Author: Rajesh Jain

An Entrepreneur based in Mumbai, India.

Thinks 1281

WSJ: “Politicians and the press mislead voters and readers when they claim that tax cuts for the rich don’t benefit other economic classes. We all gain from new, improved products made possible by innovative startups funded by the wealthy. Excessive taxation, doubtless a feature of a “middle-out” plan, could deplete the funds that entrepreneurs use to start and sustain useful ventures. Americans shouldn’t worry so much about wealth distribution. Instead, we should be grateful for how the wealthy enable entrepreneurial ideas to come to life, allowing everyone to prosper.”

Noah Smith: “[Here is] a theory of how totalitarianism might naturally triumph. The basic idea is that when information is costly, liberal democracy wins because it gathers more and better information than closed societies, but when information is cheap, negative-sum information tournaments sap an increasingly large portion of a liberal society’s resources. Remember that I don’t believe this theory; I’m merely trying to formulate it.”

Ryan Bourne: “Price controls are making a comeback across the United States. Federal, state, and local governments increasingly control rents, minimum wages, interest rates on short-term loans, healthcare prices and premiums, credit card late fees and even food delivery service charges. The sharpest inflation burst since the early 1980s has also seen Democrats demand a federal anti-price gouging law, anti-”junk fees” rules, and even efforts to prevent companies engaging in “shrinkflation” or algorithmic dynamic pricing. I call all this The War on Prices, the title of a new Cato Institute book. And when it comes to this war, economists are typically pacifists. The long sweep of history, from ancient Egypt to modern America, shows us that price controls can’t quell inflation, because they don’t fundamentally change the money supply or aggregate production. What controls on market prices guarantee is inefficiency. They squelch the delicate coordination mechanism that prices and their movements provide to encourage economical action. Price ceilings, the most common incarnation, are thus a tried-and-tested recipe for shortages, declines in product quality, and black markets.”

Anirban Mahapatra: “A study published in Frontiers in Psychology recently found that students who took handwritten notes had higher levels of brain activity across the regions responsible for movement, vision, sensory processing, and memory. In contrast, typing led to minimal activity in these areas. Researchers Audrey van der Meer and Ruud van der Weel suggest handwriting forces students to process information more deeply. When you’re writing by hand, you can’t copy everything down verbatim, so you have to think as you write, unlike typing, where the temptation to transcribe lectures word-for-word is high. In addition, handwriting reinforces memory and learning pathways. The action of forming letters creates a feedback loop with our visual and sensory systems, embedding information more deeply in our brains. This process is like drawing or building something. In all these cases, the process helps strengthen the concept and makes it stick in our memory.”

VentureBeat: “Researchers from the University of Chicago have demonstrated that large language models (LLMs) can conduct financial statement analysis with accuracy rivaling and even surpassing that of professional analysts. The findings, published in a working paper titled “Financial Statement Analysis with Large Language Models,” could have major implications for the future of financial analysis and decision-making. The researchers tested the performance of GPT-4, a state-of-the-art LLM developed by OpenAI, on the task of analyzing corporate financial statements to predict future earnings growth. Remarkably, even when provided only with standardized, anonymized balance sheets, and income statements devoid of any textual context, GPT-4 was able to outperform human analysts. “We find that the prediction accuracy of the LLM is on par with the performance of a narrowly trained state-of-the-art ML model,” the authors write. “LLM prediction does not stem from its training memory. Instead, we find that the LLM generates useful narrative insights about a company’s future performance.””

Life Notes #13: Gym

A few months ago, I started gym training. My sister, a doctor, has been telling me for many years that I need to do more than just a 30-minute walk five times a week. Her point was that the body starts losing muscle mass after the age of 40, and unless I do strength training, things could become harder as I grew older.

Here is the medical explanation from Henry Ford Health: “As we age it’s normal to experience some reduction in muscle mass, strength and function, a condition known as sarcopenia. These changes begin as early as your 30s and continue at a rate of 3% to 5% per decade. The good news is that strength training can help you maintain and rebuild muscle at any age. Research shows that older adults see even greater improvements in their muscle strength versus younger adults. “So it’s never too late to start,” says Pamela Webert, MS, ACSM-CEP, an exercise physiologist at Henry Ford Health. “Everyone should be doing strength training as part of their exercise program.””

We have a gym in our building. I never once entered it during the past two decades. Just seeing all the equipment through the glass door scared the daylights out of me! Walking was so much easier.

Last October, after another push by my sister, I decided to change. Under the guidance of a trainer, I now workout for about 35-40 minutes three times a week. The first few sessions were tough given that my body had seen no real exercise through life (except for a few years of yoga a long time ago). Having a trainer come is good because there is no “I will do it tomorrow” excuse. Now, even though I don’t fully enjoy it (!), it has become part of my weekly routine. As one grows older, the realisation starts dawning that good health must become a priority.

I asked ChatGPT to list the physical health benefits of gym training:

  • Improved Muscle Strength and Tone: Regular weight training helps build and maintain muscle mass, which naturally declines with age. This can enhance your strength, endurance, and overall physical performance.
  • Increased Bone Density: Weight-bearing exercises, such as weight lifting and resistance training, can help increase bone density, reducing the risk of osteoporosis and fractures.
  • Enhanced Cardiovascular Health: Incorporating cardio exercises, like treadmill walking or cycling, can improve heart health, lower blood pressure, and reduce the risk of heart disease.
  • Better Joint Health and Flexibility: Strengthening the muscles around your joints can improve stability and reduce the risk of injuries. Stretching and flexibility exercises can help maintain joint flexibility and reduce stiffness.
  • Weight Management: Regular exercise helps burn calories and can aid in maintaining a healthy weight or losing excess weight, which is crucial for overall health.

So, one piece of advice: don’t wait until it’s too late. Begin training now (especially if you were over 50 years of age).

Thinks 1280

WSJ: “The tech labor market is in an unbalanced state. There is demand for a specific type of tier-one AI talent—namely those who have the technical knowledge or experience working with large language models, or LLMs, that fuel chatbots with the ability to generate content. There are companies seeking candidates with those skills, but not enough workers who are qualified to do them. Then there is everyone else. Thousands of people have been laid off in the past few years, and many of those who remain employed are dealing with new management styles, reorganizations and microcuts, as more resources get shifted into AI. Those workers are now taking courses in AI, adding buzzwords to their résumés and competing in an increasingly crowded field.”

NYTimes: “In the fall of 2020, Amazon looked unstoppable. The pandemic lockdowns had supercharged its e-commerce business, and executives were busy hiring an army of new workers and expanding the number of Amazon fulfillment warehouses across the US. But the tech giant would soon face the biggest threat to its online shopping empire in recent memory, and it would come from an unlikely place: China. Over the last few years, two Chinese-owned e-commerce platforms—Shein and Temu—have quietly become some of the most popular shopping websites in the US. Shein specializes in low-end women’s fashion, while Temu focuses on home decor and household items—the same type of affordable, made-in-China products that many American consumers have come to associate with Amazon.”

Mint: “Systems that rely on more than one chatbot or use multiple Large Language Models (LLMs) are called multi-agent systems (MAS). A chatbot on the website of a bank, auto, insurance, edtech or any other company has improved over the years, thanks to advances in AI and natural language processing. But it still falls short of answering questions that might require more ‘human-like’ capabilities or pulling data from different domains. The solution lies in using multiple bots or more than one AI (artificial intelligence) model—each with a different, specialized capability, and complementing each other to deliver a better response…Just as teams of humans are better in tackling complex problems, more than one chatbot will improve customer interactions. So, a Hindi language chatbot could combine with a math teaching bot and deliver math lessons in Hindi. Each is a separate LLM (which helps chatbots understand human input and offer answers) and is better at executing specialist tasks.”

Fei-Fei Li and John Etchemendy: “An LLM is a mathematical model coded on silicon chips. It is not an embodied being like humans. It does not have a “life” that needs to eat, drink, reproduce, experience emotion, get sick, and eventually die. It is important to understand the profound difference between how humans generate sequences of words and how an LLM generates those same sequences. When I say “I am hungry,” I am reporting on my sensed physiological states. When an LLM generates the sequence “I am hungry,” it is simply generating the most probable completion of the sequence of words in its current prompt. It is doing exactly the same thing as when, with a different prompt, it generates “I am not hungry,” or with yet another prompt, “The moon is made of green cheese.” None of these are reports of its (nonexistent) physiological states. They are simply probabilistic completions. We have not achieved sentient AI, and larger language models won’t get us there.”

NYTimes: “China’s industrial dominance is underpinned by decades of experience using the power of a one-party state to pull all the levers of government and banking, while encouraging frenetic competition among private companies. China’s unrivaled production of solar panels and electric vehicles is built on an earlier cultivation of the chemical, steel, battery and electronics industries, as well as large investments in rail lines, ports and highways. From 2017 to 2019, it spent an extraordinary 1.7 percent of its gross domestic product on industrial support, more than twice the percentage of any other country, according to an analysis from the Center for Strategic and International Studies.”

Life Notes #12: IndiaVotes and Elections

IndiaVotes is a website I had created in 2011 during the time I was working for the 2014 election campaign. I had found a gap in the easy availability of election data. While the raw data was available from the Election Commission, it was in PDFs and almost impossible to search. So, a group of us had extracted the data into a database and designed a nice navigation and search interface. I am glad to say that even after 13 years, it remains the best elections data website in India. A Google search for “india elections data” shows IndiaVotes as the #1 search result.

During the recent elections, traffic spiked by a magnitude. I was very surprised. Post 2014, while the site had been updated with the results of all the elections, the interface had not changed, and the site had become slow. I guess its simplicity and authenticity has helped make it popular and the go-to destination for elections data.

It is perhaps time for an overhaul of the site. It needs a Gen AI chat interface – “show me all the constituencies that were won by a margin of under 5%” is much easier than doing the same query on the results pages. It also needs better visualisation of results – we had tried maps once but somewhere it has got lost. Another idea is a “swing calculator” – so enthusiasts can see what would happen if voting patterns changed. I would also like to bring in Form 20 data so it becomes a permanent repository of granular elections data. The one innovation we had done during the recent Lok Sabha elections was a prediction game called YouPredict which attracted a few hundred players. I am hoping that over the next few months, we can create an improved IndiaVotes site – the best needs to become even better!

**

A few friends had called me for my take on the recently concluded Lok Sabha elections. My take: after two wave elections in 2014 and 2019, India has gone back to seat-by-seat, state-by-state, caste-by-caste voting, as was the norm between 1989 and 2014. This is what I had written about in my prescient 2011 essay about how the BJP could win 275 seats in the 2014. For any party to win a majority on its own in India, it needs to create a wave and have a very high hit rate in contested seats. This did not happen in 2024.

PS: Here is the IndiaVotes page summarising the 2024 results. An interesting page to see is the alliances summary – focus on the contested voteshare.

Thinks 1279

WSJ: “Researchers looked at more than 800,000 online reviews for beauty and fashion items listed on Amazon’s website. They found that online reviews written in the present tense were more likely to be “liked”—that is, receive a thumbs-up emoji from readers—than reviews written in the two other tenses. “A 50-word review only using verbs in the present tense is about 5.5% more likely to be ‘liked’ than a 50-word review using no present-tense verbs at all,” says David Fang, a doctoral student at Stanford University and one of the paper’s authors.” Also: “We found that consumers give, on average, a higher overall rating when asked to rate the overall experience and several attributes of the experience compared with when they are asked to rate the overall experience alone. In other words, when consumers can speak to what specifically they didn’t like about an experience, they weight those negative aspects less heavily in their overall ranking.”

Ruchir Sharma: “In his farewell address, Ronald Reagan described America as the “shining city on a hill”, open to “anyone with the will and heart to get here”. I was one of those inspired to try, and today the dynamic mix of academics and entrepreneurs who energise the world’s technology leader still strikes me as a marvel. Of the top 100 US companies, 10 now have chief executives who were born in my home country, India, a breakthrough that could have happened only in a capitalist meritocracy.  Nonetheless, I worry about where the US is leading the world now. Faith in American capitalism, which was built on limited government that leaves room for individual freedom and initiative, has plummeted. Most Americans don’t expect to be “better off in five years” — a record low since the Edelman Trust Barometer first asked this question more than two decades ago. Four in five doubt that life will be better for their children’s generation than it has been for theirs, also a new low…America has become unhealthily dependent on loose money and big government.”

Wired: “[Microsoft’s] Bubeck says these results seem to indicate that making future AI systems smarter will require more than just scaling them up to still greater sizes. And it also seems likely that scaled-down models like Phi-3 will be an important feature of the future of computing. Running AI models “locally” on a smartphone, laptop, or PC reduces the latency or outages that can occur when queries have to be fed into the cloud. It guarantees that your data stays on your device and could unlock entirely new use cases for AI not possible under the cloud-centric model, such as AI apps deeply integrated into a device’s operating system.”

Ted Sarandos: “I think that A.I. is a natural kind of advancement of things that are happening in the creative space today, anyway. Volume stages did not displace on-location shooting. Writers, directors, editors will use A.I. as a tool to do their jobs better and to do things more efficiently and more effectively. And in the best case, to put things onscreen that would be impossible to do. Think about this gigantic leap from hand-drawn animation to computer-generated animation, and look how many more people animation employs today than it used to…I have more faith in humans than that. I really do. I don’t believe that an A.I. program is going to write a better screenplay than a great writer, or is going to replace a great performance, or that we won’t be able to tell the difference. A.I. is not going to take your job. The person who uses A.I. well might take your job.”

Economist: “A resumé is not a list of every job you ever had. It is not your autobiography. It is, like that hair-care advert, a marketing tool. Your audience is made up of recruiters and hiring managers. Like cocktail-party guests, they do not take a long time to decide if they want to keep talking. According to one study, such professionals spend an average of 7.4 seconds skimming a job application.”

Life Notes #11: Blogging and AIs

A couple of years ago, I had written about my blogging system. “At any time, I have a list of topics that I can write on. And that is good enough to get started. Once I start writing, the ideas flow. Some of the writing is original, while at other times I will aggregate what others have written in a single place. This reading and collating also helps me learn new topics. At times, I find myself going back to my earlier writings to refresh my own thinking.”

I have now settled into a routine. Most of my blogging happens in the early mornings on weekends. Sitting at my home desktop, I write for about 2-3 hours in a flow. (On weekdays, it’s either gym or walk so I don’t get that kind of contiguous time.) I will typically have thought through the essay theme, the sub-topics, and the opening sentences by the previous night. This way, I can begin writing without wasting precious time thinking about what to write.

Much of my recent writing has been around new ideas in marketing. Since I write for myself, there is no pressure to be perfect. Each essay moves my thinking forward. Even as I have a broad structure in mind, as I write the story takes its own course. This is what I like the most: the process of writing itself begets more writing. For example, during the process of thinking about how AI will impact marketing, many sub-themes came up: large customer models, co-marketer, and digital twins. I then also explore synthetic data and vector search, both of which were new to me. In email too, a similar process has followed. Writing about AMP led me to Email 2.0, 3.0 and eventually Action Ads and Epps (Email Apps). What I like most is naming the ideas. Velvet Rope Marketing, Generative Journeys, Co-Marketer, Inbox Commerce, Segment Twins, Singular Twins, Profipoly, Action Ads, Epps – these are all words and phrases I have come up with.

In the past year or so, one big change in my writing has been the use of AIs. I use a combination of ChatGPT, Claude, and Gemini to help with several tasks: exploring ideas, summarising my past writings, expanding and improving on briefs, helping write stories from my ideas, and preparing briefs to encourage others to read what I have written, critiquing what I have written, and adding new ideas to what I have written. Working with AIs has been the biggest change in my blogging process, and one that has helped make the process faster and better. It is almost as if I am working with a co-blogger: one who understands my thinking and works interactively with me. More than my specific voice (which is of course always there), what I want is to ensure a proper and full exploration of the ideas I am writing about. This is where the AIs excel.

The key to getting the most from the AIs is of course prompting. This is where my past writings and briefs come in. It is not just about “Write an essay about email apps” but more like “Here is all that I have written so far. Improve and expand on it.” To borrow a phrase from Kazuo Ishiguro’s “Klarna and the Sun”, the AIs have become my “Artificial Friend”. I have used the AIs to improve my titles and help me with naming (“Give me a better phrase for Singleton Twin starting with the letter “S” – and it came up with Singular Twin). I talk to it as if it’s a person working alongside me.

For me, blogging has become a way of life, an integral part of me. It frees my imagination, fuels ideas, and births innovations. The words I wrote four years ago still ring true: “I think every entrepreneur should write a blog. Not just tweets or pithy LinkedIn posts. But write about one’s ideas and aspirations in real-time. Give people a glimpse into the world that you see. Because that is what you are really doing – creating a future ahead of others. And blogging is a great way to accelerate that future.”

Thinks 1278

WSJ: “Getting angry doesn’t just hurt our mental health, it’s also damaging to our hearts, brains and gastrointestinal systems, according to doctors and recent research. Of course, it’s a normal emotion that everyone feels—few of us stay serene when a driver cuts us off or a boss makes us stay late. But getting mad too often or for too long can cause problems. There are ways to keep your anger from doing too much damage. Techniques like meditation can help, as can learning to express your anger in healthier ways.”

Economist: “The conventional language of career success moves in only one direction: up. You scale the career ladder or climb the greasy pole. If you do well, you have a rapid ascent. And if you really succeed, you reach the top. No one ever rings home to share the news that they have reached a plateau. But there is another type of career trajectory. Sideways moves, to jobs that don’t involve a promotion or even necessarily a pay rise, can be a boon to employees and organisations alike. A study carried out by Donald Sull of the Massachusetts Institute of Technology and his co-authors in 2021 found that the availability of lateral career opportunities has a marked impact on employee retention. Their research found that chances to move sideways were two and a half times more important than pay as a predictor of workers’ willingness to stay at a firm. Another paper, by Xin Jin of the University of South Florida and Michael Waldman of Cornell University, concluded that lateral moves did not just benefit organisations: employees who experienced them were more likely to be promoted and to enjoy higher wage growth later in their careers than employees who did not. You can move up by first moving sideways.” [via Mint]

Arnold Kling: “Suppose that within the next three years, I am using an AI-powered app to write this substack. I can tell the app to summarize substacks and other sources that I follow. I can tell the app to grab passages to quote. I can tell the app the main point I wish to make in an essay and have it compose a draft in my style. Once an app can do those things, I no longer need a personal computer. I just need a headset that can handle AI, using the cloud if necessary. I could keep up this substack while on a walk or on a bike ride. In the future, either AI realizes its promise or it doesn’t. If it does, then we will be accessing computer resources by using our voices, possibly with gestures. If AI doesn’t pan out, we will still need personal computers and Microsoft software, but an AI PC won’t be much of an improvement over the laptop I am using now. I see no future scenario in which masses of people will be using an AI PC. That is what I mean when I say that an AI PC is an oxymoron.”

WSJ on a great vacation: “You don’t do plan as much, you do less of what you like, you take a break from enjoying yourself, and you make yourself do things that are actually uncomfortable. If that sounds like the recipe for a lousy trip, that’s understandable. But science suggests otherwise. So my advice is to forget about what feels like the smart thing to do and embrace the opposite. The result may very well become the stories you cherish and share long after your return.”

Consumer Epps for Inbox Attention

Published July 1, 2024

1

Overview

This is the third essay in the Epps (Email Apps) series.

In the first essay (Epps: The Next Evolution in Email Engagement), I delved into the transformative potential of Epps, a new category of interactive email experiences built using AMP technology. By combining the characteristics of multi-screen implementations, real-time updates, and self-contained functionality, Epps can revolutionise email engagement by providing app-like experiences directly within the inbox. The essay explored the wide-ranging applications of Epps across industries, from e-commerce and banking to healthcare and entertainment, and presented a compelling go-to-market strategy to drive adoption among marketers. I explained how Epps represent the next evolution in email engagement, offering brands a powerful tool to capture attention, drive conversions, and foster deeper relationships with their customers. “Think of Epps as the third major property for brands, alongside websites and mobile apps. Each has its unique strengths and can operate independently. In the evolution from websites to mobile apps, many businesses reduced their websites to mere placeholders, primarily to drive app downloads. I foresee a similar trend with Epps – websites may primarily serve to capture subscriptions and showcase the Epp, with the Epp itself becoming the primary platform for user engagement and interaction.”

In the second essay (Email’s Epps Era: Transforming Customer and Employee Engagement), I explored the transformative potential of Epps in revolutionising customer and employee engagement. By leveraging AMP technology, Epps create interactive, personalized experiences within the email inbox, driving attraction, attention, action, addiction, and acquisition (the 5 As). I discussed various examples of consumer Epps, such as news, sports, stocks, and games, and wrote about the potential of a “killer Epp” like WePredict, a prediction market game that combines the wisdom of crowds with the inherent desire to predict the future. Additionally, I examined the potential of Employee Epps in enhancing corporate communication, training, and engagement by encouraging employees to map their personal email IDs to their company-issued IDs. I concluded: “Consumer Epps, Brand Epps, and Employee Epps have the potential to revolutionise the email inbox, transforming it into a dynamic, engaging, and immersive digital space. By seamlessly blending personal, professional, and consumer experiences, Epps turn the inbox into a microcosm of life, offering users a one-stop destination for entertainment, education, productivity, and rewarding interactions…The convergence of these Epps heralds a new era for email, breathing new life into a tried-and-true communication channel…In the coming years, the rise of Epps will redefine how we interact with our inboxes, setting new standards for digital engagement and paving the way for a more connected, productive, and fulfilling future.”

In this essay, I will dive deeper into the realm of Consumer Epps, exploring their pivotal role in capturing and sustaining inbox attention. Just as personal and group messaging has driven our frequent engagement with platforms like WhatsApp, the email inbox needs equally compelling reasons to entice users to open it multiple times throughout the day. Beyond brand marketing emails, which are often perceived as ads, Consumer Epps can offer a diverse range of engaging experiences. We’ll uncover how they can transform the inbox into an essential, multifaceted hub for daily interactions, providing users with continuous value and enhancing their overall email engagement. What can these Consumer Epps be? Let’s explore the possibilities.

2

Advantages

Epps have three significant advantages over conventional emails and apps which we will build on. First, Epps are interactive. This means that all the actions can be done within the email itself without requiring a clickthrough to a website or app. Second, Epps can be updated in real-time. Every time the email is opened, it can fetch the latest information from the server and thus eliminate the need for sending new emails. Third, Epps can be contained within the email inbox and don’t need separate apps to be downloaded. Let’s discuss each of these.

Interactivity

  • Self-Contained Actions: Epps are designed to be fully interactive within the email itself. This means users can complete various actions directly in the inbox without needing to click through to external websites or apps. Whether it’s scanning through a carousel of news items or getting additional info on a stock or player, all interactions happen seamlessly within the email. This reduces friction and enhances the user experience by keeping everything in one place.
  • Enhanced User Engagement: The interactivity of Epps encourages users to engage more deeply with the content. Interactive elements such as quizzes, polls, and games can make emails more engaging and fun, leading to higher user retention and satisfaction.

Real-Time Updates

  • Dynamic Content: One of the standout features of Epps is their ability to update in real-time. Each time the email is opened, it can fetch the latest information from the server, ensuring that the content is always current. This eliminates the need for sending multiple emails to update users, as a single Epp can continually refresh with the latest data.
  • Timeliness and Relevance: Real-time updates ensure that users always have access to the most relevant information. For instance, a news Epp can display breaking news as it happens, or a stock Epp can show the latest portfolio updates. This capability makes Epps highly valuable for time-sensitive content and keeps users informed without cluttering their inbox with new messages.

Contained within the Inbox

  • No Need for Additional Apps: Epps operate entirely within the email inbox, eliminating the need for users to download and manage separate applications. This is particularly advantageous for users who prefer not to clutter their devices with multiple apps or who are looking for a more streamlined digital experience.
  • Convenience and Accessibility: Since Epps are contained within the inbox, they are accessible from any device that supports email. Users can access their Epps from their smartphones, tablets, or desktops without worrying about compatibility issues or needing specific software. This universality enhances accessibility and ensures a broader reach. (Note: Epps use AMP as the underlying technology. AMP is supported by Gmail and Yahoo Email, and most browsers. It is not supported by Apple’s native email client.)

By building on these three advantages – interactivity, real-time updates, and inbox containment – Epps can significantly enhance email engagement and user experience. They transform the inbox into a dynamic, multifaceted platform that meets various needs, from entertainment and information to productivity and commerce, all within the familiar and convenient environment of the email inbox.

In my previous essay on Epps, I had discussed several Consumer Epps:

  • Part 3 discussed news, sports, and stocks
  • Parts 4 and 5 covered additional ideas, and briefly touched upon quizzes and games
  • Parts 6 and 7 explored a possible killer Epp, “WePredict”, a prediction markets game

3

MyToday Dailies

A few years ago, I wrote about a now-defunct service called MyToday. I had envisioned MyToday as daily micro-newsletters. “[They] can be read in 15-30 seconds unlike the regular emails that we typically get from brands which are full of images, text and links. Think of them like SMSes – you want to see them right away rather than later. The microns are not ad-driven, but content-rich. They could have breaking news, market updates, thoughtful quotes, recipes, health tips, travel recommendations, an excerpt from a poem, a brief on a new topic. The point is that you, as an email subscriber, see them almost as soon as they come. And in that fleeting moment, you are also exposed to the brand. Microns come daily and automatically – at the same time. Their goal? Become a habit in your life.”

MyToday microns covered various topics:

  • News across multiple categories and languages
  • Daily delights like quotes, word meanings, trivia, quizzes
  • Cultural content like short stories and poetry
  • Snippets from economics, philosophy, and history

There were over 30 microns, leading to more than 300 emails a month for subscribers of 10 microns, creating inbox clutter and high sending costs.

Epps can revolutionise this experience. MyToday could become a single Epp with various categories as options within it. Since Epps can fetch information in real-time when opened, only one email would be needed every 30 days (due to AMP email validity). Recipients simply need to “star” the email for easy access.

Epps go further by allowing new snippets to be fetched every time the email is opened. Subscribers could get as many quotes as they want in a day with a single tap on the appropriate section.

Epps could thus transform microcontent consumption, eliminating the need for multiple apps or emails. A single Epp could provide an unlimited on-demand supply for a month, streamlining the user experience and reducing clutter.

Moreover, the adaptability of Epps makes them a powerful tool for personalising content delivery. Users can customise their Epps to include only the topics they are most interested in, ensuring that every snippet they receive is relevant and engaging. This level of personalisation can significantly enhance user satisfaction and foster a deeper connection between the user and the brand.

The shift from traditional emails to Epps also opens up new opportunities for brands to innovate in their content strategies. By leveraging the real-time update capabilities and interactive features of Epps, brands can create more dynamic and immersive experiences for their audience. (Imagine new deals and offers showing up every time the Epps is opened.) This not only increases engagement but also provides a competitive edge in the crowded digital marketplace.

4

Arun’s Day

I asked ChatGPT to write a user story to showcase the power of Epps.

Pre-Epps World

Morning Routine: Arun wakes up to an inbox cluttered with multiple emails from various brands. Each email, filled with images and links, takes time to load and navigate. He often skips over them, marking many as read without engaging. To stay updated, he switches between news apps, social media, and newsletters, consuming content in a fragmented manner. His morning is hectic as he juggles multiple sources of information.

Throughout the Day: Arun receives breaking news alerts from different apps, adding to the clutter. For his daily dose of inspiration, he relies on separate apps for quotes and trivia. He checks his stock app intermittently for updates, which requires constant switching between tasks. His phone is filled with numerous notifications, creating a noisy digital environment.

Evening: By evening, Arun feels overwhelmed by the constant stream of information. His inbox is filled with unread emails, many of which are irrelevant by the time he opens them. He spends time deleting and organizing emails, a task he finds tedious. Arun misses out on engaging content because he can’t keep track of everything.

Post-Epps World

Morning Routine: Arun wakes up to a single MyToday Epp in his inbox. This Epp contains all his preferred updates, from breaking news to inspirational quotes. He can access everything with a single tap, saving time and reducing clutter. The Epp’s real-time updates ensure that the content is always fresh. Arun reads through the latest news, checks his stock updates, and enjoys a daily quote, all within one email.

Throughout the Day: Instead of switching between multiple apps, Arun uses the MyToday Epp to stay updated. He receives live sports scores, personalised news, and even participates in interactive quizzes, all within his email. The Epp’s dynamic content feature keeps him informed and engaged throughout the day. When he needs a break, he plays a quick game embedded in the Epp, keeping his mind sharp and entertained.

Evening: In the evening, Arun revisits the MyToday Epp to catch up on any updates he might have missed. He reads an interesting short story and checks his portfolio’s performance. The Epp’s real-time updates mean he doesn’t miss out on any important information. Arun finds that he has more free time and a cleaner inbox, allowing him to focus on what matters most.

Impact of Epps on Arun’s Life

  • Increased Engagement: Arun is now more engaged with his content. The interactive nature of Epps makes learning new things fun and seamless.
  • Better Time Management: With all his content consolidated in one Epp, Arun saves time and reduces the cognitive load of switching between apps.
  • Continuous Learning: Arun uses his free moments to learn new things, play games, and stay updated, enriching his daily routine.
  • Reduced Digital Clutter: His inbox is no longer overwhelmed with multiple emails, making it easier to manage and more pleasant to use.

In summary, MyToday Epps have transformed Arun’s digital life, making it more organized, engaging, and fulfilling. He looks forward to his daily Epp, which keeps him informed, entertained, and inspired throughout the day.

5

Framework

To summarise, here are the various ideas for Epps:

  • News, Stocks, Sports: These information-based Epps can be sent once a month and update in real-time when the email is opened, providing the latest information instantly.
  • Microcontent: Epps with content like bite-sized content like tips and quotes can also be sent monthly, fetching new content on-demand whenever the email is accessed, ensuring always-fresh and relevant snippets.
  • Quizzes and Games: Depending on content volume and type, these interactive Epps Epps can be sent daily or less frequently, engaging users with interactive challenges. For example, a Wordle-like game could present a new word with each interaction.

I asked Claude to see how this framework could be expanded. Here is the lightly-edited response.

  • Personalized Recommendations: Epps can provide users with personalized recommendations based on their interests, preferences, and behaviour. Examples: movie recos, book suggestions, product recos.
  • Social Epps: The purpose is to foster social interaction and engagement among users within the email inbox. Examples: community discussions, peer challenges (like fitness trackers), leaderboards.
  • Utility Epps: These Epps provide users with practical tools and utilities to enhance productivity and convenience. Examples: calendar integration, to-do lists, weather forecasts
  • Sponsored Epps: Collaborate with brands to create sponsored Epps that provide value to users while promoting products or services. They could also allow users to make in-Epp purchases or subscribe to services directly within the email itself.

What is truly revolutionary about Epps is their potential to create an entirely new ecosystem that leverages the unique advantages of the email inbox. Just as Apple’s iPhone introduced a new world of smartphone apps and transformed our daily lives, the push capabilities, interactivity, real-time updates, and self-contained nature of Epps empower content providers, developers, and businesses across industries to create innovative experiences that seamlessly integrate into users’ lives. By harnessing the ubiquity, accessibility, and personal nature of email, Epps offer a frictionless, engaging, and efficient way to consume content, interact with brands, and stay informed, making the inbox a central hub for a myriad of daily activities.

From news and entertainment to e-commerce and productivity tools, the Epps ecosystem promises to streamline tasks, reduce information overload, and provide a more personalised, contextually relevant experience. This transformative approach to digital engagement will foster deeper connections, drive meaningful interactions, and unlock new possibilities for enhancing the user experience in a clutter-free, user-centric environment. As Epps continue to evolve and gain adoption, they have the potential to redefine not just email engagement and marketing but the broader landscape of how we interact with digital content and services in our everyday lives.

6

Add-Ons

There are four additional ideas which could make Epps powerful and make the email inbox even more compelling: Atomic Rewards (Mu), Action Ads, AI, and a category I have termed as “Advanced Innovations.”

Atomic Rewards: Represented as “Mu,” these gamification elements incentivize user engagement. Users can earn Mu by opening emails, participating in quizzes, playing games, or completing interactive tasks. These rewards can be accumulated and redeemed for perks such as discounts, exclusive content, or additional features within the Epp. For instance, Mu could be used to place bids in WePredict. By incorporating Atomic Rewards, Epps create a compelling reason for users to consistently engage with their inbox, transforming mundane email interactions into a rewarding experience.

Action Ads: These redefine the traditional advertising model by embedding interactive, actionable advertisements directly into the email content. Unlike standard ads that redirect users to external websites, Action Ads enable users to engage with the ad content within the email itself, such as making a purchase, signing up for a service, or participating in a survey. For example, an AI-optimised Action Ad could promote a new fitness app or workout gear to a user frequently engaging with fitness-related Epps, increasing the likelihood of conversion. This seamless integration reduces friction and enhances user experience, making it easier for brands to capture attention and drive conversions without disrupting the user’s email journey.

AI Integration: AI can significantly enhance personalization and relevance within Epps. AI algorithms can analyse user behaviour, preferences, and interactions to tailor content and recommendations uniquely for each individual. This can range from personalised news feeds and product suggestions to adaptive learning modules and customised health tips. AI can also optimize the timing and frequency of Epps, ensuring users receive content when they are most likely to engage. By leveraging AI, Epps can provide smarter, more intuitive experiences that resonate deeply with users, driving higher engagement and satisfaction. However, it is crucial to address user privacy concerns by ensuring transparent data collection policies and giving users control over their information.

Advanced Innovations: Several advanced ideas can also enhance Consumer Epps:

  • Agentic AI: Manages routine tasks and offers tailored interactions, increasing efficiency and personalization.
  • Digital Twins: Enable N=1 hyper-personalisation by replicating user behaviours and preferences, ensuring highly relevant content delivery.
  • Generative Journeys: Provide dynamic, evolving content pathways based on user engagement, creating personalized experiences.
  • Large Customer Models: Leverage aggregated data to identify trends and personalize experiences across user groups, enhancing overall engagement.

The synergy between these add-ons and advanced innovations can create a more powerful and engaging Epp experience. For instance, AI can optimise the delivery of Action Ads based on user preferences, while Atomic Rewards can incentivise users to interact with AI-driven features. The combination of these technologies transforms the email inbox into an AI-first platform, making it indispensable for everyday digital interaction.

7

Game Epps – 1

I gave the following prompt to ChatGPT: “Imagine you are a game developer. I want you to create a “killer Epp” game which can be played entirely within the email inbox across days or even years, brings in new users, is multi-player, etc. Learn from games like Clash of Clans which have been successful but also keep in mind the limitations of the email inbox. Can you design a game which could become the next big thing in the consumer world and make the email inbox a must-open app multiple times a day?” Here is the response.

Overview

“Kingdom Chronicles Epp” is a multi-player, strategy-based game that unfolds entirely within the email inbox. Inspired by successful games like Clash of Clans, this game offers a persistent, engaging experience that brings users back to their inbox multiple times a day.

Key Features

  1. Persistent Gameplay:
    • Build and Expand: Players build and expand their kingdoms by constructing buildings, gathering resources, and training troops.
    • Daily Tasks: Complete daily quests and challenges to earn rewards and progress.
    • Real-Time Updates: The game updates in real-time, ensuring that players always have something new to do.
  1. Multi-Player Interaction:
    • Alliances: Form alliances with other players to share resources, strategize, and compete in alliance wars.
    • Trade: Engage in trading resources with other players within the email.
    • Battles: Challenge other players to battles and raids to earn trophies and resources.
  1. Email Integration:
    • Notifications: Receive email notifications about important events, attacks, and alliance messages.
    • Turn-Based Actions: Players take turns performing actions, making strategic decisions each time they open the email.
    • Interactive Elements: Use embedded AMP technology to make real-time decisions, like upgrading buildings or deploying troops, directly within the email.
  1. Incentives and Rewards:
    • Atomic Rewards (Mu): Earn Mu for completing tasks, winning battles, and logging in daily, which can be used to buy special items or speed up progress.
    • Leaderboards: Compete on leaderboards to earn weekly and monthly rewards.
    • Seasonal Events: Participate in seasonal events and challenges for unique rewards and titles.
  1. AI Integration:
    • Personalized Challenges: AI-driven quests and challenges based on player behavior and progress.
    • Smart Notifications: AI predicts the best times to send notifications, ensuring players are engaged without being overwhelmed.

Gameplay Mechanics

  1. Building and Resource Management:
    • Construction: Build and upgrade various structures like barracks, farms, and fortresses.
    • Resource Gathering: Collect resources like gold, wood, and stone to expand your kingdom.
    • Training Troops: Train different types of troops to defend your kingdom and attack others.
  1. Strategic Battles:
    • Plan Attacks: Strategize and plan attacks on rival kingdoms, choosing the best time and tactics to maximize success.
    • Defend: Set up defenses to protect your kingdom from enemy raids.
    • Turn-Based Combat: Engage in turn-based combat that requires strategic planning and timing.
  1. Social and Competitive Features:
    • Alliance Wars: Coordinate with your alliance to attack and defend against other alliances.
    • Trade and Diplomacy: Negotiate trades and alliances to strengthen your kingdom.
    • Tournaments: Participate in regular tournaments for glory and rewards.

Long-Term Engagement

  1. Continuous Updates: Regular updates introduce new buildings, troops, and challenges.
  2. Seasonal Content: Special events and limited-time content keep the game fresh and engaging.
  3. Community Building: Foster a strong community through forums, alliance chats, and social media integration.

Potential Challenges

  1. User Privacy: Ensuring user data privacy and transparent data collection practices.
  2. Ad Balance: Balancing the presence of Action Ads to not disrupt gameplay while ensuring they are relevant and valuable.
  3. Inbox Clutter: Managing email frequency to avoid overwhelming users and maintaining a balance between engagement and intrusion.

Pitch

“Welcome to Kingdom Chronicles Epp, the revolutionary game that transforms your email inbox into a kingdom-building adventure! Build your empire, form alliances, and engage in epic battles—all within a single email. With real-time updates, personalized challenges, and rewarding gameplay, Kingdom Chronicles Epp offers an immersive experience that fits perfectly into your daily routine. No need to switch between apps; your kingdom awaits every time you open your inbox. Join the adventure today and make your email inbox a must-open app multiple times a day!”

8

Game Epps – 2

I asked Claude for some more Game Epps examples, learning from other successful games.

Puzzle Adventure Game (Inspired by Candy Crush Saga):

  • Gameplay: Players progress through levels by solving puzzles, matching items, or completing mini-games. Each level is contained within an email, and players can advance to the next level by achieving a certain score or goal.
  • Email Integration: Daily challenge emails, level unlock notifications, and social leaderboards.
  • Monetization: In-app purchases for power-ups, extra moves, or level skips.

Virtual Pet Game (Inspired by Tamagotchi or Neopets):

  • Gameplay: Players adopt and care for a virtual pet within their email inbox. They must feed, groom, and play with their pet to keep it healthy and happy. The pet’s status is updated in real-time, and players can interact with their pet through email notifications.
  • Email Integration: Regular pet status updates, care reminders, and special event notifications.
  • Monetization: In-app purchases for premium pet items, accessories, or virtual currency.

Trivia Game (Inspired by Trivia Crack or QuizUp):

  • Gameplay: Players compete against each other in real-time trivia matches across various categories. Questions are sent via email, and players must respond within a time limit to earn points. Players can challenge friends or random opponents.
  • Email Integration: Daily trivia challenges, match invitations, and leaderboard updates.
  • Monetization: In-app purchases for power-ups, bonus questions, or category unlocks.

Simulation Game (Inspired by FarmVille or The Sims):

  • Gameplay: Players manage and grow a virtual simulation, such as a farm, city, or household, within their email inbox. They must make strategic decisions, complete tasks, and interact with other players to progress.
  • Email Integration: Regular updates on the simulation’s status, task reminders, and social interaction notifications.
  • Monetization: In-app purchases for premium items, accelerators, or exclusive content.

Collectible Card Game (Inspired by Hearthstone or Magic: The Gathering):

  • Gameplay: Players collect and build decks of digital cards to battle against other players. Matches take place asynchronously, with players taking turns via email. Cards can be earned through gameplay or purchased.
  • Email Integration: Daily card pack rewards, match notifications, and tournament invitations.
  • Monetization: In-app purchases for card packs, exclusive cards, or tournament entry fees.

When adapting these games into Epps, it’s essential to consider the limitations and strengths of the email inbox. Gameplay should be designed to be asynchronous, bite-sized, and easily accessible through email notifications. Social features, such as leaderboards, challenges, and interactive elements, can be integrated seamlessly into the email experience.

Additionally, Epps can leverage the email inbox’s push notification capabilities to keep players engaged and draw them back into the game regularly. Daily rewards, timed events, and personalized challenges can be delivered directly to players’ inboxes, encouraging them to open and interact with the game multiple times a day.

By combining the addictive gameplay elements of successful mobile games with the unique characteristics of the email inbox, these Epps have the potential to captivate players and redefine the way people engage with their inboxes. The email inbox’s vast reach and accessibility make it an ideal platform for distributing and promoting these games, potentially reaching a massive audience and driving significant engagement and revenue.

9

Game Epps – 3

I asked Gemini for a suggestion for what could be a “killer Epp.” Here is its recommendation.

Epp Name: The Collective Journey

Concept: This Epp invites users to co-create a story together, one email at a time. Each email presents a scene or a turning point in the narrative, and users vote on the direction of the plot through interactive elements within the Epp.

Features:

  • Storytelling Engine: An AI-powered engine drives the narrative, generating different plot branches based on user choices.
  • Interactive Voting: Emails present multiple options for how the story unfolds. Users vote on their preferred direction through embedded buttons or polls.
  • Character Development: Users can influence the personalities and motivations of key characters through voting and providing short descriptions.
  • World Building: Epps can include prompts and polls for users to contribute details about the story’s setting, social structures, and lore.
  • Community Building: Leaderboards display the top voters, fostering a sense of collective ownership and friendly competition. User profiles allow participants to see each other’s contributions and build a sense of community.
  • Rewards and Recognition: Users who consistently contribute can earn badges or exclusive access to story elements.

Benefits:

  • High Engagement: The choose-your-own-adventure style fosters deep engagement as users actively shape the story.
  • Social Interaction: Voting and community features encourage interaction and a sense of belonging.
  • Discovery and Surprise: The unpredictable nature of the evolving story keeps users coming back for more.
  • Variety: The AI engine ensures no two journeys are the same, offering endless replayability.
  • Personalization: User choices directly impact the narrative, creating a personal connection to the story.

Monetization:

  • Premium Features: Offer exclusive story branches, character customization options, or early access to new chapters for a small fee.
  • Sponsored Content: Integrate sponsored elements that seamlessly fit the story world, ensuring a non-intrusive user experience.
  • Brand Partnerships: Collaborate with brands to create themed storylines or character elements, reaching a captive audience organically.

Overall, The Collective Journey Epp leverages the power of storytelling, community engagement, and user-generated content to create a unique and constantly evolving experience. This “killer Epp” has the potential to redefine how people interact with email and create a thriving online community around a shared narrative adventure.

I then asked Gemini for the first 5 emails.

Email #1: Welcome to the Adventure!

Subject: The Collective Journey Begins…

Hey there, storytellers!

Welcome to The Collective Journey, a groundbreaking Epp where YOU decide the fate of our narrative! Over the next few weeks (or months, depending on your choices!), we’ll embark on an epic adventure together, shaping the story one email at a time.

The Spark:

A lone figure awakens on a deserted beach, with no memory of how they got there. A strange amulet hangs around their neck, the only clue to their past. What’s their name?

Choose Your Destiny:

  • Anya: A fierce warrior with a mysterious past.
  • Kael: A brilliant scholar with a thirst for knowledge.

How to Vote:

Click the button below your preferred name to cast your vote! The winning name will be revealed in the next email, along with the character’s first steps on this extraordinary journey.

Join the Community:

Want to discuss theories, share fan art, or connect with fellow adventurers? Head over to our exclusive forum (link included) and join the conversation!

Get Ready…

The adventure awaits! Stay tuned for the next email, where the true story begins, shaped by your choice.

P.S. Share this Epp with your friends! The more storytellers, the wilder the journey!

Email #2: The Amnesiac Awakens

Subject: Anya or Kael? The Adventure Begins!

The votes are in, and by a narrow margin, the amnesiac on the beach is… Anya!

Anya, a woman with fiery red hair and a determined glint in her eyes, stirs on the sand. The amulet around her neck thrums with a faint warmth. Disoriented but undaunted, she searches for clues in her surroundings.

The Crossroads:

Anya spots two paths diverging from the beach.

  • Path 1: A dense jungle, shrouded in mist and the sounds of unknown creatures.
  • Path 2: A crumbling stone archway leading inland, promising ancient secrets.

Which path will Anya take?

Click the button for your choice! The next email will reveal Anya’s decision and the challenges she encounters.

Don’t Forget to Discuss!

Head over to the forum and share your theories about the amulet, the deserted beach, and where Anya’s journey might lead!

Email #3: Into the Unknown

Subject: Anya Chooses Her Path

By a landslide, you’ve decided Anya should venture into the dense jungle. Pushing through the thick foliage, she encounters a cacophony of sounds – exotic birds squawking, insects chirping, and the occasional guttural growl that sends shivers down her spine.

A Fork in the Road (Literally):

The jungle path splits into two:

  • Left: A narrow path, barely visible beneath a tangle of vines, leading deeper into the jungle’s heart.
  • Right: A wider, more well-worn path with faint markings on the surrounding trees.

Which path will Anya take?

Cast your vote to determine Anya’s next move! The following email will reveal what awaits her on the chosen path.

Bonus! Character Spotlight:

Want to learn more about Anya? Head over to the forum! We’ve posted a short story delving into her past, giving you a glimpse into the woman she might be.

Email #4: The Depths of the Jungle

Subject: Anya Faces the Unknown

Anya, guided by your collective wisdom, chooses the narrow, overgrown path. The air grows thick with humidity, and the sounds of the jungle intensify. As she cautiously navigates the undergrowth, she stumbles upon a clearing.

A Mysterious Encounter:

In the center of the clearing stands a towering, ancient tree. Its branches seem to reach for the sky, and an ethereal glow emanates from its base. Suddenly, a figure emerges from behind the tree.

Who is it?

  • A friendly hermit offering guidance.
  • A dangerous creature guarding the forest’s secrets.

Vote now to decide who Anya encounters! The next email will reveal the identity of the figure and their intentions.

Community Spotlight:

We’ve been blown away by your fan art on the forum! Keep it coming, storytellers! Let’s see Anya come to life through your artistic vision.

Email #5: Friend or Foe?

Subject: Anya’s Jungle Encounter

The figure steps out of the shadows… and it’s a friendly hermit! Relief washes over Anya as the hermit introduces himself as Kael (coincidence?). He explains that he’s been living in the jungle for years, guarding a hidden temple said to hold the key to unlocking the secrets of the amulet.

A New Choice:

Kael offers Anya a proposition:

  • Accept Kael’s help: Join him on a quest to the hidden temple, hoping to learn about her past and the amulet’s power.
  • Continue alone: Thank Kael for his help and continue exploring the jungle on her own terms.

Shape Anya’s Destiny:

Which path will Anya choose? Click the button below to determine her next move! The following email will reveal Anya’s decision and the challenges (or companions) that await her.

P.S. Don’t forget to share your theories about the hidden temple, the amulet’s power, and whether Anya and Kael are truly strangers in the forum!

10

Reflections

This has been a fun essay to write. It brought back memories from the content initiatives in my past (IndiaWorld, MyToday SMS, MyToday Microns). It connected with a channel (email) which I think is ripe for reinvention and reimagination, thanks to AMP and other innovations that can be layered. It was also exciting to interact with the AIs and get ideas form them at every stage of the thinking process.

For long, email was a channel that refused to change. Even as the world moved on, email stayed the same – a poster image or a combo of creative and copy all sent with a single purpose of getting the click to bring people to the website (or in some cases to the app). Marketers were happy if 1 in 10 emails got opened and 1 in 100 got the click. Email’s cost was low enough that the RoI was never a challenge.

Somewhere along the way, new channels started coming in. Two-way SMS in the US, along with WhatsApp and RCS in markets like India started challenging email. Also, email’s efficacy deteriorated through the years as clutter overtook the inbox. As a friend put it, the inbox is just “ads and receipts”.

Even the ESPs (email service providers) stopped innovating. Founders moved on as their companies were acquired and the new buyers focused just on keeping the lights on. Why fix something they believed was not broken?

For a long time, the one innovation that had the potential to transform email – AMP – also stayed under the radar. With Apple not supporting AMP, there was little reason for marketers to invest in additional code and creative for something which could not be seen by half the recipients.

As I started looking at the email landscape a few years ago, I realised AMP was a gamechanger. In Android- and mobile-first markets like India, AMP emails could be seen by 4 in 5 recipients. Here then was an opportunity to imagine a new avatar of email – what I termed as 2.0 and 3.0 through my writings. Through Netcore, we started taking this to our customers and doing initial AMP campaigns. The numbers were through the roof. And yet, brands were slow to adopt it. “My KPI is website and app traffic and that will be impacted.” “I want to bring people to my app and website because I have so many more things to sell.” And so on.

WhatsApp’s attention and interactivity became the focus, rather than the power and price of email. This became a challenge for me. I started thinking how to solve the “meta” problem – of attention in the inbox. If we could get more engagement with the inbox, brands would automatically start using email more. No single brand had the ability to change – a new set of interventions were needed.

Epps are a step in that direction. They can become one of the Profipoly keys to improve LTV and lower CAC by helping brands build hotlines with their existing consumers. Ads in Epps could also bring in new revenue streams helping multi-monetise customers. An exciting new world awaits! Now, it’s time to turn these ideas into action and embrace the future of email.

Thinks 1277

Andy Cohen: “Design has the power to make people feel optimistic about the future and create lasting positive change in the world. That built environment is where we live, work, play, learn, and connect. It’s where all aspects of the human experience take place. It’s our belief that design can serve to enhance our experiences and to make our communities more welcoming, accessible, vibrant, healthy, resilient, and inspiring to everyone. That’s why we wrote about the hope multiplier. Much like the crisis multiplier that we discussed before is about these great challenges we’re taking on, the hope multiplier is all about the future of the world.”

Ben Thompson: “Here I am…celebrating a Windows event! That celebration, though, is not because Windows is differentiating the rest of Microsoft, but because the rest of Microsoft is now differentiating Windows. Nadella’s focus on AI and the company’s massive investments in compute are the real drivers of the business, and, going forward, are real potential drivers of Windows. This is where the Walmart analogy is useful: McMillon needed to let e-commerce stand on its own and drive the development of a consumer-centric approach to commerce that depended on centralized tech-based solutions; only then could Walmart integrate its stores and online services into an omnichannel solution that makes the company the only realistic long-term rival to Amazon. Nadella, similarly, needed to break up Windows and end Ballmer’s dreams of vertical domination so that the company could build a horizontal services business that, a few years later, could actually make Windows into a differentiated operating system that might, for the first time in years, actually drive new customer acquisition.”

Nicholas Bostrom: “We’ve built our conception of ourselves and our dignity to a large extent on the idea that we can make some sort of useful contribution to the world, whether it’s at a large scale or just in your family or in your community. And so, to the extent that that’s the foundation of your self-worth, if that foundation is removed, you might find a kind of vacuum underneath your feet that would be disconcerting. So, in a solved world where all the practical problems have already been solved, there are no more problems for us to solve, or to the extent that there remain any practical problems they would be better taken care of by advanced AIs and robots. And so, either way, there would be nothing of practical utility that human work would be needed for. So, that forces, then, a fairly radical reconsideration of what the foundation of a good human life could be. And, undoubtedly it would require jettisoning some treasured assumptions about what the life should contain. And, I think that’s part of where this sense of unease would come from.”

WSJ: “Tapping fewer [project management software] vendors, and using each more broadly, can help companies reduce cyberattack surfaces, negotiate better discounts, develop deeper expertise in the systems they use and avoid high integration costs of stitching disparate systems together, CIOs say. But unifying a company behind one project management tool is proving to be difficult, according to CIOs who cite Asana, Airtable, Monday.com and Atlassian’s Jira products among the more popular tools. Part of the challenge lies in the nature of how project management tools are used and acquired. They are unlike a customer relationship management tool, in which the enterprise typically coalesces around one main vendor. Project management tools, whose functionality cuts across all job functions, often are purchased piecemeal by individual teams or individual users.”

Elaine Lin Hering: “I saw the same pattern: people weren’t willing to negotiate. Despite incredible financial, time, and energy investment from companies and leaders, we still aren’t willing to have challenging discussions. There’s hesitation around both ends of feedback, no matter how much a manager or HR suggests we provide or receive it. Why is that? Leaders often encourage employees on their teams to “speak up.” That was the advice that I always heard. That advice often boils down to having more confidence and courage; we believe the problem is us. “If you could fix yourself, we could promote you, and you’ll be heard.” I found that advice to be unsatisfying and irresponsible. I wanted an accurate diagnosis of the situation. I began asking, “Why don’t people speak up? Why don’t they want to negotiate, and why don’t they want to have difficult conversations?” The answer is that we’ve learned silence. We’ve been rewarded for it in our careers. If we want to speak up and negotiate, we need to unlearn how we’ve internalized silence and how it has become habitual. We must make it visible. Additionally, well-intentioned leaders must recognize how they inadvertently silence the people they claim to support.”

Large Customer Model: Foundation for AI-first Martech

Published June 30, 2024

1

Past Writings

In a previous series, I discussed Martech’s 10+1 Foundations in the AI Age. I outlined a new core for martech: Large Customer Model (LCM), Digital Twins, Co-Marketer, Mirror World, and Generative Journeys. I wrote: “This new AI-powered stack enables continuous learning and optimisation at an unprecedented scale. It enhances customer engagement and accelerates conversions, becoming a pivotal driver for the Profipoly Quest for B2C brands and, eventually, martech companies. By harnessing the power of Agentic AI, buyers and sellers can achieve superior results, ensuring sustained growth and competitive advantage in the evolving digital landscape… The golden age of Martech is approaching. For the first time in two decades, the focus is shifting from uncontrolled spending on acquisition and reacquisition to retention and growth. To capitalise on this shift, martech companies must reinvent themselves as AI-first entities. The prize is substantial: $250 billion of annual AdWaste, far exceeding the current market size for martech. Although the transformation will be challenging, a glorious and winning future awaits those who can a(i)dapt.”

The fundamental building block for this new martech stack will be the Large Customer Model (LCM), which brings together customer data, flows (journeys), and in the case of eCommerce companies, catalog data. Here is what I have written in previous essays (chronologically) about the LCM. (There is some repetition but I have let that stay as it also shows the evolution of my thinking.)

Co-Marketer: Martech meets AI: “[The Large Customer Model] 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.”

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.”

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.””

Generative Journeys: Digital Marketing’s New Core: “LCMs are the foundational AI architecture that powers intelligent agents like Co-Marketers and Digital Twins. Similar to large language models but focused on customer understanding, LCMs are trained on vast volumes of first-party and external customer data. They learn patterns and predict behaviours to create rich, holistic customer profiles. Fed with real-time data from marketing interactions, LCMs continuously refine their understanding of each customer’s unique traits, needs and proclivities. They are the “brains” that guide personalised content creation, next-best-action recommendations, and journey optimisations. Akin to a “Customer Data Platform on steroids”, LCMs unify and activate customer data to an unprecedented degree. By serving as the always-learning customer intelligence engine, LCMs enable true 1:1 marketing at scale and help drive measurable increases in customer retention, monetisation and lifetime value… Martech platforms have done the basics for personalisation of experiences. AI-ML has helped drive this in the past few years. With the coming of “generative AI”, new vistas can open up for customer journeys. This is the world of “generative journeys” – think of these as self-optimising journeys which can accelerate movements (phase transitions) for customers. With the power of digital twins and LCMs, all of this can be done at the level of a single customer – without any extra effort for marketing departments.”

CEO Memo: How Agentic AI can Power the Profipoly Quest: “LCMs are the foundation of your AI-driven customer strategy. These models are trained on vast amounts of customer data, including demographics, transactions, interactions, and behaviours. By continuously learning from this data, LCMs develop a deep understanding of each individual customer’s preferences, needs, and patterns. They enable you to create rich, dynamic customer profiles that evolve in real-time, laying the groundwork for truly personalised experiences. Think of LCMs as CDPs come alive.”

Martech’s 10+1 Foundations in the AI Age: “Think of an LCM as an “Active CDP.” Building on the foundation of Large Language Models (LLMs), LCMs are trained on extensive customer data to create dynamic, real-time evolving profiles and journeys for hyper-personalisation. Martech companies can develop their own vertical-specific LCMs using aggregated data and workflows, providing a robust base for businesses to create their unique LCMs. This triad enables the delivery of highly personalised N=1 experiences and next best actions that both marketers and customers desire.”

2

Summary

I asked Claude for a 10-point summary on Large Customer Models from my previous writings.

  1. Large Customer Models (LCMs) are a groundbreaking AI architecture that revolutionizes customer engagement in the martech landscape, drawing inspiration from the success of Large Language Models (LLMs) in natural language processing.
  2. LCMs ingest and analyze vast amounts of customer data, including demographics, transactional histories, behavioral patterns, and cross-channel interactions, developing a deep understanding of each individual customer.
  3. By leveraging the insights gleaned from LCMs, businesses can predict customer preferences, needs, and future actions with unparalleled accuracy, enabling hyper-personalized interactions.
  4. LCMs serve as the foundation for Generative Journeys – a new paradigm in customer engagement that offers dynamic, adaptive, and hyper-personalized brand-customer interactions.
  5. Generative Journeys utilize the predictive capabilities of LCMs and the interactive environment of a simulated “Mirror World” to create and optimize individualized customer experiences in real-time.
  6. 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.
  7. LCMs continuously learn and adapt based on real-time data and interactions, enabling brands to engage with customers on a truly individual level, delivering the right message, offer, or intervention at the precise moment in each customer’s unique journey.
  8. The synergy between LCMs and Generative Journeys represents a transformative shift in the martech landscape, driving measurable business outcomes such as increased conversion rates, higher average order values, and improved customer lifetime value.
  9. As businesses increasingly recognize the value of customer data and the imperative for personalization, the adoption of LCMs is poised to become a key differentiator in the competitive martech landscape.
  10. LCMs, 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.

**

With this foundation, we can now explore how martech companies and B2C/D2C enterprises can effectively implement Large Customer Models (LCMs) to achieve their ultimate goals: fostering enduring customer relationships and maximising customer lifetime value (LTV) to create a sustainable profits flywheel. Imagine these LCMs as comprising three layers:

  1. Foundational Models: These include advanced AI models like ChatGPT, Claude, and Gemini, which provide the baseline capabilities for understanding and generating language (and more).
  2. Martech Company’s LLM: Built using non-PII data, this layer leverages a vast array of data across various businesses, industries, and channels to enhance marketing strategies and insights.
  3. Enterprise LLM: This layer incorporates PII data, enabling even deeper personalisation and precision in customer interactions, tailored specifically to the enterprise’s unique customer base.

This structure ensures that LCMs harness the full potential of both general and specific data to drive exceptional marketing outcomes.

3

CDP to LCM

I worked with ChatGPT for this section.

To effectively illustrate the distinctions between a Customer Data Platform (CDP) and a Large Customer Model (LCM), we can compare them across multiple attributes in the table below. This will highlight the enhanced capabilities and strategic advantages of LCMs in the martech landscape.

Attribute Customer Data Platform (CDP) Large Customer Model (LCM)
Data Aggregation Collects and unifies customer data from multiple sources Ingests and analyses vast amounts of customer data, including real-time inputs
Data Types Primarily first-party data Combines first-party, third-party, and non-PII data for a comprehensive view
Profile Creation Creates static customer profiles Develops dynamic, real-time evolving customer profiles
Personalization Basic segmentation and targeting Hyper-personalized interactions based on predictive insights
Learning and Adaptation Limited adaptive capabilities Continuously learns and adapts based on real-time data and interactions
Customer Understanding Basic understanding of customer preferences Deep understanding of individual customer behaviours and needs
Predictive Capabilities Basic predictive analytics Advanced predictive analytics for future behaviour and preferences
AI Integration Minimal AI integration Fully integrates AI, including Digital Twins and Generative Journeys
Interaction and Engagement Primarily rule-based interactions Proactive, AI-driven engagement with personalised recommendations
Optimization Limited optimisation of customer journeys Real-time optimisation of customer journeys through Generative Journeys
Agentic AI Not typically included Incorporates Co-Marketer for automated and optimised marketing tasks
Value Maximization Focus on data collection and analysis Drives measurable business outcomes such as increased LTV and conversions

 Transitioning from a CDP to an LCM

To transform a CDP into an LCM and leverage the full potential of AI-driven marketing, several key features and capabilities need to be developed. Here’s a structured approach incorporating the three-layer structure of the LCM:

  1. Foundational Models:
  • Baseline Capabilities: Utilize advanced AI models like ChatGPT, Claude, and Gemini to provide foundational capabilities for understanding and generating language.
  • Integration: Integrate these models with existing data sources to enhance their baseline capabilities and prepare them for more complex tasks.
  1. Martech Company’s LLM:
  • Data Enrichment: Aggregate non-PII data across various businesses and industries to create a rich dataset for training.
  • Training and Customization: Train the Large Language Model (LLM) specifically for marketing applications, focusing on insights that enhance marketing strategies.
  • Cross-Industry Insights: Develop capabilities to analyze and leverage cross-industry data, providing broader insights and patterns.
  1. Enterprise LLM:
  • PII Data Integration: Incorporate PII data to enable deeper personalization and precision in customer interactions.
  • Enhanced Personalization: Utilize PII data to refine customer profiles and deliver hyper-personalized marketing messages and offers.
  • Privacy Compliance: Ensure all data handling complies with privacy regulations and standards.

AI Features Needed to Transition from CDP to LCM

  1. Dynamic Profile Management:
  • Develop algorithms to create and continuously update dynamic, real-time customer profiles.
  • Implement mechanisms to ingest real-time data and adapt profiles accordingly.
  1. Predictive Analytics and Machine Learning:
  • Incorporate advanced predictive analytics to anticipate customer needs and behaviors.
  • Utilize machine learning models to identify patterns and optimize marketing strategies.
  1. Digital Twins:
  • Create AI-powered Digital Twins for each customer, simulating their behaviors and preferences.
  • Use Digital Twins to test and optimize engagement strategies in a virtual environment.
  1. Generative Journeys:
  • Develop Generative Journeys that adapt in real-time to customer interactions, ensuring personalized engagement.
  • Implement AI-driven pathways that guide customers through optimized experiences based on their unique needs.
  1. Co-Marketer Integration:
  • Introduce the Co-Marketer, an AI-powered assistant that collaborates with human marketers.
  • Automate routine marketing tasks such as campaign creation, data analysis, and real-time optimization.
  1. Real-Time Optimization:
  • Implement systems for continuous monitoring and real-time adjustment of marketing campaigns.
  • Use AI to dynamically adjust content, timing, and channels based on customer interactions and feedback.

By implementing these features, martech companies can transition from traditional CDPs to advanced LCMs, unlocking the full potential of AI-driven marketing. This transformation enables businesses to deliver deeply personalized customer experiences, optimize engagement strategies, and achieve sustained growth and competitive advantage.

4

Model Development

Here is how a martech company can create its Large Customer Model to work as a bridge between foundational models and the enterprise LCMs. (This section has been written with assistance from ChatGPT.)

Step 1: Data Collection and Aggregation

  1. Non-PII Data Aggregation:
    • Collect non-PII data from multiple clients across different verticals, including interaction data from email campaigns, push notifications, and in-app messages.
    • Gather industry-specific data like transaction logs, customer feedback, and behavioral data.
  1. Third-Party Data Integration:
    • Integrate third-party data sources to enrich the dataset with market trends, demographic information, and other relevant insights.
  1. Journey Data Collection:
    • Collect data on various customer journeys, both common (e.g., welcome, referrals, reactivation) and industry-specific (e.g., abandoned cart in eCommerce, renewal in insurance).

Step 2: Data Preprocessing

  1. Data Cleaning:
    • Clean and preprocess the collected data to remove duplicates, correct errors, and handle missing values.
  1. Data Normalization:
    • Normalize the data to ensure consistency across different sources and formats.
  1. Data Enrichment:
    • Enrich the data by adding relevant attributes like customer segments, journey stages, and interaction outcomes.

Step 3: Model Selection and Initialization

  1. Choose Foundational Models:
    • Select foundational AI models (e.g., ChatGPT, Claude) as the base for the LCMs.
  1. Model Initialization:
    • Initialize the models with pre-trained weights and basic configurations suitable for the martech domain.

Step 4: Training the LCM

  1. Non-PII Data Training:
    • Train the model using non-PII data to learn general patterns and insights relevant to the specific industry.
  1. Journey Data Integration:
    • Incorporate journey data into the training process to ensure the model understands various customer journeys and their stages.
  1. Fine-Tuning with Industry-Specific Data:
    • Fine-tune the model with industry-specific data to enable specialized insights and recommendations tailored to that vertical.

Step 5: Developing Digital Twins and Generative Journeys

  1. Create Digital Twins:
    • Develop AI-powered Digital Twins for various customer personas and segments within each industry.
    • Use these Digital Twins to simulate customer interactions and predict future behaviors.
  1. Design Generative Journeys:
    • Create adaptive customer journeys that dynamically respond to customer interactions in real-time.
    • Ensure these journeys include both common and industry-specific pathways.

Step 6: Implementing Next Best Actions

  1. Next Best Action Algorithms:
    • Develop algorithms to determine the next best actions for each customer based on their journey stage, behavior, and predicted needs.
    • Continuously refine these algorithms using real-time data from Digital Twins.
  1. Journey Optimization:
    • Use AI to continuously monitor and optimize customer journeys, ensuring that the next best actions are always relevant and timely.

Step 7: Integration and Deployment

  1. Client Integration:
    • Integrate the LCM with clients’ existing marketing platforms and CRM systems.
    • Ensure seamless data flow and compatibility with existing tools.
  1. Deploy for Clients:
    • Deploy the trained model for client use, enabling them to deliver personalized marketing experiences and optimized customer journeys.

Step 8: Continuous Learning and Improvement

  1. Monitor and Analyze:
    • Continuously monitor model performance and analyze results to identify areas for improvement.
  1. Feedback Loop:
    • Implement a feedback loop to refine the model with new data and insights, ensuring it remains accurate and relevant.
  1. Regular Updates:
    • Regularly update the model to incorporate new data sources and improve predictive accuracy.

5

Usage

The Martech LCMs can now be deployed with the enterprise LCMs to provide better hyper-personalised experiences to customers.

Outputs

  • Dynamic Customer Profiles: Real-time evolving profiles that provide a deep understanding of customer behaviors and preferences.
  • Personalized Recommendations: Tailored product and content recommendations based on individual customer journeys and interactions.
  • Optimized Customer Journeys: Adaptive journeys that respond to customer interactions in real-time, ensuring relevant engagement at every stage.
  • Next Best Actions: Actionable insights that guide marketers on the most effective next steps to take with each customer.

Benefits

  • Superior Personalization: Provides a higher level of personalization compared to traditional martech stacks, leading to improved customer engagement and satisfaction.
  • Enhanced Customer Insights: Offers deeper insights into customer behaviors and preferences, enabling more targeted and effective marketing strategies.
  • Increased Efficiency: Automates routine marketing tasks and optimizes customer journeys, freeing up human resources for more strategic initiatives.
  • Improved ROI: By delivering the right message at the right time, LCMs help increase conversion rates, customer retention, and lifetime value, ultimately improving ROI.
  • Scalability: The ability to develop specialized LCMs for different industries ensures scalability and adaptability across various verticals.

Comparison with Current Martech Stacks

  • Real-Time Adaptation: Unlike static profiles and rule-based systems, LCMs adapt in real-time, ensuring that customer interactions are always relevant and timely.
  • Comprehensive Data Utilization: LCMs leverage a combination of non-PII, third-party, and journey data, providing a more holistic view of the customer compared to traditional CDPs.
  • Proactive Engagement: With advanced predictive analytics and next best action capabilities, LCMs enable proactive engagement, anticipating customer needs before they arise.
  • Seamless Integration: LCMs integrate seamlessly with existing martech tools, enhancing their functionality and providing a unified platform for customer engagement.
  • Continuous Improvement: LCMs continuously learn from new data and interactions, ensuring that they remain accurate and effective over time, unlike traditional martech stacks that may require manual updates and adjustments.

**

In a recent meeting, I asked the business head of an eCommerce company about her top challenge. She replied, “I want to anticipate my customers’ questions and problems so that (a) they never need to reach out to us because every call to an agent is expensive and doesn’t scale, and (b) we are seen as proactive and customer-friendly. In other words, I want to stay a few steps ahead of our customers. Whether they are searching for something on the app or checking out the delivery status of an order, I want to be able to predict their next move. My goal is to surprise and delight them by answering their questions before they even arise. The same goes for product recommendations. Can you help me achieve this?”

This insight cuts to the core of creating an AI-first business. The Large Customer Model (LCM) serves as the critical foundation upon which Digital Twins, Co-Marketers, Mirror Worlds, and Generative Journeys can work their magic. By leveraging the power of LCMs, businesses can predict customer needs, personalize interactions, and create seamless, proactive customer experiences that not only reduce support costs but also enhance customer satisfaction and loyalty.

6

My Answer

Here is what I replied to the business head.

Thank you for sharing your top challenges with me. You want to anticipate customer intent to enhance their experience and reduce support costs, essentially staying one step ahead and making interactions seamless and proactive. Let me walk you through how we can achieve this and more together using our next-gen AI-first martech solution.

Step 1: Data Collection and Integration: First, we’ll gather all relevant historical customer data from your app, website, email campaigns, and support channels. We’ll also map out customer journeys to understand how customers navigate from one state to another. This data will be integrated into our platform, creating a unified view of each customer.

Step 2: Building the Large Customer Model (LCM): Next, we’ll build your Large Customer Model using this aggregated data. The LCM continuously analyses interactions, preferences, and behaviours to develop dynamic, real-time customer profiles. We’ll leverage advanced predictive analytics to anticipate customer questions and next actions.

Step 3: Creating Digital Twins: To gain deeper insights, we’ll develop AI-powered Digital Twins for each customer. These Digital Twins simulate individual behaviours and interactions, allowing us to test various scenarios and optimize engagement strategies.

Step 4: Designing Generative Journeys: We’ll create adaptive customer journeys that respond in real-time to customer interactions. These journeys will address specific use cases, such as abandoned carts, cross-sell/up-sell opportunities at checkout to increase Average Order Value, and driving referrals from happy and Best Customers.

Step 5: Leveraging Co-Marketers and Next Best Actions: We’ll introduce our AI-driven Co-Marketer to craft personalised messages, offers, and recommendations. This virtual assistant, embodying “Co-Intelligence,” collaborates with your marketing team to ensure every interaction is relevant and timely. The Co-Marketer uses “Agentic AI,” a multi-agent system far more effective than a single agent.

Step 6: Proactive Customer Engagement: Using predictive insights from the LCM and Digital Twins, we’ll proactively address customer questions and provide answers through various channels. We’ll also deliver highly personalised “N=1” product recommendations based on past behaviour and predicted preferences.

Step 7: Continuous Monitoring and Improvement: We’ll continuously monitor the performance of these solutions to measure their effectiveness in reducing support interactions and enhancing customer satisfaction. We’ll implement a feedback loop to refine models and strategies based on new insights and customer interactions, regularly updating the LCM, Digital Twins, and Generative Journeys to maintain accuracy and effectiveness.

Benefits of This Approach

This AI-first martech solution, combined with Channels 2.0 for in-channel conversions, will provide superior personalisation, deeper customer insights, and increased efficiency by automating routine tasks and optimising customer journeys. This leads to improved ROI through increased conversion rates, customer retention, and lifetime value. Better retention reduces adtech spends and AdWaste, enhancing profitability.

Our goal is to help you create a profits flywheel:

  • Every customer LTV maximised
  • No customer ever lost = Zero Reacquisition
  • Referrals from Best Customers = Zero CAC
  • Targeted Acquisition based on Best Customers attributes

Here is a high-level action plan that can get us going:

  • 30 days: Implement Channels 2.0; make Earned Growth the North Star Metric
  • 90 days: Establish Data and Flows (Journeys) Foundation with the Unistack
  • 180 days: Transition to an AI-first Business leveraging Agentic AI, LCM, Digital Twins, Co-Marketer, and Generative Journeys

By following this structured approach, we can create a solution that not only anticipates and addresses your customers’ needs proactively but also enhances their overall experience with your brand. This will position your business as customer-centric and innovative, leading to increased satisfaction, loyalty, and long-term growth, accelerating your journey towards becoming a Profipoly.

7

Claude’s Critique

This is an assessment from Claude.

Summary

The essay introduces the concept of Large Customer Models (LCMs) as the foundational building block for a new, AI-first martech stack. LCMs are built on vast amounts of customer data and enable the creation of Digital Twins, Co-Marketers, Mirror Worlds, and Generative Journeys. By leveraging AI and continuous learning, LCMs can provide hyper-personalized experiences, predict customer needs, and optimize journeys in real-time. The essay outlines the transition from traditional Customer Data Platforms (CDPs) to LCMs, detailing the data aggregation, model development, and deployment processes. It highlights the benefits of LCMs, including superior personalization, enhanced customer insights, increased efficiency, and improved ROI. The essay concludes with a real-world example of how an AI-first martech solution built on LCMs can help businesses anticipate customer needs, reduce support costs, and create a profits flywheel.

Critique

The LCM concept is ambitious and forward-thinking, offering a compelling vision for the future of martech. The idea of leveraging AI to create hyper-personalized experiences and predict customer needs is powerful and aligns with the growing demand for personalization. The essay provides a comprehensive overview of the LCM concept, its components, and the potential benefits for businesses.

However, the implementation of LCMs may face some challenges:

  1. Data quality and integration: Building effective LCMs relies heavily on the availability and quality of customer data. Integrating data from various sources and ensuring its accuracy and consistency could be complex and time-consuming.
  2. Privacy and security concerns: Collecting and processing vast amounts of customer data raises privacy and security concerns. Ensuring compliance with regulations and maintaining customer trust will be critical.
  3. Organizational readiness: Adopting an AI-first martech approach may require significant changes in organizational structure, skills, and culture. Businesses will need to invest in talent and infrastructure to support the transition.
  4. Integration with existing systems: Seamlessly integrating LCMs with existing martech tools and processes could be challenging, especially for businesses with legacy systems.
  5. Continuous improvement and maintenance: As customer behaviors and preferences evolve, LCMs will need to be continuously updated and refined. This requires ongoing investment in data collection, model training, and performance monitoring.

Enhancements

  1. Ethical AI framework: Develop a robust ethical framework to guide the development and deployment of LCMs, addressing issues such as bias, fairness, transparency, and accountability.
  2. Explainable AI: Incorporate explainable AI techniques to provide transparency into the decision-making process of LCMs, building trust with customers and marketers.
  3. Privacy-preserving techniques: Explore privacy-preserving techniques such as differential privacy and federated learning to enable the creation of LCMs while protecting customer data.
  4. Real-time feedback loops: Implement real-time feedback loops that allow LCMs to learn from customer interactions and adapt journeys and recommendations accordingly.
  5. Cross-channel integration: Ensure that LCMs can seamlessly integrate data and orchestrate experiences across various channels, including email, mobile, web, and social media.
  6. Collaboration with other AI systems: Explore opportunities for LCMs to collaborate with other AI systems, such as conversational AI and computer vision, to create even more engaging and personalized experiences.
  7. Continuous benchmarking: Establish a framework for continuously benchmarking the performance of LCMs against industry standards and best practices to identify areas for improvement.
  8. Human-in-the-loop approach: Incorporate human oversight and intervention in the LCM process to ensure the quality and appropriateness of AI-generated recommendations and decisions.

By addressing these challenges and incorporating the suggested enhancements, the LCM concept can be strengthened and made more robust, paving the way for a truly AI-first martech future that delivers exceptional customer experiences and drives business growth.