Thinks 1746

Economist: “Is the decline of reading making politics dumber? As people read less they think less clearly, scholars fear…There will be other losses from a reading decline. Few engines of social mobility are more effective than reading: just ask the Scottish shepherds. Rich children may do it more, but reading is an egalitarian invention. No one—not your nanny, not your tutor, your friends or your posh school—can impel you to devour a book except you. Reading is not merely a tool: it is also one of life’s great pleasures, as Dickens knew well. As Joe, the kind blacksmith in “Great Expectations”, says: “Give me a good book…and sit me down afore a good fire, and I ask no better.” Once people forget that, things really will feel bleak.”

WSJ: “At its most basic level, much like eBay, livestreaming lets anyone sell. Sellers stream videos on their phone, tablet or computer via apps like Tilt or Whatnot. In real time, they talk viewers through items they’re selling from the intimacy of their bedroom or a high-production set. Shoppers get answers to their questions in a live-chat before bidding on an item in an auction or committing to a purchase. In the more corporate version, big brands like Poshmark, Amazon and eBay itself now all offer livestream shopping, often with “known quantity” hosts.”

Arnold Kling on reading with AI: “Reading a non-fiction book from cover-to-cover is not efficient. I used to say that I read books “from the outside in.” I look at the book flap to find out about the author, who wrote the blurbs, and the subject matter of the book. Then I read the introduction and conclusion in order to get the main ideas. If I have read something by a different author that seems relevant, I look for that author in the index, and I head to those pages… I start by asking the AI to summarize the key themes of the book. For each theme that the AI lists, I stop and try to put it into my own words. I test my understanding by feeding my words into the AI, in order get confirmation that my interpretation is correct. Another way that I ensure understanding is to suggest possible examples or ask the AI to provide examples.”

Bloomberg: “India’s four-year-old mission to develop a local semiconductor industry is gaining momentum, suggests government data. To date, there are 10 semiconductor projects; $18 billion in investment commitments; subsidies of over $7 allocated; 23 chip design projects sanctioned; a new semiconductor-led technical education curriculum, and over 60,000 students under various training programs.”

“Who Lost My Customers and Killed My Profits?” (Part 1)

A Question

For years, I’ve fought against the $500 billion AdWaste plague—the staggering burn of budgets reacquiring customers brands already knew. In presentation after presentation, I’ve shown how 70% of marketing budgets are wasted on reacquisition—much of it becoming ‘revenue taxes’ paid to Google and Meta for the privilege of finding lost customers. This crusade against AdWaste has become my calling card, the foundation of my thinking about modern marketing’s fundamental dysfunction.

But recently, that foundation was shaken.

I was reading Laura Ries’s provocative new book, The Strategic Enemy, when her central thesis stopped me cold. Ries argues that breakthrough companies don’t succeed by being better—they succeed by defining and defeating a strategic enemy. Uber didn’t just offer better taxis—it declared war on the taxi industry. Tesla didn’t just make electric cars—it declared war on combustion engines. The enemy crystallises the mission, rallies the troops, and clarifies the value proposition.

This made me confront an uncomfortable question: What does Netcore truly stand against?

The obvious answer seemed clear—we fight the Adtechs, those profit-devouring giants who’ve turned customer reacquisition into a trillion-dollar tax on business growth. For years, I’ve positioned them as marketing’s great villain, the strategic enemy that must be defeated.

Then a colleague asked me a question that changed everything.

“What if you’ve got it backwards?”

He continued with surgical precision: “What if Adtechs aren’t the disease but merely the symptom? What if the real story is that Martech platforms—companies like ours—created the very problem we claim to solve? Think about it: brands only pay the Google tax because their marketing technology failed to keep customers engaged. They only need reacquisition because retention didn’t work.”

The implications were staggering. If Martech had delivered on its promise—if it had truly enabled brands to build lasting customer relationships—would the AdWaste problem even exist? When brands ask, “Who lost my customers, moved my profits, and killed my future?” perhaps they shouldn’t point at Mountain View or Menlo Park. Perhaps they should look at their marketing clouds, their customer engagement platforms, their entire Martech stack that promised retention but delivered abandonment.

Every failed retention campaign, every ignored customer, every broken journey creates another profitable transaction for Google and Meta.

Martech hasn’t been fighting Adtech; it’s been feeding it.

This revelation transforms everything. It means the enemy isn’t external—it’s internal. The call isn’t coming from Silicon Valley; it’s coming from inside the house. We haven’t been David fighting Goliath; we’ve been Goliath’s arms dealer.

If this hypothesis is correct—and I believe it is—then NeoMarketing isn’t just the antidote to Adtech. It’s the cure for Martech’s disease. And that single shift changes everything—how we build, how we position, and how we deliver the future of marketing.

Thinks 1745

Mint: “As marketers move beyond impressions, attention emerges as the new metric for effectiveness. Agencies and brands are adapting to a world where visibility is no longer guaranteed—and neither is impact.”

SN Subrahmanyan, chairman & MD, Larsen & Toubro: “Our philosophy is simple: grow to sell or sell to grow. ‘Grow to sell’ means scaling businesses until they’re attractive for monetisation. ‘Sell to grow’ applies when businesses underperform—we exit and reallocate capital. I’ve applied this approach extensively. And when a business isn’t saleable, we wind it down.”

WSJ: “A classic version of the loss leader is high-low pricing: Price a product at a loss and stick it in the back of the store if possible. Costco does this with its other famous loss leader, the $4.99 rotisserie chicken. “Chances are you’re going to pick up other items in the store while you’re going to buy that loss leader, and usually those other items are priced at a higher margin,” said Barbara Kahn, a Wharton School marketing professor…Conventional thinking behind loss leaders centered on high-low pricing. But a 2014 paper from economists Younghwan In and Julian Wright added another wrinkle on how a loss leader might work. Their idea: A company advertises a low-price product to signal that upgraded items in the same category are also a good buy.”

Bloomberg on AI in America’s schools.

Arnold Kling: “My outlook for the future of writing is that it will look more like editing. The AI will do most of the work. A good editor can suggest topics. He can provide general guidance. He can recommend style. When the author submits a draft, the editor can propose revisions. My guess is that in another year or two only a very few students will be able to develop enough skills to write better than an AI. But maybe every student can learn to work with an AI as an editor.”

Martech’s Post-SaaS, AI-First Trillion-Dollar Future (Part 8)

AI Analysis

I asked Claude and ChatGPT to review the alignment with the ideas discussed in the vibe coding essay.

Claude

The core ideas between your two essays align remarkably well and create a coherent narrative arc. Here’s how they connect and what might be worth considering:

Strong Alignment Points

  1. The Commoditization of Features

Both essays nail the central insight: AI/vibe coding makes features trivial to build, so value shifts to what can’t be instantly replicated:

  • Vibe coding essay: “accumulated intelligence, validated data patterns, and institutional trust”
  • Martech essay: “Accumulated behavioural intelligence from billions of interactions”
  1. The Platform/OS Vision

Both position the future as platforms enabling ecosystems rather than monolithic applications:

  • Vibe coding: “Marketing OS… iOS or Android of Martech”
  • Martech: “Agent Marketplace… turning martech from monolithic software into a composable agent economy”
  1. Outcome-Based Economics

Both emphasize the shift from capability to results:

  • Vibe coding discusses outcome-based pricing emerging from the pricing crisis
  • Martech makes this central with Progency and Alpha models
  1. The Democratization Theme

Both recognize that AI enables non-technical users to build solutions:

  • Vibe coding: “citizen developers” and “domain expert developers”
  • Martech: The “hypertail” of billions of micro-apps

Potential Gaps or Tensions

  1. The Speed of Transformation
  • Martech essay: “2-3 year window” for transformation
  • Vibe coding essay: Suggests more gradual adoption with hybrid approaches Consider reconciling these timelines or acknowledging different speeds for different segments.
  1. The “Vibe Coding Hangover” Warning Your vibe coding essay extensively covers the downsides (security vulnerabilities, debugging nightmares, cost explosions), but the martech essay is more optimistic. You might want to acknowledge in the martech essay how companies will navigate these challenges.
  2. The Human Element The vibe coding essay touches on developer role evolution (“architects, reviewers, and quality guardians”), while the martech essay focuses more on marketer empowerment. Consider addressing how marketing teams will need to evolve their skills.

What You Might Add

  • The Competitive Dynamics: While both essays mention AI-native startups vs. incumbents, you could explore more deeply how vibe coding specifically enables new martech entrants to challenge established players.
  • The Data Governance Challenge: With vibe-coded tools proliferating and accessing APIs, how do companies maintain data governance, security, and compliance? This bridges both essays’ concerns.
  • The Integration Reality: Vibe coding makes building easy but integration complex. How does this affect the “8,000 tools to infinite micro-apps” transition?
  • The Pricing Model Transition: You could explore how companies practically transition from seat-based to outcome-based pricing while vibe coding disrupts their cost structure.

The Unified Narrative

Together, these essays tell a powerful story:

  1. Vibe coding democratizes software creation
  2. This forces martech to transform from features to outcomes
  3. The winners will be intelligence and trust platforms that enable infinite creation while guaranteeing results

Your vision of Netcore as the “trust, intelligence, and outcomes” layer that enables vibe-coded innovation while solving real problems (AdWaste, revenue taxes) is compelling and consistent across both pieces.

The main opportunity is to more explicitly connect how vibe coding’s challenges will be solved by the new martech architecture. This would strengthen the argument that established players like Netcore have unique advantages in the vibe coding era—not despite the disruption, but because of it.

ChatGPT

Alignment of Core Ideas

  1. Democratization vs. Reinvention
  • Vibe Coding → Anyone can now create software via natural language, making features and interfaces instantly replicable.
  • Post-SaaS Martech → Because features are commoditised, martech defensibility shifts to intelligence, outcomes, and data moats.
    👉 Alignment: Both highlight that features are no longer the moat—the future lies in outcomes, data, and orchestration.
  1. Agents as the Next Layer
  • Vibe Coding → Agents become orchestrators, stitching together multiple SaaS tools into workflows without human setup.
  • Post-SaaS Martech → Agents become the new operating system (Agents Collective, BrandTwins, TwinLedgers).
    👉 Alignment: Both position agents as the real interface, replacing dashboards and reducing SaaS to infrastructure.
  1. The Build vs. Buy Shift
  • Vibe Coding → Build vs. buy tilts toward “build,” since custom solutions can be spun up cheaply via prompts.
  • Post-SaaS Martech → Enterprises will increasingly build their own tools, collapsing SaaS categories into agentic orchestration.
    👉 Alignment: Both anticipate category collapse as vibe coding and agents empower bespoke, in-house solutions.
  1. New Business Models
  • Vibe Coding → Challenges SaaS seat-based pricing; pushes toward usage and outcomes.
  • Post-SaaS Martech → Introduces Alpha (outcome-based economics), Ads (cooperative networks), and ZeroBase/Progency models.
    👉 Alignment: Both agree SaaS pricing is obsolete; the future is outcome-linked.

What You’ve Missed (Gaps)

  1. Human + Organisational Strain
  • In the Post-SaaS essay, you explore AI intensity (compressed cycles, burnout risk).
  • In Vibe Coding, this organisational/human sustainability angle is underplayed. Adding it would highlight that the bottleneck isn’t just what AI can do, but what humans and orgs can absorb.
  1. Security, Reliability, and Compliance as Differentiators
  • Vibe Coding essay touches on debugging nightmares and security vulnerabilities.
  • Post-SaaS essay doesn’t stress enough that in a world of infinite vibe-coded apps, established martech players like Netcore can win by being the trust, compliance, and reliability layer.
  1. Ecosystem / App Store Vision
  • Vibe Coding hints at an ecosystem where many micro-apps emerge.
  • Post-SaaS frames martech’s future as trillions in value through Agents, Attention, Alpha, Ads.
  • Missing piece: the App Store / Marketplace model—Netcore (or others) as the “iOS of Marketing,” enabling vibe-coded/agent-built apps to plug into a trusted ecosystem.
  1. Atomic Rewards / Mu Layer
  • Post-SaaS covers Mu under Attention, but the Vibe Coding essay doesn’t link democratized software creation with incentive systems. Connecting them (e.g., vibe-coded attention apps monetised via Mu) would strengthen coherence.

Bottom Line

Yes — the essays align beautifully. Vibe Coding explains why SaaS economics collapse (features become disposable), and Post-SaaS Martech explains what replaces them (Agents, Attention, Alpha, Ads).

The biggest gap is not conceptual but architectural: you should explicitly connect “vibe coding builds apps” with “martech provides intelligence, trust, outcomes”. That framing makes the two essays feel like two halves of one manifesto.

Thinks 1744

WSJ: “The main difference between America’s brand of capitalism and elsewhere: a focus on the individual and an incentive to take risks.”

NYTimes reviews “The Story of CO2” [via Business Standard]: “Almost all of the energy that we have access to comes from the sun, and photosynthesis requires CO2.  In the usual processes, that energy trickles up through the food chain until it’s exhausted and released as waste heat. But the great luck of this planet is that rather than being consumed or rotted (same thing), reduced to waste and raw materials, some carbon stores — washes of plankton and heaps of swamp life — were instead entombed for millennia in stone. Thus, fossil fuels are “fossilised sunlight”: solar energy on reserve. This buried carbon also acts, in one of Brannen’s running metaphors, as a giant capacitor. It was charged by geology; it is now being discharged by human workings “on a planetary scale.”” 

New Yorker: “A.I. is coming for culture…We’re used to algorithms guiding our choices. When machines can effortlessly generate the content we consume, though, what’s left for the human imagination?”

SaaStr: “Everyone thinks their AI tool will save labor costs, but you can’t all get credit for the same labor savings. When five different AI vendors are each asking for $60K-100K+ a year to automate parts of your sales process – SDR tools, BDR tools, conversation intelligence, pipeline tools – the math stops working. Again, yes it’s cheap than a human.  So that gets the budget nod — today.  For now.  But ultimately, the pressure will come as we spend millions and millions on different, paid AI agents from different vendors that seem to overlap…Smart companies are already moving toward the Rippling approach: “Give us five agents and an orchestration layer, and we’ll handle it all.” Why manage five point solutions when one vendor can deliver the complete workflow?”

WSJ on how to use AI to learn a difficult concept: “AI offers the ability to dive into fields we never thought we’d learn—as long as you watch out for hallucinations and proceed step by step. First, whether it is French existentialism or principles of building, ask the AI for a big-picture overview: Tell it that it is delivering a first-year university lecture, or explaining the idea to a 10th-grader. Ask it to tell you the major terms in the field, summarize key findings and describe areas of uncertainty and disagreement. Once you’ve grasped that overview, do your own research: Look for peer-reviewed articles that have plenty of citations (100 or more is ideal; 20 or 30 is all right for niche topics). Give the articles to the AI and ask it to synthesize the findings. If you learn better out loud, use Claude or ChatGPT’s audio interface to talk to the AI about each article and ask questions. You can also upload a collection to Google’s NotebookLM, and ask it to generate a podcast on the subject, based on the articles.”

Martech’s Post-SaaS, AI-First Trillion-Dollar Future (Part 7)

Attention, Agents, Alpha, Ads

As martech companies navigate the AI transformation, four foundations will determine who thrives and who becomes obsolete:

  1. Agents: The New Operating System

The age of dashboards and manual workflows is ending. AI agents are becoming marketing’s operating system, multiplying human capabilities rather than just assisting them:

  • Agents Collective: Internal co-marketers autonomously handling segmentation, campaign orchestration, and optimisation at superhuman scale
  • Twin Factory: Manufacturing BrandTwins (customer AI representatives) powered by TwinLedgers, delivering true N=1 personalisation and profitability management where every customer has their own P&L
  • Agent Marketplace: Creating an ecosystem where specialised agents (content creators, campaign optimisers, audience analysers) can be deployed, combined, and orchestrated like apps on a platform—turning martech from monolithic software into a composable agent economy
  1. Attention: Engineering the Upstream Currency

Attention is upstream of every outcome—without it, no channel or campaign succeeds. Yet traditional channels (email, SMS, push, RCS, WhatsApp) face saturation, regulation, and declining engagement. The future lies in owning attention:

  • Attention Magnets: Daily touchpoints like The Brand Daily (daily brand touchpoints) or Muniverse (gamified brand experiences) where customers return voluntarily rather than avoid
  • Attention Currency: Mu powers a loyalty program which converts passive audiences into active participants, creating a sustainable attention flywheel where engagement is rewarded and measured
  • The next battle isn’t about messaging more—it’s about engineering enduring attention
  1. Alpha: Hedge Fund Economics for Marketing

The SaaS subscription model is giving way to outcome-driven economics. Borrowing from hedge funds’ distinction between alpha (excess returns), beta (market returns), and carry (value share):

  • ZeroBase Economics: Brands pay only for incremental uplift in revenue, LTV, or retention above baseline
  • Progency Partnerships: Vendor and brand co-create growth and share in the upside
  • By focusing on alpha—the excess return delivered—martech transforms from cost centre to profit engine
  1. Ads: The Second Revenue Revolution

Adtech built a $700B industry in two decades—with $500B being pure AdWaste spent on reacquisition. Martech, trapped in narrow SaaS thinking, remains a fraction of this. AI opens a different play:

  • PII-Powered Cooperative Networks (NeoN): Brands pool first-party data for surgical reactivation, reacquisition, and lookalike acquisition, bypassing the Google/Meta duopoly
  • ActionAds: Intent-rich, in-place ads that drive engagement without clicks or wasted impressions
  • Twin promise: Save brands billions by cutting AdWaste while unlocking new revenue pools for brands and martech providers

The Trillion-Dollar Opportunity

Adtech scaled by capturing attention, monetising through ads, and tolerating massive waste. Martech must now scale differently—combining Agents, Attention, Alpha, and Ads into a new architecture of growth. This is the essence of post-SaaS marketing: AI-native, outcome-driven, and retention-first.

The prize isn’t incremental SaaS revenue. It’s building a trillion-dollar martech industry that finally delivers on marketing’s impossible promises: precise engagement at scale, enduring customer relationships, and profitable growth where every dollar spent generates measurable returns.

The companies that master these four foundations won’t just survive the AI disruption—they’ll lead marketing’s evolution from cost centre to profit amplifier, from message blaster to intelligence orchestrator, from vendor to growth partner. The impossible becomes inevitable, making martech companies invincible in this new future. Martech must stop thinking like SaaS and start architecting the future of customer value creation.

Thinks 1743

Rebecca Heiss: “A study of workplace interventions to reduce stress, published in Industrial Relations Journal in 2024, revealed a startling truth: Of the 90 different stress-reduction strategies tested in corporate settings, which included meditation, massage and breathing exercises, only one consistently mitigated the negative effects of stress: serving others…People experiencing their own stress had all instinctively relieved this pressure by helping someone else—in this case, me. They weren’t following any wellness program or stress-management protocol. They were simply, and perhaps unconsciously, responding to their own anxiety by extending kindness to another person…This helped me see how we’ve been approaching stress relief backward. Instead of turning inward with bespoke wellness practices, we do best when we turn outward—toward the needs of others. This doesn’t mean meditation and self-care are useless, just that they are incomplete solutions.”

Crazy Stupid Tech: “[Cloudflare CEO] Prince wants to talk about the future of the web and journalism with me because he thinks the AI chatbot revolution is killing both of them. And he thinks he can help fix that with something he calls pay-per-crawl, a gambit he and Cloudflare launched on July 1…There are no ads when AI chatbots give you the answer. If there are links to sources, users almost never click on them.  AI chatbots also drive up publishers’ bandwidth costs because they crawl thousands of times a day…And now Google itself is accelerating the problem. As more and more users ditch Google search for their favorite AI chatbot, Google itself is referring less of the traffic that’s still using Google search. Instead, to compete with the AI chatbots, Google is using its own AI chatbot Gemini to answer those questions immediately.”

FT: “Cinematic-quality AI production tools are helping to launch thousands of digital avatars — or “AI influencers” — into the creator economy, which was estimated to be worth $250bn in 2023, whether newly generated personas or clones of existing influencers…Proponents argue such tools can help existing influencers by automating some of their work — translating video content into other languages, responding to fans or deploying animated versions of themselves to clinch marketing deals, even while they sleep. For brands, there is the promise of cheap, instant influencer marketing and full control over what an avatar looks like and says. It is, according to Alexandru Voica, head of corporate affairs and policy at media generation start-up Synthesia, the “great equaliser”, whereby even small brands without big budgets can afford “polished, studio-quality content at scale”.”

Economist discusses “There’s Got To Be A Better Way”: “The authors’ premise is that many of the processes which govern work within organisations are broken. Whether they are flawed from the outset or malfunction over time, they need constant monitoring and improvement. At the heart of the book is a simple instruction to managers: go and see how things actually work. “If you aren’t embarrassed by what you find,” they write, “you probably aren’t looking closely enough.””

Bloomberg: “The best-case scenario, of course, would be that [Ashish] Vaswani hits on another breakthrough with the impact of the transformer. Llion Jones, another co-author of the “Attention” paper, says hunger is mounting for another leap. The leading AI labs have made significant strides in wringing out increased performance from transformer-based models, as they’ve adapted them to handle larger datasets, developed strategies to increase their reasoning and applied them to specific use cases. “They’ve been around for so long that every single permutation that one can think of has been tried,” Jones says. He says there are still valuable projects to be done with transformers, but he’s mostly scrapped them from his personal research agenda in favor of more speculative work. “I decided I’ve had enough of them.””

Martech’s Post-SaaS, AI-First Trillion-Dollar Future (Part 6)

My Writings

The martech industry stands at an inflection point where three powerful forces converge. First, the vibe coding revolution is commoditising feature development—what once took months to build now takes minutes to generate through AI. Second, the agent economy is transforming marketing from human-operated dashboards to AI-orchestrated systems operating at superhuman scale. Third, B2C companies face an accountability crisis, haemorrhaging 15-20% of revenue to Google and Meta while drowning in billions of AdWaste, even as their martech vendors collect fees regardless of results.

This convergence exposes a fundamental flaw in traditional martech business models: they sell potential while customers need outcomes. They charge for messages and MAUs (monthly active users) while value comes from results. They protect features while intelligence becomes the real moat.

The vibe coding disruption accelerates this reckoning. When anyone can generate a marketing automation tool through conversation with AI, the traditional defensibility of “we built this complex feature set” evaporates. What can’t be vibe-coded? Accumulated behavioural intelligence from billions of interactions. Deliverability reputation built over years. Trust infrastructure ensuring compliance and security. And most importantly—proven ability to generate profitable outcomes.

My 200+ essays on marketing’s future have explored how martech must evolve from selling software to delivering growth. The following seven themes represent a fundamental reimagining where martech companies become true partners in profit generation, succeeding only when their customers succeed.

  1. Progency: The Hybrid Product-Agency Model

The most radical reimagining—fusing product with AI-powered agency services where payment is based on alpha (incremental growth above baseline). Instead of selling software access, martech companies sell guaranteed outcomes. This model:

  • Takes on execution risk and shares in upside
  • Solves marketing’s “Mission Impossible” by aligning incentives completely
  • Transforms martech from cost centre to profit amplifier
  • Charges based on actual lift in revenue, LTV, or retention achieved
  1. ZeroBase: Zero-Risk Entry with Pure Outcome Pricing

Eliminates adoption barriers by charging nothing upfront—monetising only on incremental results. This model:

  • Proves value before charging anything
  • Particularly powerful for retention initiatives with clear baseline measurements
  • Directly attacks the “revenue tax” problem by demonstrating ROI first
  • Shifts all vendor risk to performance
  1. Agentic Marketing Infrastructure

AI agents operating at superhuman scale creates entirely new opportunities:

  • Workflow automation-as-a-service: Where agents handle entire marketing operations
  • BrandTwins: AI representatives for individual customers that negotiate with brands, with TwinLedger (maintaining P&L for every single customer, and not segments)
  1. Composable API-First Architecture

Unbundling martech into microservices that AI agents and vibe-coded apps consume:

  • Segmentation engines exposed as APIs
  • Deliverability infrastructure as a service
  • Predictive models accessible programmatically
  • Campaign orchestration tools automated without human intervention
  • Charging per API call rather than per seat, enabling infinite scaling
  1. AdWaste Elimination as a Service

Directly attacking the billions wasted on ineffective advertising:

  • Charging based on AdWaste reduced rather than features used
  • Building owned media assets (e.g. The Brand Daily) that reduce paid channel dependence
  • Shifting focus from acquisition (expensive) to retention (profitable)
  1. Atomic Rewards and Micro-Incentive Platforms

Reimagining loyalty as precision behaviour modification:

  • Micro-incentives delivered at exact moments to influence decisions
  • Charging for behaviour change achieved not program management
  • Real-time optimisation of incentive timing and amount
  • Payment based on incremental customer actions generated

**

The Race to Reinvention

These seven models converge on a singular truth: the future of martech isn’t about better software—it’s about guaranteed growth. Tomorrow’s martech companies will be growth partners, not software vendors, succeeding only when their customers succeed. This shift from “pay for potential” to “profit from performance” represents a complete inversion of the vendor-customer relationship.

The timing is critical. Clayton Christensen’s disruption theory suggests incumbents rarely survive paradigm shifts through incremental adaptation—they must fundamentally transform or be replaced. With AI-native startups already building outcome-first platforms from scratch, established martech players have a narrowing window—perhaps 2-3 years—to reinvent themselves.

The survivors won’t be those with the most features or slickest interfaces, but those solving the real problems plaguing B2C companies: revenue taxes paid to digital monopolies and billions wasted on ineffective advertising. In this new paradigm, martech companies amplify profits rather than sell tools, earn from outcomes rather than charge for access, and provide the intelligence and trust infrastructure that no amount of vibe coding can replicate.

The question isn’t whether this transformation will happen, but which companies will lead it, and which will be left behind, trying to sell dashboards in an age of autonomous agents.

Thinks 1742

David Brooks: “I sometimes hear people say that you have to love yourself before you can love others. But this is backward. You have to observe yourself loving others before you can see yourself as lovable and before you genuinely are lovable.”

WSJ: “In the past three years, in the wake of Russia’s invasion of Ukraine, $120 billion of venture capital has flowed into the once-neglected defense sector. Silicon Valley has gotten over its woke resistance to the U.S. military. Anduril Industries is leading the way on autonomous warfare; Shield AI is delivering decision-making help to combat pilots and drones; Saronic Technologies is focused on naval warfare. They’re fixing a problem that began during the Cold War, the estrangement of an ever-shrinking defense oligopoly from the fast-moving civilian economy. As recently as the 1980s, Mr. Sankar estimates, 6% of procurement dollars went to companies whose sole business was with the Pentagon. Now it’s 86%. Chrysler once built tanks and missiles. Ford built satellite equipment. General Mills—the cereal company—was in the artillery and guidance-system business. Not anymore. The government became too difficult a customer—too many rules, too little opportunity to scale up. It stopped being open to the kind of innovation and learning that drives the rapidly evolving commercial marketplace.”

Mantic: “Good decision-making is the ultimate meta-skill that lets humanity prosper. However, our decision-making is severely bottlenecked by our prediction capabilities. Imagine if Western governments had proactively allocated the appropriate level of attention and resources to coronavirus pandemics, deterrence of Russian aggression in Ukraine, the rise of generative AI, and supply chains for rare earths. At Mantic, our goal is to solve judgemental forecasting. An example question: Will Iran close the Strait of Hormuz before 2027? To answer this question, the forecaster must understand the state of the world and reason about how things will play out. These are uncertain, so – rather than selecting a single outcome – the forecaster assigns probabilities over the set of possible outcomes. To measure their performance, you must ask the forecaster hundreds of questions, wait to see what happens, and apply a scoring function that penalizes the discrepancy between each prediction and the observed outcome. Human “superforecasters” are the best judgmental forecasters.”

FT: “[Amul’s] co-operative model has propelled it to a 75 per cent market share of the country’s milk market and helped India become the world’s largest milk producer — contributing 25 per cent of global production…Amit Vyas, Amul’s managing director, said the business model, which involves more than 18,000 village co-operative societies, over 3.6mn farmers and a network of more than 1mn retailers, works because “the production, processing and marketing is all owned by the farmers”. Another factor in Amul’s success, according to Vyas, is its procurement system, which secures 35mn litres of milk a day from cows, buffaloes and even camels. Since it was set up in 1946, Amul has bought everything each of its members produces “every day of the year, rain or shine”, he said. “Be it one litre or 500, we’ll buy it and pay it on the day,” he explained.”

Martech’s Post-SaaS, AI-First Trillion-Dollar Future (Part 5)

State of Martech

I asked AIs to analyse The State of Martech 2025 by Scott Brinker and Frans Riemersma and list out relevant themes.

  1. The Hypertail Revolution: From 8,000 Tools to Infinite Micro-Apps

Martech is evolving from today’s overwhelming 8,000+ point solutions into a “hypertail” of billions of AI-generated, on-demand micro-applications. Through vibe coding and natural language prompts, marketers can instantly create custom tools without technical expertise. This transforms martech from a fixed catalog of SaaS products to an infinite, generative ecosystem where the distinction between “buying” and “building” dissolves.

  1. Marketing AI’s Paradox: Behind but Poised for Breakthrough

While marketing AI lags behind sales and customer success AI, this creates a unique opportunity window. With 78% of companies using AI for content production but only early-stage adoption of AI agents, martech sits at an inflection point. The category-defining companies haven’t emerged yet, meaning both incumbents and startups can still claim the autonomous marketing space.

  1. From Stack to Orchestrator: The Architectural Revolution

The martech stack of 2027 won’t be a stack at all—it will be an AI orchestrator. CDPs are declining as the center, replaced by cloud data warehouses (56% integration), MAP/CEP platforms, and CRMs. AI agents don’t just assist; they autonomously orchestrate campaigns across platforms through new standards like MCP (Model Context Protocol), making today’s campaign builders and dashboards look like “spreadsheets in the age of algorithms.”

  1. Data Infrastructure as the New Moat

With nearly 60% of companies running AI apps directly on cloud data warehouses/lakehouses, proprietary data has replaced product features as the primary differentiator. In an AI-first world where features can be instantly replicated, the companies sitting on rich, unique customer data will create defensible positions. This shift fundamentally changes martech’s value proposition from tool provision to data intelligence.

  1. The Autonomous Engagement Transformation

AI is finally delivering on martech’s decades-old promise of “right message, right person, right time” through true N=1 personalisation. The shift from campaign management (human-driven, tool-assisted) to autonomous customer engagement (AI-driven, human-supervised) represents a fundamental change. AI agents watch, learn, and gradually take over marketing execution, creating adaptive experiences that evolve with each interaction.

  1. The Great Consolidation and Category Collapse

Traditional martech categories face extinction or radical transformation. CDPs are being hollowed out by AI-driven integration, while entire categories of specialised tools will collapse into agentic platforms. The 2-3 year survival window means martech companies must either transform into AI-native platforms, position for acquisition, or face obsolescence as AI-native entrants rise.

  1. The Build vs. Buy Disruption

Generative AI is making it viable for enterprises to build custom marketing solutions in-house, threatening the traditional SaaS model. Combined with citizen developers creating instant applications, this erodes the dominance of established martech vendors. The barrier between vendor and customer blurs as companies can generate their own marketing tools on demand.

  1. Uneven Adoption Creates Opportunity Gaps

B2C companies lag B2B in deep AI integration, while content production dominates over more sophisticated uses like segmentation and personalisation. With AI assistants at 87.5% adoption but agents still early-stage, there’s a clear progression path. Companies that can accelerate customers along this maturity curve—from assistants to agents to fully autonomous systems—will capture the market.

The Bottom Line: Martech faces the most dramatic transformation in its history. The category must evolve from a fragmented collection of 8,000+ tools to AI-orchestrated platforms that operate on proprietary data moats, generate infinite micro-applications on demand, and deliver truly autonomous customer engagement. Success belongs to those who embrace this shift completely, not those who merely bolt AI onto existing products.

These 4 graphics are relevant for our future discussion: