Co-Marketer: Martech meets AI

Published May 31, 2024

1

Copilots

In my previous essay “New SaaS: Services, AI Agents, Sharing”, I wrote:

There are two “New SaaS” innovations which can underpin the New SaaS model for B2C Martech: a Digital Twin for a “segment of one”, and a Co-Marketer for a “department of one”.

Digital Twin: Envision a hyper-personalised AI companion for each customer, not just mirroring their actions but also predicting future behaviours (‘next best actions’) with remarkable accuracy. This advanced AI agent delves deep into individual customer data and journeys, using AI-driven insights to foresee and shape future interactions. It dynamically engages with the brand for tasks like tracking purchases, managing service requests, and filtering offers. This embodiment of the “segment of one” philosophy leverages AI to craft unique, waste-free experiences that maximise customer lifetime value. [Also see iDarpan: How Mirror Worlds and Digital Twins will Revolutionise eCommerce.]

Co-Marketer: A brand’s marketing team can also do with some help. A lot of time is spent in repetitive, time-consuming activities like identifying segments, making creatives, running campaigns, and analysing data. AI autonomous agents can offload many of these tasks. A Progency can oversee these agents and be incentivised based on outcomes. This could enable a “department of one” where the marketer lays out the objectives and the AI-enabled Co-Marketer works on the optimisations necessary to achieve the goals.

These innovations not only exemplify the New SaaS model’s potential in revolutionising B2C Martech but also underscore the synergistic integration of Services, AI Agents, and Sharing. By harnessing these components, brands can unlock unprecedented levels of personalisation and efficiency, propelling marketing into a new era of intelligence and customer-centricity, and a big leap forward in the quest to becoming a Profipoly.

In this series, I want to discuss further the idea of a “Co-Marketer”.

**

With the rise of Gen AI and foundational models, “copilots” have been emerging to help humans with their day-to-day tasks. I use ChatGPT, Claude, and Gemini for my writing – almost like a co-researcher and co-writer. Software engineers have started using co-pilots and AI assistants for code writing and testing.

As Moveworks puts it: “An AI copilot is a conversational interface that uses large language models (LLMs) to support users in various tasks and decision-making processes across multiple domains within an enterprise environment. By leveraging LLMs, AI copilots possess the capability to understand, analyze, and process vast amounts of data. AI copilots play a crucial role in enhancing productivity and efficiency by: providing context-aware assistance, automating mundane tasks, analyzing data, enabling seamless communication, and unifying disparate systems…In a nutshell, an AI copilot acts to simplify complex tasks and provide valuable guidance and support, ultimately elevating the user experience and driving businesses toward their goals effectively and efficiently… AI copilots have strong foundations built on two essential components: artificial intelligence and integrations across systems.”

Aisera adds: “AI Copilots are indeed virtual assistants enhanced by Artificial Intelligence to boost productivity and efficiency in various work settings. By leveraging large language models (LLMs) to facilitate natural, human-like conversational interactions, assisting users in a wide variety of tasks. They are designed to work seamlessly with existing tools and workflows, providing real-time assistance without disrupting the user’s work process. AI copilots are meticulously designed to boost productivity and smoothen operational processes with a high level of accuracy. Their capabilities allow them to predict user requirements effectively, offering customized solutions with impressive precision.”

Pratik Bhadra writes: “GenAI can serve as a marketing assistant by offering insights into audience preferences. By dynamically adapting marketing strategies in real time and providing suggestions for improvements based on performance metrics, GenAI co-marketers can optimize marketing efforts. GenAI can also predict the next best action (NBA) for individual customers, leading to more personalized experiences, upgrading from a current state of marketing campaigns for everyone in segments to a future state of goal-based personalization activation.”

At the heart of co-pilots and AI assistants is an idea which Ethan Mollick calls “co-intelligence.”

2

Co-Intelligence

Ethan Mollick’s new book, “Co-Intelligence: Living and Working with AI” is an excellent overview of the power of Gen AI and tomorrow’s world. He writes in his book: “AI is what those of us who study technology call a General Purpose Technology (ironically, also abbreviated GPT). These advances are once-in-a-generation technologies, like steam power or the internet, that touch every industry and every aspect of life. And, in some ways, generative AI might even be bigger… Where previous technological revolutions often targeted more mechanical and repetitive work, AI works, in many ways, as a co-intelligence. It augments, or potentially replaces, human thinking to dramatic results. Early studies of the effects of AI have found it can often lead to a 20 to 80 percent improvement in productivity across a wide variety of job types, from coding to marketing… We have invented technologies, from axes to helicopters, that boost our physical capabilities; and others, like spreadsheets, that automate complex tasks; but we have never built a generally applicable technology that can boost our intelligence. Now humans have access to a tool that can emulate how we think and write, acting as a co-intelligence to improve (or replace) our work.”

Ethan says in an interview with Ezra Klein: “A.I. is built like a tool. It’s software. It’s very clear at this point that it’s an emulation of thought. But because of how it’s built, because of how it’s constructed, it is much more like working with a person than working with a tool…But if you think about it like programming, then you end up in trouble. In fact, there’s some early evidence that programmers are the worst people at using A.I. because it doesn’t work like software. It doesn’t do the things you would expect a tool to do. Tools shouldn’t occasionally give you the wrong answer, shouldn’t give you different answers every time, shouldn’t insult you or try to convince you they love you. And A.I.s do all of these things. And I find that teachers, managers, even parents, editors, are often better at using these systems, because they’re used to treating this as a person. And they interact with it like a person would, giving feedback. And that helps you. And I think the second piece of that “not tool” piece is that when I talk to OpenAI or Anthropic, they don’t have a hidden instruction manual. There is no list of how you should use this as a writer, or as a marketer, or as an educator. They don’t even know what the capabilities of these systems are. They’re all sort of being discovered together. And that is also not like a tool. It’s more like a person with capabilities that we don’t fully know yet.”

From Ethan’s book: “By acting as a co-intelligence managing work, or at least helping managers manage work, the enhanced capabilities of LLMs could radically change the experience of work. A single AI can talk to hundreds of workers, offering advice and monitoring performance. They could mentor, or they could manipulate. They could guide decisions in ways that are subtle or overt… With exponential change, AIs a hundred times better than GPT-4 start to actually take over human work. And not just office work, either, as there is some early evidence that LLMs may help us overcome the barriers that have made building working robots so challenging. AI-powered robots and autonomous AI agents, monitored by humans, could potentially drastically reduce the need for human work while expanding the economy.”

So, what will co-intelligence in the world of martech look like?

3

Inputs

I asked ChatGPT, Claude, and Gemini the same question: “I am writing an essay about how a “co-marketer” can help marketers in B2C companies. A co-marketer is an AI-powered co-worker, a co-intelligence in the words of Ethan Mollick. How would a martech company create a co-marketer? How would a CMO use a Co-marketer?” Here are the responses I got.

ChatGPT

To create a Co-marketer, a martech company would integrate AI technologies like machine learning, natural language processing, and data analytics into their platforms, enabling personalized and dynamic marketing strategies. The AI Co-marketer would analyze consumer data, predict trends, and automate tasks, becoming an integral part of the marketing team.

A CMO would use a Co-marketer to enhance decision-making, streamline marketing operations, and personalize customer interactions. By leveraging AI insights, the CMO can achieve higher efficiency in campaigns, improved customer engagement, and ultimately, increased conversion rates, making the Co-marketer an invaluable asset in achieving marketing objectives.

Claude

Creating a Co-Marketer AI

For a martech company to create an effective co-marketer AI, there are several key elements they would need to consider:

1. Data Aggregation and Analysis: The foundation of the co-marketer would be a robust data platform that can ingest and analyze massive amounts of customer data, market trends, campaign performance, and other relevant information. This would require advanced data engineering and machine learning capabilities to extract meaningful insights.
2. Domain Knowledge Embedding: The co-marketer would need to be imbued with deep domain expertise in marketing, consumer behavior, advertising, branding, and related fields. This could be achieved through careful curation of training data, as well as collaboration with marketing experts to codify their knowledge.
3. Conversational Interfaces: To make the co-marketer truly collaborative, it would need natural language processing and generation abilities to engage in seamless dialogue with human marketers. Intuitive conversational interfaces would allow the co-marketer to understand queries, provide recommendations, and explain its reasoning.
4. Predictive Capabilities: A key advantage of the co-marketer would be its ability to forecast campaign performance, identify emerging trends, and proactively suggest optimization opportunities. This would require advanced machine learning models trained on historical data to generate accurate predictions.
5. Continuous Learning: The co-marketer should have the capacity to learn and adapt over time, incorporating feedback from human users and adjusting its knowledge and decision-making processes accordingly. This would ensure the co-marketer remains relevant and valuable as marketing practices evolve.

Leveraging a Co-Marketer as a CMO

A Chief Marketing Officer (CMO) could harness the capabilities of a co-marketer AI in several ways to improve marketing effectiveness and efficiency:

1. Campaign Planning and Optimization: The CMO could rely on the co-marketer’s data-driven insights to inform strategic campaign planning, target audience selection, messaging development, and budget allocation. The co-marketer could also continuously monitor campaign performance and suggest real-time optimizations.
2. Content Creation and Personalization: The co-marketer could assist in generating personalized content and creative assets by leveraging its understanding of customer preferences, industry trends, and brand guidelines. This could significantly streamline the content production process.
3. Market Intelligence and Trend Spotting: The co-marketer’s ability to analyze vast amounts of data could provide the CMO with valuable market intelligence, including emerging consumer preferences, competitive moves, and industry disruptions. This would enable the CMO to make more informed strategic decisions.
4. Collaborative Decision-Making: The CMO could engage the co-marketer in an interactive, conversational manner to brainstorm ideas, explore scenarios, and seek recommendations. The co-marketer’s objective analysis and creative suggestions could complement the CMO’s own expertise and intuition.
5. Team Enablement: By offloading certain routine tasks and analytical work to the co-marketer, the CMO could free up their team to focus on higher-level strategic initiatives, fostering a more collaborative and innovative marketing organization.

Overall, a well-designed co-marketer AI has the potential to significantly enhance the CMO’s capabilities, improve marketing performance, and drive business growth for B2C companies.

Gemini

The Rise of the Co-Marketer: AI Assistance for B2C Success

In today’s dynamic B2C landscape, marketers constantly seek an edge. Enter the co-marketer, an AI-powered “co-worker” envisioned by Ethan Mollick. This essay explores how martech companies can develop co-marketers and how CMOs can leverage them to enhance marketing efforts.

Building the Co-Marketer: A Martech Challenge

Martech companies have the tools to craft a powerful co-marketer. Here’s a potential approach:

1. Data Acquisition and Integration: The co-marketer ingests vast amounts of data – customer demographics, campaign performance, market trends, competitor analysis – from various sources like CRM, marketing automation platforms, and social media.
2. Advanced Analytics and Machine Learning: The co-marketer utilizes machine learning algorithms to analyze the data. It can identify customer segments, predict campaign performance, and recommend optimal marketing strategies.
3. Content Creation and Personalization: The co-marketer assists with content creation by analyzing customer preferences and suggesting topics, formats, and channels for targeted campaigns. It can even personalize content for individual customers.
4. Real-Time Optimization and Reporting: The co-marketer constantly monitors campaign performance, identifies areas for improvement, and suggests adjustments in real-time. It can also generate comprehensive reports with insightful data visualizations.

The CMO’s Co-Pilot: How to Leverage the Power

CMOs can utilize co-marketers in several ways:

1. Strategic Planning: Instead of relying solely on intuition, CMOs can use the co-marketer’s data-driven insights to define marketing goals, identify target audiences, and develop data-backed marketing strategies.
2. Campaign Development and Execution: The co-marketer can streamline campaign creation by suggesting content ideas, optimizing ad placements, and automating repetitive tasks. This frees up the CMO’s team for more creative endeavors.
3. A/B Testing and Optimization: The co-marketer’s real-time analysis allows for continuous optimization of campaigns. It can recommend A/B testing different strategies and adapt campaigns based on results, maximizing effectiveness.
4. Predictive Analytics and Forecasting: With its ability to analyze historical data and market trends, the co-marketer can forecast future customer behavior and predict campaign performance. This allows CMOs to make informed decisions for future marketing efforts.

The Future of Marketing: A Collaborative Approach

The co-marketer is not a replacement for human marketers. It’s a powerful co-worker that provides data-driven insights and automates tasks. By leveraging this AI co-pilot, CMOs can make data-backed decisions, optimize campaigns for maximum impact, and ultimately achieve greater success in the B2C landscape. As martech continues to evolve, the co-marketer is poised to become an indispensable tool for B2C marketing success.

[Rajesh] Very useful inputs! Next, I will describe my thinking.

4

The Need

Martech is about customer retention and growth. It is about maximising customer lifetime value (CLV) by personalising the journey and experience for every customer. Marketers do this by using martech platform to help track what customers are doing on their properties (websites and apps), segment them, craft messages, and then orchestrate campaigns across multiple touchpoints (email, SMS, WhatsApp, RCS, and browser and app notifications).

Martech is hard work. Millions of customers mean billions of data points to be analysed to craft hundreds of campaigns to a multitude of segments. Martech platforms (like what Netcore offers) help make this process easy, but the marketing department still has plenty to do. AI in martech is starting to help predict next best actions for cohorts and at times, even for individuals. As the touchpoints have grown, so has the complexity. The idea of a “unified customer view” has grown to overcome data silos with the help of a “customer data platform” (CDP). Martech is central to converting the cost of acquisition into revenues and profits.

As I wrote in The 7½ Futures of Martech Companies:

Every business needs to sell what it makes, and marketing is the core (along with innovation). Marketing has, of course, changed through the decades, and continues to evolve. Digital marketing is now central to every business strategy. Adtech has grown to a $500 billion industry as it helps businesses acquire (and reacquire) customers. Even though martech has grown and is probably about a tenth of the size of adtech, I believe the future will be a more equitable balance in spending. This will mean a big shift in budgets and exponential growth in martech spending. An array of tech breakthroughs will make this happen. One of the biggest opportunities in software is therefore the engineering of a $250 billion shift from AdWaste (wrong acquisition and reacquisition).

Martech should always have been the primary focus of digital marketing. But in the past two decades, with the ease of spending on adtech, it has been reduced to a bit player. The obsession with growth has fuelled spending on acquisition rather than retention. This has resulted in a massive transfer of value from brands (the actual sellers) to the intermediaries (ad sellers, cloud sellers, and marketplaces). Brands have lost control of data, relationships and their customers. They have even become dependent on the adtech platforms to reconnect with their own customers because they are unable to get across to them. Fortunately, help is at hand. The change has to be driven by martech companies.

The martech department needs help. Just like digital agencies evolved to assist the marketing department with their branding, acquisition, and retargeting campaigns on Google and Meta, martech agencies are trying to help with retention and engagement. (An idea I have discussed in the past is that of a Progency, a performance-oriented martech agency.) But retention and development of existing customers is a much harder problem to tackle because of the complexities involved with data, channels and properties (touchpoints), segments, and journeys. Marketers need a companion, a co-intelligence, a Co-Marketer.

5

Imagine

Maya is CMO (or Chief Profits Officer, as she calls herself) at A1Books, am omnichannel retailer. She is working with Netcore’s Raman, the Co-Marketer. When she comes in to work, Raman has already analysed data from the previous day, and has suggestions ready for the day’s activities. A new book by a best-selling author is being published the next day. Raman has identified customers most likely to buy – based on their previous purchases of books from the same author and those interested in the genre. Raman has creatives ready – optimised for different channels. It knows the preferred channel of each customer. It has taken the primary creatives and tweaked it into a million different creatives – one for every customer, based on their preferences (language, channel), demographics (age, gender), and recent behaviour (active, inactive). All Maya needs to do is to review and greenlight.

At the start of the quarter, Maya had set a few goals for Raman in terms of revenues and conversions. She also had some stock of books that she wanted to clear at discounted prices. Raman knows this. By using the “digital twin” of every customer, Raman knows exactly what book at what price can be pitched to each customer to attain the goals Maya has set. By creating smart bundles (an attractive price for a new book with a few books from the inventory), Maya is hoping to make sure that profitability is not compromised. Raman is helping her target a “segment of one” – a unique message for every one of her millions of customers.

Maya reminisces about the past when her department had a team driven to exhaustion with the scale of daily work. There were many repetitive tasks being done leaving little or no room for creativity and innovation. The options for targeting were multiplying with the rise of omnichannel. Inefficiency was rising leading to an even greater dependence on expensive adtech to ensure growth was not impacted. That was when Netcore had introduced its Co-Marketer, Raman.

Raman took away all the grunt work. It never got tired. It never worried about the quantum of data to be processed. It took inputs from Maya natural language (voice, in most cases). It relied on custom LLMs (“Large Customer Models”) to be able to predict customer journeys and actions at the level of N=1 (hyper-personalised for every individual). It also scoured social media for book mentions and breaking news to target those who may be interested in the back (long tail) catalog – these sales were very profitable because discounting was not needed. Raman itself would run simulations in a “mirror world” with the digital twins and identify the right message to be sent at the right time on the right channel for every customer to maximise every shopper’s lifetime value, thus creating enduring relationships.

Maya’s martech team was now a “department of one” for a “segment of one” tailored approach to marketing. She liked to say her mantra was “SOO, DOO” (So, Do) – a call-out for action! She had redeployed her team to do things AI was not able to do: have in-person conversations with customers to better understand their reading habits, facilitate the creation of book clubs and meetups in every city, coordinate author events at A1Books’ stores, and even identify smaller retailers and D2C companies for potential acquisition to expand the product portfolio.

Raman as Co-Marketer has transformed her workday and A1Books’ P&L, putting her on track to run a P&L (a step towards fulfilling her aspiration of becoming CEO someday in the future).

6

Raman

I described how Maya used Netcore’s Co-Marketer, Raman. So, how does Raman work under the hood to help Maya ensure a “department of one” for a “segment of one” marketing?

Raman is a collection if autonomous AI agents working in tandem to help with goal attainment. Unlike the previous generation of rules-centric modules and workflow orchestration, these agents are constantly learning to enable conversion optimisation. The idea of “Kaizen” (continuous improvement) is built-in to Raman. Raman is not a tool, but more of a co-worker who can work with a target, a sort of “digital twin” for Maya.

Raman’s army of specialised AI agents do various tasks: one agent works as a CDP, collecting and cleaning the data from the various touchpoints; another agent tracks real-world news and listens on social media to see which themes could help with book sales; a third agent works on creative generation (this is itself a collection of micro-agents which work to create a dizzying array of content and messages which the “digital twin” of every customer can identify as the right next best action for is real-world equivalent); a fourth agent works on content from books which can be used to persuade buyers; a fifth agent aggregates actions and analyses the results of every campaign and feeds it back to the digital twin). This is the “Mirror World” that a helps power Raman.

Raman has made martech even simpler than adtech, and thus has enabled a huge shift in budgets. As marketer’s realised that half their spending was being wasted on acquisition and reacquisition, they understood that the only path to profitability was to maximise revenues from existing customers and ensure they referred their family and friends. Raman was the bridge – ensuring that every customer’s potential was tapped to the full. It even engaged in conversations with customers to ensure that they found the right books for their interests – in some cases, even helping customers discover latent passions, just like a friend.

Netcore’s Raman is itself a general purpose technology built on Gen AI. It can be adapted to any B2C business. It starts by imbibing existing customer and catalog data. It can then magically make the connections. LLMs like ChatGPT predict the next word in a sentence. LCMs (large customer models) like Raman can predict the next best action in a customer journey. It also knows how to fill in the data gaps by gently asking customers – thus deepening its pool of zero-party data, a must for creating effective “digital twins.”

Netcore’s Raman is thus bringing to life the true power of Gen AI: a second-order technology built to work as an intelligent companion, an “artificial friend” in the words of Kazuo Ishiguro (in his book “Klara and the Sun”).  Raman has put co-intelligence to work, helping shift billions of dollars of AdWaste to brand profits, enabling brands to build better futures for themselves and their customers.

Powered by Raman, Netcore has reinvented itself as an AI-first martech company, a true growth and profits partner for its customers. By bringing martech and customer relationships centre stage, its “CMO2CEO” program has democratised (and humanised) AI, enabling marketers like Maya to rise and flourish. Netcore’s vision of “empowering marketers to build enduring relationships between brands and customers” is unlocking a new world where marketing is, once again, central to our lives.

7

Four Techs

A co-marketer works in a larger environment of four techs which will transform martech and brand outcomes – the other three are digital twins, mirror world, and large customer models.

Co-Marketer: As we have discussed, think of the co-marketer not as a tool, but as a person. Co-Marketers like Raman will take on goals rather than do simple request-reply chats. This is the next generation of AI where an AI agent can spawn and supervise other agents, much like a manager can. From segmentation to content to channel orchestration, AI agents can do the work of a marketing department to assist the CMO. What the CMO needs to do is to give the broad direction. For example, the CMO could say, “For my Best Customers, I need to ensure 20% revenue growth and an increase in frequency of purchase.” The Co-Marketer then should be able to identify the right products and the persuasion messages specific to each individual (N=1) to work towards achieving the outcome. For this, the co-marketer will need to coordinate with a Digital Twin for every customer.

Digital Twin: The co-marketer works on behalf of the CMO; the digital twin is a representation of a customer. It is a ‘living’ embodiment of the data that the system has. It is constantly learning from the actions of the real customer and other streaming data. It stays a few steps of the actual customer, thus helping the co-marketer predict what actions are likely to be done next and therefore guide the customer journey towards the goals the CMO wants. The digital twin can also work for the customer: identifying latest trends, scouring deals, even creating content which its “real-world” representation (the customer) is likely to consume.

Mirror World: The world of autonomous AI agents between the CMO and the customers can be thought of as the “mirror world.” It is a world of constant action. Digital twins are at work computing the next best actions, and the co-marketer is testing hypotheses and stimuli. Think of this as a playground to run an infinite set of A/B tests for every customer to see what paths will provide the outcomes the marketer wants.

Large Customer Model (LCM): This is the foundational model for all interactions. Just like today’s LLMs, the LCM is built on data – customer data, catalog data, real-world data (weather, news, social media trends), and results from the myriad experiments being performed. Think of the LCM as a CDP on steroids, constantly sifting through millions and billions of new inputs to update the digital twins and inform the co-marketer.

All this may sound futuristic. But it’s a future which is coming fast. It has been years and decades in the making. Brands had the data and static workflows, but this was way beyond the capability of humans to process and action dynamically. Think of this as the next generation: beyond algorithms and early multi-modal Gen AI systems. A generation in AI is counted in months, not years. This exponential growth will lay the foundation for the new world of Martech – think of this as M3, where M1 were the point solutions and M2 is the unified stack. By combining with E3 (hotlines via email), M3 becomes the mechanism to power retention and revenue maximisation at scale for every customer. This is what will eliminate the AdWaste that has become the monster that eats up brand profits. E3 and M3 – with their focus on hotlines and conversions, respectively – are the twin engines to power brands in their Profipoly Quest, and CMOs to CEOs.

8

Customer View

Arun is a loyal customer of A1Books. He opens his email inbox to find the daily micron from A1Books. Today’s email has an excerpt from Liu Cixin’s new book. It also has a quiz on “The Three-Body Problem” which he takes and maxes. His is rewarded with 12 µ for this success. He remembers telling A1Books to test his knowledge on the subject after having watched a recent Netflix series. The quiz was custom created for him. Arun has a vacation coming up in Thailand, and wants A1Books to give him suggestions on books about the country – history, travel guides, food, and more. The email now becomes a conversational platform and shopping cart. Arun buys two books and also asks A1Books to send a series of interactive quizzes to test his knowledge about Thailand.

Later in the day, Arun is looking for a new bookcase for his growing collection of books. He goes to the A1Books website to browse the collection. In fact, he realises that the need was triggered by a few recommendations he had seen in an A1Books email a few days ago. (How did it know, he wonders.) He shortlists a few, and A1Books then shows him how his books collection would look on the shelves. Of course, A1Books knows all the books he has bought but he is still amazed at how well the books have been categorised and placed on the shelves.

In the evening, on his way back from work, he sees another email from A1Books. There are recommendations of places to visit in Thailand, a short quiz on That history, and as he scrolls down, a carousel of ads for hotels in Bangkok. Because these are extremely relevant and contextual, he sees them more as useful content than “ads”. He does an opt-in with a single tap on one of the ads to get a series of microns from a resort about 25 kms from Bangkok which looks very exciting.

There was a time when Arun used to dread opening his inbox. That has changed. The Mu in the Subjects of the emails informs him that those emails come with incentives and are interactive, and so he prioritises them. The emails themselves are so much more relevant. At times he even wonders if they can read his mind! The emails themselves have become mini-apps. Even when he goes to the websites of these new age brands, he sees them reconfigured to his most recent actions. All this is a far cry from the sameness that permeated the messages Arun received and the content he saw in the pre-AI era.

Arun can now distinctly sense two types of brands: the ones who are AI-first where there is an extraordinary level of personalisation and prediction, and the ones which are still trapped in the past. He knows where he is likely to spend his money, and therefore which brands will survive and which will not. He is reminded of an acronym he had come across a few days ago: ABC, for AI-Brand Customer. A1Books made the leap, and he is now one of their ABCs!

9

Summary, Critique, Enhancements

ChatGPT

Summary

The essay explores the concept of a Co-marketer, an AI-powered assistant in the martech space, which acts as a copilot in marketing endeavors. Drawing inspiration from Ethan Mollick’s idea of “co-intelligence,” it positions the Co-marketer as a transformative tool for B2C companies, offloading repetitive tasks and optimizing marketing strategies for enhanced customer engagement and conversion. The narrative extends to imagining practical applications, like an AI assisting a CMO in real-time marketing decisions, thereby revolutionizing the martech industry and propelling businesses towards more personalized and efficient marketing practices.

Critique

The essay offers a visionary outlook on AI’s potential in martech but could benefit from more tangible examples and case studies to ground its predictions. While the concept of a Co-marketer is compelling, the essay might overestimate the current capabilities of AI, risking an overly optimistic view that could overlook practical challenges like data privacy concerns, integration complexities, and the nuanced understanding of human behaviors that AI has yet to fully grasp. Addressing these potential limitations and providing a balanced view of AI’s role in marketing could enhance the essay’s depth and credibility.

Enhancements

To enrich the Co-marketer concept, consider incorporating elements like ethical AI usage, continuous learning mechanisms that adapt to changing market dynamics, and more collaborative features that facilitate human-AI interaction. Integrating feedback loops where marketing teams can input real-world outcomes to refine AI predictions and strategies could also add value, ensuring that the Co-marketer evolves in alignment with business goals and customer expectations.

Claude

Summary

This essay explores the concept of a “co-marketer” – an AI-powered co-worker that can assist marketers in B2C companies. It examines how martech companies can create an effective co-marketer and how Chief Marketing Officers (CMOs) can leverage such a system.

The key elements for building a co-marketer include robust data aggregation and analysis capabilities, domain knowledge embedding, conversational interfaces, predictive capacities, and continuous learning. The co-marketer can then help CMOs in areas like campaign planning and optimization, content creation and personalization, market intelligence and trend spotting, collaborative decision-making, and team enablement.

The essay also delves into the idea of “co-intelligence” from Ethan Mollick’s work, where the co-marketer is viewed as a collaborative “co-worker” rather than just a tool. It highlights how the co-marketer can adapt and learn, complementing the CMO’s expertise and intuition to drive better marketing outcomes.

The essay also introduces the concepts of digital twins, mirror worlds, and large customer models as foundational technologies that enable the co-marketer to function effectively. It envisions the co-marketer as a core component of the next generation of martech, known as “M3”, that can help eliminate “AdWaste” and empower brands to build enduring customer relationships.

Critique

The essay provides a comprehensive and well-structured overview of the co-marketer concept, including its potential benefits and the technical elements required for its development. The author effectively weaves in insights from industry experts like Ethan Mollick to provide a solid theoretical foundation.

One strength of the essay is the level of detail in describing the key capabilities a co-marketer should possess, such as data aggregation, domain knowledge, conversational interfaces, and predictive abilities. This level of specificity helps readers understand the technical complexities involved in creating such an AI-powered co-worker.

However, the essay could be strengthened by including more real-world examples or case studies to illustrate how the co-marketer concept has been or could be implemented in practice. Providing concrete examples of how CMOs have leveraged a co-marketer to improve marketing outcomes would make the ideas more tangible and relatable for the reader.

Additionally, the essay could explore potential challenges or limitations of the co-marketer approach, such as concerns around data privacy, ethical considerations, or the integration with existing marketing technologies and processes. Acknowledging and addressing these issues would lend the essay more balance and depth.

Overall, the essay presents a compelling vision for the role of AI-powered co-marketers in the future of B2C marketing, but could benefit from more practical examples and a more nuanced discussion of potential obstacles and tradeoffs.

Enhancements to the Co-Marketer idea

To further enhance the co-marketer concept, the essay could consider the following elements:

1. Explainability and Transparency: Emphasize the importance of the co-marketer being able to explain its recommendations and decision-making processes to the CMO and marketing team. This transparency can build trust and enable better collaboration.
2. Ethical Guardrails: Discuss the need for clear ethical guidelines and governance structures to ensure the co-marketer’s actions align with the brand’s values and customer preferences. This could include mechanisms for oversight, feedback loops, and the ability for humans to override the co-marketer’s decisions.
3. Adaptive Learning and Personalization: Explore how the co-marketer can continuously adapt its knowledge and decision-making based on the unique characteristics and preferences of the CMO and the marketing team. This personalized approach can help the co-marketer become a more integrated and valuable partner.
4. Multimodal Interactions: Expand on the ways the co-marketer can engage with the marketing team, such as through voice, text, visual aids, and even virtual/augmented reality interfaces. This can create a more immersive and natural collaborative experience.
5. Collaborative Innovation: Discuss how the co-marketer can be leveraged to facilitate ideation, brainstorming, and the development of novel marketing strategies and campaigns. By combining the co-marketer’s data-driven insights with the team’s creativity, the potential for innovation can be enhanced.

Incorporating these elements can further strengthen the co-marketer concept and make it a more comprehensive and adaptable solution for CMOs and marketing teams.

Gemini

Summary

This essay explores the concept of a co-marketer, an AI-powered “co-worker” for B2C marketers. The author argues that current martech solutions require significant human effort and lack personalization. Co-marketers, built with machine learning and large customer models (LCMs), can analyze vast amounts of data, predict customer behavior, and automate tasks. This frees up marketers to focus on strategy and creativity.

The essay details how co-marketers could be built and used by CMOs, including tasks like campaign planning, content creation, and real-time optimization. It emphasizes the collaborative nature of co-marketers, working alongside human marketers to achieve marketing goals.

The essay concludes by describing the broader ecosystem of technologies that will enable co-marketers, including digital twins (customer representations), mirror worlds (simulations for testing), and LCMs. This future martech (M3) promises to eliminate advertising waste and maximize customer lifetime value.

Critique

The essay provides a compelling vision for how AI can revolutionize B2C marketing. The co-marketer concept offers a clear solution to the challenges of data overload and personalization at scale.

However, there are some areas for improvement. The essay doesn’t delve into potential drawbacks of co-marketers, such as bias in algorithms or lack of human empathy in marketing messages. Additionally, the technical details of building and deploying co-marketers could be more fleshed out.

Finally, while the essay mentions data privacy, it could be explored further. How will co-marketers ensure responsible data collection and use to maintain customer trust?

Enhancements

• Explainability and Transparency: Co-marketers should be able to explain their reasoning behind recommendations, allowing for human oversight and trust-building.
• Ethical Considerations: Co-marketers should be programmed with ethical guidelines to prevent manipulation or bias in marketing strategies.
• A/B Creativity Testing: Co-marketers could not only optimize campaigns but also test different creative approaches, fostering innovation alongside data-driven decision making.
• Omnichannel Integration: Co-marketers should seamlessly integrate across all customer touchpoints, ensuring a consistent and personalized experience.

10

More Arun Stories

ChatGPT

Imagine Arun beginning his day sipping coffee and scrolling through emails. He stumbles upon a personalized message from A1Books, highlighting a new release in a thriller series he’s been following. Intrigued, he clicks through to the AI-powered website, where Raman, the virtual Co-Marketer, greets him with a tailored selection of books based on his reading habits.

As Arun explores, Raman suggests a limited-edition bundle featuring the new release, complete with author-signed memorabilia. Enthralled by the offer and the seamless interaction, Arun adds the bundle to his cart, along with a recommended prequel he missed.

Later, while taking a break at work, Arun revisits A1Books for a quick escape into the literary world. Raman updates him on a live author Q&A happening in an online book club formed around the thriller series. Joining the session, Arun finds himself in a lively discussion, sharing theories and insights with fellow enthusiasts.

By the end of the day, not only has Arun enriched his book collection, but he’s also deepened his engagement with the A1Books community, all thanks to the personalized, AI-driven journey crafted by Raman. This experience cements his loyalty to A1Books, turning a routine purchase into a memorable adventure in the world of books.

Claude

Arun, a busy professional in his mid-30s, woke up to a notification from the A1Books app on his smartphone. “Good morning, Arun! Based on your recent reading interests, we’ve curated a selection of new releases and hidden gems that we think you’ll enjoy.”

Intrigued, Arun tapped on the notification and was taken to a personalized landing page on the A1Books website. The page displayed book recommendations tailored to his preferences, including a new bestselling thriller, a thought-provoking non-fiction title, and a collection of short stories by his favorite author.

“Hmm, this looks interesting,” Arun mused as he scrolled through the recommendations. He noticed a prompt at the bottom of the page: “Want to know more? Chat with our AI assistant.” Curious, Arun clicked on the prompt, and a conversational interface appeared.

“Hello, Arun. I’m Claude, an AI assistant created by A1Books to help you discover great reads. How can I assist you today?” the interface responded.

Arun explained that he was particularly intrigued by the non-fiction title and asked Claude for more details. The AI assistant provided a concise summary of the book, highlighting the key themes and insights it offered. Arun was impressed by the depth of knowledge and natural language interaction.

“That sounds right up my alley. Can you help me add it to my cart and checkout?” Arun requested.

“Absolutely, Arun. Let me handle that for you.” Claude seamlessly guided Arun through the purchase process, applying any relevant discounts or offers. “Your order has been placed, and the book will be delivered to your doorstep within the next two business days. Please let me know if you have any other questions or if there’s anything else I can assist you with.”

Arun was surprised by the level of personalization and effortless interaction. “This is really impressive, Claude. I had no idea A1Books had such advanced AI capabilities.”

“Thank you, Arun. A1Books is committed to providing a truly exceptional customer experience. Our AI-powered systems, including digital twins and a co-marketer, work tirelessly to understand your preferences and anticipate your needs,” Claude explained.

As Arun continued his day, he encountered various touchpoints with the A1Books brand, each seamlessly integrating the AI-driven experience. From receiving personalized book recommendations via email to engaging with the co-marketer on the website to help him discover new authors, Arun felt like he had a personal concierge assisting him throughout his reading journey.

By the end of the day, Arun had not only discovered a new favorite book but also felt a stronger connection to the A1Books brand. He appreciated how the company’s AI-first approach had transformed the way he interacted with and discovered books, making it a truly personalized and effortless experience.

“This is the future of retail,” Arun thought to himself as he settled in to start reading his new purchase. “A1Books has set the standard for what a customer-centric, AI-powered brand can achieve.”

Gemini

Arun stirred awake to the soft chime of his bedside speaker. “Good morning, Arun,” a gentle voice greeted him. “Looks like today might be a good day to curl up with a new book. Based on your recent browsing history, I think you might enjoy ‘Emergence’ by David Chalmers. It explores the mysteries of consciousness, a topic you’ve shown interest in lately.”

Arun smiled. This was Anika, his AI companion from A1Books, the online bookstore he frequented. He’d initially been skeptical of an AI assistant, but Anika had proven surprisingly helpful. She not only recommended books but also tracked his reading progress, synced audiobooks across devices, and even facilitated discussions with other readers online.

After breakfast, Arun headed to work. On the train, he pulled out his phone and browsed the A1Books app. Anika had curated a personalized feed for him, featuring new releases in his favorite genres alongside articles about upcoming author events. He noticed a notification: “Looks like you’re nearing the end of your current book. Would you like to pre-order the sequel?” With a tap, he secured his copy, eager to continue the story.

Later that day, while grabbing lunch, Arun received a video call from A1Books. It wasn’t Anika this time, but a friendly face he recognized – his favorite author, giving a live Q&A session. Anika had noticed his past purchases of the author’s work and facilitated the surprise connection. Arun’s day was brightened by the unexpected interaction.

Back home, Arun settled into his favorite armchair, ready to delve into “Emergence.” As he read, Anika displayed contextual information and definitions alongside the text, enriching his understanding. He finished the book in a single sitting, feeling intellectually stimulated and wanting more.

He opened the A1Books app again. Anika suggested joining a virtual book club discussing “Emergence.” Intrigued, Arun signed up. The evening unfolded with lively discussions with fellow readers, facilitated by Anika’s AI algorithms that matched participants and steered conversations.

Before bed, Arun reflected on his day. A1Books, with Anika’s guidance, had transformed his reading experience. It wasn’t just about buying books anymore; it was about discovery, connection, and a deeper engagement with the literary world. He drifted off to sleep, already anticipating Anika’s recommendations for tomorrow.

**

[Rajesh] Reading the summaries, critiques, enhancement suggestions, and the stories from ChatGPT, Claude, and Gemini, I could not help but think: Isn’t it amazing what AI can already do? For me, AI has already become a co-writer. While I still do the first-level of thinking and writing, I find the AIs coming up with angles I had not thought about. This is the world of co-intelligence. It is already here, for those of us who chose to inhabit it.