.

ChatGPT

Enhanced Customer Support

  1. Proactive Customer Service:
    • AI-powered digital twins can predict when a customer might need support based on their interactions and behavior patterns. This allows companies to proactively reach out and offer assistance before the customer encounters an issue, improving customer satisfaction and loyalty.
    • Example: If a customer frequently searches for troubleshooting information, their digital twin can prompt a support agent to reach out with solutions before the customer files a complaint.
  1. Personalized Customer Support:
    • Digital twins can provide customer service agents with a detailed history and preferences of the customer they are assisting, allowing for more personalized and efficient service.
    • Example: When a customer contacts support, the agent can immediately see the customer’s recent interactions, purchase history, and any previous issues, enabling them to provide tailored assistance.

Dynamic Pricing and Promotions

  1. Real-Time Pricing Adjustments:
    • AI-powered digital twins can analyze market trends, competitor pricing, and customer behavior to dynamically adjust prices in real-time, ensuring competitive pricing and maximizing revenue.
    • Example: If a customer shows high interest in a product but hasn’t purchased it, the digital twin can trigger a personalized discount to encourage conversion.
  1. Targeted Promotions:
    • Digital twins can help in creating highly targeted promotions based on individual customer behavior and preferences, ensuring that promotions are relevant and effective.
    • Example: A digital twin can identify customers who are likely to respond to a limited-time offer and tailor the promotion specifically to their interests and buying patterns.

Product Development and Feedback

  1. Customer-Driven Product Innovation:
    • Digital twins can gather and analyze customer feedback in real-time, helping companies to quickly adapt their products to meet customer needs and preferences.
    • Example: If a digital twin identifies a recurring complaint about a product feature, the company can prioritize updates to address the issue.
  1. Virtual Product Testing:
    • Companies can use digital twins to simulate how customers might interact with new products or features before they are launched, reducing the risk of product failures and improving the overall customer experience.
    • Example: A1Books could use digital twins to test different layouts of their online bookstore to see which one provides the best user experience.

Cross-Selling and Up-Selling

  1. Intelligent Cross-Selling and Up-Selling:
    • Digital twins can analyze purchase patterns and customer preferences to suggest relevant complementary products or upgrades.
    • Example: If a customer buys a book, the digital twin might suggest related books or audiobooks based on the customer’s reading history and interests.
  1. Subscription and Membership Programs:
    • Digital twins can identify customers who are likely to benefit from subscription services or loyalty programs, and personalize the offers to increase adoption rates.
    • Example: A1Books can use digital twins to identify frequent buyers who might be interested in a subscription service for exclusive content or early access to new releases.

Customer Retention Strategies

  1. Predictive Churn Analysis:
    • Digital twins can predict which customers are at risk of churning based on their behavior and interactions, allowing companies to take preemptive measures to retain them.
    • Example: If a customer’s engagement drops significantly, the digital twin can trigger a retention campaign with personalized offers to re-engage the customer.
  1. Loyalty Programs Optimization:
    • By analyzing customer behavior, digital twins can help optimize loyalty programs to ensure they are rewarding the behaviors that contribute most to business goals.
    • Example: A1Books can tailor its loyalty program rewards based on what motivates each customer, such as discounts, exclusive content, or early access to new books.

Enhanced Analytics and Insights

  1. Real-Time Marketing Analytics:
    • Digital twins can provide real-time analytics and insights into the effectiveness of marketing campaigns, allowing for agile adjustments and optimization.
    • Example: If a marketing campaign isn’t performing as expected, the digital twins can provide insights into why and suggest modifications to improve results.
  1. Behavioral Segmentation:
    • Digital twins can help in segmenting customers based on detailed behavioral data, allowing for more precise and effective targeting.
    • Example: A1Books can segment its customers into groups based on their reading habits, purchase frequency, and engagement levels, and tailor marketing strategies accordingly.

Claude

  1. Ethical considerations: Discuss the potential privacy concerns and ethical implications of using such detailed digital representations of customers. How can marketers ensure they’re using this technology responsibly?
  2. Integration with IoT devices: Explore how digital twins could incorporate data from Internet of Things (IoT) devices to create even more accurate customer profiles. For example, smart home devices or wearables could provide insights into daily habits and preferences.
  3. Predictive inventory management: Digital twins could be used to optimize inventory across physical and online stores based on predicted customer behavior and external factors like weather or local events.
  4. Virtual product testing: Discuss how digital twins could be used to simulate how customers might interact with new products before they’re launched, allowing for better product development and marketing strategies.
  5. Cross-industry applications: Explore how the concept of digital twins in marketing could be applied to or integrated with other industries like healthcare or finance for a more holistic customer experience.
  6. Augmented and Virtual Reality integration: Consider how digital twins could enhance AR and VR experiences for customers, creating immersive and personalized shopping environments.
  7. Dynamic pricing strategies: Explain how digital twins could inform real-time pricing decisions based on individual customer behavior and market conditions.
  8. Customer service applications: Discuss how digital twins could be used to enhance customer service by predicting issues and personalizing support interactions.
  9. Regulatory challenges: Address the potential regulatory hurdles that might arise as this technology becomes more prevalent in marketing.
  10. Impact on traditional marketing roles: Explore how the advent of AI-powered digital twins might transform traditional marketing job roles and required skill sets.

Thinks 1321

Akash Prakash: “Given that we have a $4 trillion gross domestic product (GDP) and a household savings rate of 20 per cent, these savings, restricted to Indian assets, are increasingly going into equities, making India a very favourable place to list. Even on an absolute basis, this is a very attractive and growing savings pool. In a world where investors complain of closed IPO markets and a lack of listings, the Indian markets stand out in terms of receptivity to new listings. All types of companies across industries, business models and of differing maturity can list. We are seeing multiple IPOs and secondary sales every day. This vibrancy also strengthens the startup ecosystem as the ability for venture capital (VC) to exit via the capital markets is not questioned.”

PwC: “Marketing services is another area likely to face significant change for many of the same reasons as the entertainment industry. GenAI-powered tools for marketing were among the first generation of GenAI applications available. The market is flooded with young vendors in this space and is likely to see significant consolidation in the coming months as a result. Established incumbents such as Salesforce are increasingly incorporating generative AI into their existing products as well. As in entertainment, video- and music-generation tools will offer significant cost savings for marketing services. Another similarity: the personalization that the cost and speed of generative AI enables is among the use cases offering the most transformational value, and its impact is still nascent. GenAI could even bring about a disintermediation of marketing services due to the leverage it provides to the companies they currently serve.”

Time: “Humans are more than medical profiles. Every aspect of our health is deeply influenced by the five foundational daily behaviors of sleep, food, movement, stress management, and social connection. And AI, by using the power of hyper-personalization, can significantly improve these behaviors…Most health recommendations at the moment, though important, are generic: your patient portal might send you an automated reminder to get a flu shot or mammogram, or your smartwatch may ping you to breathe or stand. The AI health coach will make possible very precise recommendations tailored to each person: swap your third afternoon soda with water and lemon; go on a 10-minute walk with your child after you pick them up from school at 3:15 p.m.; start your wind-down routine at 10 p.m. since you have to get up at 6 a.m. the next morning to make your flight.”

NYTimes: “Research has long shown that health and longevity comes down to five fundamental lifestyle behaviors: exercising regularly, eating a nutritious diet, eschewing cigarettes, limiting alcohol consumption and nurturing meaningful relationships…It follows that perhaps the best protocol for living a good, long, fulfilled and productive life is to focus on nailing what actually matters, and then not stress about the rest. If your concern is that life is fragile and short, you simply don’t have time to waste. This stuff is simple, somewhat boring and harder to make money off of than trendy supplements, complex-sounding theories and new gadgets — but it’s what actually works.”

Podcast with Thrifty Titans

I did a podcast with Saikat Pyne (Thrifty Titans).

From the LinkedIn post: “In this episode, Rajesh shares his journey of turning minimal investments into massive returns for your startup. Learn the essential steps for bootstrapping a SaaS venture, managing resources on a tight budget, and acquiring customers with minimal spends. Also discover the power of financial discipline and how to maintain a lean team while achieving significant growth. This episode is packed with invaluable insights for early stage founders. Don’t miss this masterclass on running lean and aiming big!”

Thinks 1320

The 100 Best Books of the 21st Century: from NYTimes. The top 3: My Brilliant Friend by Elena Ferrante; The Warmth of Other Suns by Isabel Wilkerson;  Wolf Hall by Hilary Mantel.

Axios: “A new kind of turf war is breaking out on the web, with AI bots battling other AI bots to seize or defend stockpiles of the AI era’s most valuable commodity: data. AI makers hungry for more data to train their language models are grabbing everything they can, while information owners are increasingly fighting fire with fire by turning to AI-powered tools to protect their intellectual property.”

NYTimes: “Elevators in North America have become over-engineered, bespoke, handcrafted and expensive pieces of equipment that are unaffordable in all the places where they are most needed. Special interests here have run wild with an outdated, inefficient, overregulated system. Accessibility rules miss the forest for the trees. Our broken immigration system cannot supply the labor that the construction industry desperately needs. Regulators distrust global best practices and our construction rules are so heavily oriented toward single-family housing that we’ve forgotten the basics of how a city should work. Similar themes explain everything from our stalled high-speed rail development to why it’s so hard to find someone to fix a toilet or shower. It’s become hard to shake the feeling that America has simply lost the capacity to build things in the real world, outside of an app.”

WSJ: “When we have a daily snack at about the same time, we are more likely to adjust the rest of our intake to offset the snack calories, says Richard D. Mattes, a professor of nutrition science at Purdue University in Indiana. With unplanned snacks, we tend to just add the calories to our daily total. If you have cake at the office for a co-worker’s birthday, you’ll probably still eat the lunch you brought and the dinner you planned, Mattes says. Splurging is fine once in a while, but frequent randomly timed snacks can make us consume excess calories that can lead to weight gain, he says. Most people need to eat every three to five hours during the day to keep energy levels up and hunger at bay, said Grace Derocha, a registered dietitian in Troy, Mich., and a spokeswoman for the Academy of Nutrition and Dietetics.”