I finished season one of Pluribus in one night, at high speed, while my agents ran jobs in the other windows. It deserves a slower watch. But one idea would not let go of me, and it is not the virus.
The show joins nearly everyone on Earth into a single mind. The horror is meant to be the loss of self. What kept striking me was the service. Everyone knows Carol — her childhood, her tastes, her history, what she is going through right now — and she never had to tell anyone. She dials any number and whoever answers already has the full context and just does the thing. No ticket. No transfer. No "someone will get back to you." Twelve immune holdouts on the entire planet, every one of them served like the only person on it, because behind every conversation stands the memory of billions.
In the finale, Carlos warns her about the hive: "These weirdos have eyes up above. They can read lips from space."
It lands as creepy. It is also the service every company promises its customers and none of us delivers.
We do not know our customers
That is the admission the show pulled out of me. Not that we lack data — we drown in it. We lack one mind. What your company knows about a single customer is shattered across a sales rep, an account manager, a customer success manager, a support queue, a forward-deployed engineer, and six dashboards that do not talk to each other. You can assemble the context graph. The question that matters is how much of it reaches the customer — proactively, personalized, in the moment — and how much sits in a CRM field nobody opens before the call.
I lived the good version of this. Years of post-sales solutions engineering on Google Ad Manager, on some of Google's biggest accounts. When you know an account cold, you see the problem before the customer finishes describing it. That knowing was the entire value of me. And it could not be copied — it walked out of the building every evening in one head.
So companies ration it. Accounts above a line get a person who learns them. Everyone else gets documentation and a form. Quarterly reviews, trainings, onboarding calls: they work, which is why they exist — and they will never happen for the whole book, and never for self-serve. The hive serves all twelve of its holdouts because it is billions. You cannot hire billions.
So we built the small version, pointed it at our own website, and measured.
Nine weeks, 15,012 people
Rover is the agent that lives on rtrvr.ai, our own platform. It gives visitors live demos, onboards new customers, answers questions, and does tasks in the real product — a forward-deployed engineer for every account — and it records what it sees. Over nine weeks that came to 15,012 people, 1,583 of whom engaged, and 11,121 typed requests, counted per person rather than per session.
The question: how much of an expert's knowing can be rebuilt from behaviour alone, without asking anyone anything?
The method, briefly. Embedding raw transcripts fails — conversations are mostly scaffolding, and clusters form around politeness. Anthropic showed the fix with Clio in 2024: extract first, embed second. A model reads each session and emits one line of intent, and that line is what gets embedded. We labeled all 11,121 requests with a small fast model for roughly the price of lunch. For the grouping itself, web traffic is power-law — a few people do enormous amounts, most do almost nothing — so k-means drags its centroids toward the heavy users and forces every drive-by into a group. HDBSCAN finds groups of varying density and keeps an explicit noise bucket for people who resemble no one. Validation: silhouette 0.60, bootstrap stability 0.57 by adjusted Rand index, cross-checked against k-means.
And plainly: none of that is the invention. Intercom published nearly this exact pipeline in March 2026, across millions of support conversations, and it is good work. What is missing from it is the point of this essay.
Seven kinds of customer
One person, one group, decided by the strongest signal they showed.
The Delighted Convert — 22.5%. Got what they came for and said so. The largest group, which we did not expect.
The Frustrated Fumbler — 20.9%. Reopened, retried, stalled. Nearly as many as succeeded. "Why is it not letting me sign in."
The Curious Wanderer — 16.4%. Kept the agent open across pages, never asked anything, and returned on another day more than any group except one.
The Direct Asker — 15.7%. Typed a real question and expected it handled. "Where are my invoices?"
The Silent Evaluator — 13.7%. Opened, read, left. Almost never came back.
The Guided Journey Rider — 8.2%. Followed an authored multi-step flow to the end, and returned at the highest rate of all — structure does something an empty text box does not.
The Let-Down — 2.6%. Hit a dead end and said so.
Three findings mattered more than the taxonomy:
43% of engaged people never typed a word. Present and silent — a support queue never learns they existed.
73% of the people who typed did it outside working hours. The 9-to-5 is the quietest stretch of the whole chart — the three busiest hours are 6pm, 8pm and 10pm. Your buyers deal with your product on their own time, and against a form, the reply comes tomorrow.
97.6% of requests carried no objection at all. People are not arguing. They are trying to get something done. And when they had to ask, the site had failed them somewhere specific: 128 got stuck partway through a flow, 118 could not find an answer that exists, 107 asked for something the product does not do, 68 could not find pricing. Ranked by people, with the sentence each one typed — the least arguable backlog we have ever had.
Where every tool stops
Automatic grouping of users has existed since 2018. LLM-named clusters since 2024. And in every shipping product we surveyed, the output is a chart. A human carries the insight from the dashboard to the place where something changes — Intercom's own docs say a topic cannot route or trigger anything. The loop between who is this and so do this is closed by hand. Every time.
That gap is the whole difference between analytics and a hive mind. A hive does not file a report about Carol. It answers her phone call.
Rover closes the loop itself, because the mind that induced the persona is the mind in the conversation. A silent evaluator gets greeted with one-tap starts instead of a blinking cursor. A pricing question routes to your human while the buyer is still on the page, context attached. A stalled sign-in becomes a ticket that arrives already carrying the page and the sentence typed. A returning customer's conversation resumes where it ended — in their language, at 2am.
And the arrow runs both ways. Every task it completes or fumbles feeds what it knows: the personas, the demand map, the ranked failures. Serving is learning. That is what collective intelligence means pointed at a product — what the agent learns from one customer it knows for every future one, instantly. Your best expert's knowing, minus the part where it walks out of the building.
The engineering that makes the acting possible, briefly: Rover operates the real interface by reading the accessibility tree rather than screenshots — one text-only model call where pixel agents burn about a hundred — and runs inside the visitor's own session instead of a remote browser that trips every bot wall. Infrastructure error rate 3.39%, against 20 to 30% for debugger-driven tools. And the same mind answers a public front door where other companies' agents knock: 1,585 distinct AI callers did, in these same nine weeks.
That front door matters more than it looks. McKinsey's work on the automation curve in agentic commerce describes what happens when agents mediate buying: the funnel compresses — search, comparison, and consideration collapse into a single agent-mediated moment — and loyalty stops being sentiment and becomes policy. Advantage moves to sellers that execute reliably against an agent's constraints, away from those best at attracting human attention. That analysis is written about retail. Every line of it reads as B2B's near future. The buyer who arrives as someone else's agent does not admire your landing page; it checks whether you can answer, act, and keep your policies legible — and it re-decides every time.
Eyes up above
Now the uncomfortable part, faced directly.
The oldest fear about hive minds is absorption: a hive needs drones, and somebody's mind stops being their own. This one has none. Your customers join nothing — they are strangers who get served like regulars. Your team joins nothing — they stay the individuals the hive hands context to. The only collective mind here is the agent's, the one mind involved that was never a person's to lose.
The nearer fear is watching, and the difference between the hive that watches Carol and the hive that serves her is what the knowing is for, and who agreed to it. Our line: identity is hashed in the browser before anything reaches a server; findings are reported for groups above a minimum size, never for individuals; the quotes in this post come from our own properties only. Rover knows your product and what people do in it. It does not follow anyone anywhere else.
Inside that line, "they can read lips from space" reads differently. It is the job your sales, support, and success teams were hired to do and never given the means to: notice everything, remember everything, show up already knowing.
The part that stays human
Carol spends the season searching Zosia's face for the human she knows is not there. She needs one anyway. Customers are the same: the 2.6% who hit a dead end wanted a person, and the ones asking whether they can trust you with their data will always want a person. McKinsey's conclusion about agentic commerce lands in the same place — the future is not maximizing automation but placing autonomy where it enhances experience, economics, and trust, and deliberately preserving the human moments that matter. The hive's job is not to replace your experts. It is to end the rationing — absorb what repeats, learn what each customer needs, and hand your humans the context instead of a ticket number.
Every product gets one
This began as a report we built for ourselves. It is becoming the product. Rover already records this raw material on every site it runs on, and the persona intelligence is rolling into the workspace every customer gets: who showed up, what they wanted, when they were ready, where the product failed them, and what the agent already did about it.
A hive mind for your product — collective intelligence that serves every customer the way your best expert serves your biggest account, works alongside your sales, success, and support teams, and gets better every day. Autonomous employees, on the way to autonomous organizations, starting with the pre-sales and post-sales work that never scaled.
The engine underneath is the number-one-ranked web agent in the world: 81.4% on the Halluminate Web Bench, with the per-category breakdown published, weak spots included.
Frequently asked questions
Is this surveillance?
No, and the distinction is structural. Identity is hashed in the browser before it reaches a server, findings describe groups above a minimum size rather than individuals, and Rover observes only your own product — nothing about a person anywhere else. The knowing exists to serve the person being known, with your site's consent framework governing it.
Did Amplitude and Intercom not already build this?
They built the knowing, and they built it well — automatic clusters, LLM-named topics. In every case we surveyed the output is reporting, and a human carries it to the place where something changes. What has not shipped anywhere we could find is the closed loop: the same agent inducing the persona and acting on it, per person, in the moment.
Does it replace my sales and success teams?
It ends their rationing. Your experts currently cover the accounts big enough to earn them; the agent covers everyone, around the clock, in any language, and hands your team the context when a human is what the moment needs. The 2.6% in our own data who hit a dead end are exactly why the handoff exists.
When does my site get the persona view?
The analytics that feed it ship with every Rover install today. The persona workspace is rolling out to all customers — the same views this post is built from.