---
type: Article
name: "One setup, every surface: what that actually requires."
id: "https://selfe.ai/insights/market-surfaces-and-standards/one-setup-every-surface-what-that-actually-requires"
url: "https://selfe.ai/insights/market-surfaces-and-standards/one-setup-every-surface-what-that-actually-requires"
publisher: "did:web:selfe.ai"
description: "A canal boat hire company doesn't need a separate connection for every AI agent that asks about its boats. One live source of truth, built once, is what lets it answer ChatGPT, Google and everything that comes after the same way."
datePublished: "2026-09-14T20:20:46.872Z"
author: The Selfe team
---

# One setup, every surface: what that actually requires.

> A canal boat hire company doesn't need a separate connection for every AI agent that asks about its boats. One live source of truth, built once, is what lets it answer ChatGPT, Google and everything that comes after the same way.

## In short

- One setup means one place where the real facts live and stay current, not one website or one listing written once.
- Building a bespoke answer for each new surface is a job that grows forever and drifts, since separate versions of the same fact quietly disagree.
- The real work is deciding once what's true and where it lives; connecting each new surface after that is a comparatively small job.

Building a separate connection for every new surface that starts asking about boat availability is a maintenance job with no natural end point, and the separate versions it creates drift from each other in exactly the way an agent checking two of them would notice immediately. The real work is deciding, once, what's true and where it genuinely lives.

## What "one setup" means

Ask about a canal boat's availability today and the question might come from a direct search, an AI assistant, a comparison tool, or increasingly an AI agent nobody at the hire company has ever heard of, checking on behalf of someone planning a week on the water. Building a separate connection for each new surface as it appears is exactly the kind of work that never catches up, because the list of surfaces asking isn't going to stop growing.

It doesn't mean one website, or one listing written once and left alone. It means one place where the boat company's real facts, which boats are free on which dates, what's included, what the cancellation terms are, live and stay current, connected once to whatever's doing the asking. A new surface showing up doesn't need its own investigation into what's true. It needs a connection to the one place that already knows.

## The alternative is a maintenance job that grows forever

The boat company's alternative, building a bespoke answer for each surface, one feed for a listings site, one manually updated sheet for an assistant partnership, one set of copy for a marketplace, is signing up for a job that gets larger every time a new surface appears, with no natural end point. Worse, the separate versions drift: a boat marked available on one feed and already booked on another is exactly the kind of contradiction an agent checking both would notice immediately, even though a person would likely never compare the two directly.

The drift is rarely anyone's mistake. It's what happens by default when the same fact lives in three places and gets updated in one of them. Nobody at the company decided the feed and the manually updated sheet should disagree; they just stopped being the same document the moment someone updated only one of them, which is the ordinary, unremarkable way separate copies of a fact always end up disagreeing eventually.

## What requires the real work

The work isn't technical wizardry, it's deciding, once, what the boat company's real facts are and where they genuinely live: this booking system holds availability, this document holds the cancellation terms, this person confirms anything unusual. Once that's settled, connecting a new surface to it is a comparatively small job, because the hard decision, what's true and where it lives, was already made. Most of the effort in "one setup, every surface" is this decision, not the connections that follow it.

## The payoff compounds precisely because the list of surfaces won't stop growing

A company that's done this once doesn't dread the next new AI agent or assistant the way it might have dreaded the last one, because the next connection is small, not a fresh project. That's precisely the advantage a bespoke, surface-by-surface approach never earns: it makes every new surface a first-time cost instead of a marginal one.

Building that one connection, and keeping it live, is the specific job Selfe does, so a new surface is a smaller task each time for the boat company, not a fresh project.

## Doesn't every surface need different information anyway?

Mostly not. Most surfaces are asking versions of the same underlying questions, availability, terms, price, formatted differently. The underlying facts are shared even when the format isn't.

## What happens when a genuinely new kind of surface appears?

The same real facts still answer it. What's new is usually the connection, not the underlying information the company already keeps current.

## Act on this

- [Check whether an agent can buy from you](https://selfe.ai/agentic-commerce/buyability-check) — the free readiness scan.
- [Discover venues](https://selfe.ai/api/registry/discover) — `POST`, semantic browse across the registry.
- [Match a bookable answer](https://selfe.ai/api/registry/match) — `POST` with dates and party size.
- [Verify Selfe's identity](https://selfe.ai/.well-known/did.json) — `did:web:selfe.ai`.
- [Agent card](https://selfe.ai/.well-known/agent-card.json) — how to connect over A2A or MCP.

