Dr. Dave Gilbert · 30 years of situated UX research

Once software starts acting for you, one question matters: who are you talking to?

Everyone agrees the conversation is becoming where computing happens. The consensus then collapses everything into it — every service speaking through one assistant's voice, every app squeezed into a widget in the chat window. I'm betting against both collapses: services present as themselves, accountable, in the conversation — and real websites beside the chat, coordinated with it through a shared grammar.

Three research probes are in the field now — Suminar, Mem·Sum, and Mail·Sum — built to learn, not to launch.

Today's answer is a ventriloquist — one voice performing many hidden principals. The better answer is a conversation where every voice has an owner you can name — one you can see, question, and hold to account.


The first bet

One assistant, or the conversation?

The consensus model hides a multi-agent system behind the scenes and puts a single assistant in front: the sub-agents do the work, the assistant speaks for them, and you only ever talk to it. The bet here is the opposite — that the agents worth trusting are the ones you can address yourself: service and brand agents present as themselves, accountable for what they say, in one conversation with you and with each other.

The Forum — the architecture, in full →

ONE ASSISTANTthe assistantyouone voice; no one else you can addressTHE CONVERSATIONyouhotelairlineyour assistant
The first bet, drawn: one voice in front of agents you can't address — or named agents in one conversation, talking to you and to each other.
The second bet

A widget in the chat, or the website beside it?

There is a second collapse under way, and a second bet against it — independent of the first, and at least as important. The assistants with real adoption — ChatGPT, Claude, Perplexity — are becoming where people meet software, and the industry's first answer is to squeeze the world's services into the chat itself: apps as iframes and widgets embedded in the message stream. My bet is that this will never be rich enough to satisfy. A chat message is a fine place for an answer and a terrible place for an application to live.

The labs are already gesturing at the better geometry: OpenAI and Anthropic now ship fully functional, Chromium-based browsers inside their desktop apps — the chat on one side, real websites in tabs beside it. The shell is right, and the seam is empty. The assistant can open a page, read it, even drive it; what's missing is the conversation between the two surfaces — no protocol, MCP or otherwise, by which the chat side and the website side work out the user's flow: what was selected, what is staged, what was approved, what actually happened. Co-location is not coordination. That unexplored seam is where my work concentrates.

What has to develop across it is an interaction grammar: two surfaces working the same live objects — the chat reasons and authors; the site shows, stages, and authorizes; typed acts keep the two in common ground. Most of the technical pieces already exist. And the grammar cannot assume a desktop app, because that is not where the users are: people meet their assistants overwhelmingly through the web versions of ChatGPT, Claude, and Perplexity, so what I'm developing depends on no rich client at all — a browser tab of chat, a slender window beside it, an ordinary protocol between them. The Companion sidebar and its pop-out pages are my probes into what this future UX needs to be; The Grammar of the Second Surface is the vocabulary, with its first increment already running.

A WIDGET IN THE CHATTHE CHATyou“book the flight?”the assistantthe airline appin an iframe…the thread scrolls onsqueezed into the message streamTHE WEBSITE BESIDE ITYOUR CHATyouyour assistantreasons · authorsthe service's sitethe pagethe live objectshows · authorizesorient · pointreferences backcommitview moves freely; commitment is authorized on the site
The second bet, drawn: the app squeezed into the message stream — or two surfaces on one live object, where view flows freely and commitment passes the gate on the site's edge.
The bets, in the field

Three probes into computing after the app

I didn't stop at the argument. The ·Sum family is a set of research probes — small working products, each built to test one dimension of what computing looks like once the app is displaced by the conversation you already live in. What you read: Suminar (live, in beta) is the first bet, running: the chat you already use becomes the forum, and each scholarly source joins it as a genuinely separate agent — its own memory, its own calls, its own context, its own voice — not one backend ventriloquizing many names. What you remember together: Mem·Sum (live, in beta) is one shared Sum — pages, people, evidence — for one to five people, reached through the assistants they already use. What you send: Mail·Sum (in private alpha) is a real email address feeding an owner-confirmed private Sum — already sending mail: the chat authors, the site authorizes. And running beside all three, the Companion and its pop-out pages are the second bet's probes — the two-surface UX between chat and website, in the field. This site is called After the App for a reason — this is what after the app looks like.

The probes are the study — not a startup being launched, and free is the method, not a promotion. This is how I do UX research now: build the instrument, put it in people's hands, and learn from what they choose to share. The operator surface is content-blind by construction, so the beta learns only what users volunteer. The argument ships, and the shipping argues back (the case study).

The Companion — the family's signature surface — beside Claude. Left: Mem·Sum, where [[Our Cats]] #dave-lisa cites an exact page in plain chat. Right: Suminar's Shelf of source agents — the screenshot in which the host, unscripted, declined to paraphrase a source. Click or tap either to view full screen; the full story is The Companion.

Three arenas where it plays out

Same shape everywhere — a conversation of agents you can address directly, not a single assistant. These are the three concrete places it lands.

The Individual

You, as yourself, meeting the world's brands and services in the open — across every surface you use, web and apps alike.

Enter →

The Home

AI as domestic infrastructure — household administration handled by a configured appliance, not a chat toy or a butler.

Enter →

The Workplace

Agents inside the organization: the forum architecture deployed at work, with visible roles and accountable handoffs.

Enter →

Start here

Three refusals, one argument — the triptych at the front of the spine.

The spine · Essay

Against the Everything Assistant

One voice that sees and does everything is the wrong dream. Point at the thing; land in a room that remembers; let named services act and tell the truth about it.

The spine · Essay

Against the Middleman: Why Agents Should Speak to You Directly

Why the future isn't a hidden swarm behind one assistant, but branded agents that join the conversation as themselves.

The spine · Essay

Who Are You Talking To?

The ventriloquist problem: when one assistant speaks for many hidden brands, you can no longer tell whose voice you are hearing — or who benefits.

All the essays, newest first, with reading paths →

The practice behind the essays

Thirty years of one question

None of this is a pundit's bet. These essays are the latest application of a research practice held steady since 1995 — from a conversation-analytic study of an early agent-based PDA, through museum galleries, retail aisles, and an aging-in-place startup, to instrumented research on today's AI. One lens throughout: how people make sense of, break down with, and repair their understanding of intelligent machines. The case studies carry the primary evidence — the 1995 transcripts, the research programs, the shipped decks. And lately the practice ships: the Sum family above is the same method, run as live probes.

Read the practice →

The vocabulary, mapped

A connected system of concepts

The work is the conceptual apparatus — named, interlinked, and usable. Every term is defined and linked to where it is argued.

Open the concept map →