# How an AI agent reads your business: the four interfaces behind the answer

> How AI agents read a business: machine-readable profile, structured data, text twin and controlled query — with first-party measurements and the honest limit.

![Isometric illustration: a glowing data core surrounded by four surfaces — text lines, a data grid, list rows and a keyhole — connected to the core by thin lines.](https://cdn.btlabs.dev/media/ki-agent-vier-schnittstellen-datenkern-2688x1520-7f28bc57.webp)

Berger+Team · Nov 19, 2026

Topic: [Machine-readable website →](https://btlabs.dev/en/ai-website)

When someone asks an assistant about a business today, that assistant rarely opens the website the way a person sees it. It fetches what is [machine-readable](https://btlabs.dev/en/glossary/machine-readable-website) — and what it finds there decides whether your business appears in the answer or not.

This is not speculation. On this website, AI and search systems triggered **23,520 requests** in a 30-day window up to August 2026\. Among them, systems that clearly belong to assistants: ClaudeBot with 1,171 requests, GPTBot with 815, OAI-SearchBot with 476.

## What does an AI agent actually fetch?

An [AI agent](https://btlabs.dev/en/glossary/ai-agent) does not fetch one page — it fetches four different things, and each answers a different question. The machine-readable profile answers "who is this and what is here?". The [structured data](https://btlabs.dev/en/glossary/structured-data) answers "which facts apply?". The text twin answers "what does it actually say?". The controlled query answers "what is current right now?".

Together, these four make up a company's discovery surface. If one is missing, the agent has to guess — and guessing is exactly where wrong recommendations come from.

## Interface 1: the machine-readable profile

A machine-readable profile is a simple text file in the root directory that tells a [language model](https://btlabs.dev/en/glossary/llm-large-language-model) , in plain form, what the site is about and where the important content sits. The proposal came from Jeremy Howard and was published in September 2024.

The honest framing matters here: in 2026, Ahrefs analysed the domains in its web analytics service that had visitors in May. 28% of them had an [llms.txt](https://btlabs.dev/en/glossary/llms-txt) — and **on 97% of those domains, nobody requested the file in May**, neither bots nor humans. The sample skews technical. The file on its own therefore achieves little; at most it can help if what it points to is cleanly readable as well.

## Interface 2: structured data

Structured data are machine-readable annotations in the page source that separate facts from their presentation: opening hours, address, services, authorship, publication date. A person reads "we're here for you Monday to Friday". A machine only derives a reliable time span from that if it is annotated separately as a date.

That is the difference between a statement a model has to interpret and one it can simply read. Interpreting produces errors; reading does not.

## Interface 3: the text twin

A text twin is the same page in plain text — no navigation, no layout, no scripts. For an agent, that is the difference between a document and a building site: it doesn't have to work its way through menus, consent dialogues and deferred loading, but gets the content directly.

That saves it not just effort but time — and time is a scarce resource for agents. Anything fetching on a limited time budget gives up on slow or deeply nested pages and sees only a fraction.

## Interface 4: the controlled query

The first three interfaces are static: they deliver what was true at the moment of publication. The fourth is a controlled query option — a defined access point through which an authorised system can ask specifically for current details, instead of inferring them from a page.

The difference shows in everything that changes: availability, current services, contacts. Facts fetched statically age between two visits. A query is always current.

The decisive part is the control. Such an access point is not an open gate but a door with a key: whoever uses it is known, and what they may do is defined.

## Why four interfaces and not one?

Because no system uses all four the same way. Some assistants take only the text. Others follow the profile. Others read nothing but the structured data. Serving only one interface makes you invisible to precisely those systems that prefer another.

It is the same reasoning as with multilingual sites: you don't build for the language you hope will be asked, but for all of those that occur.

## Not everyone claiming to be an assistant can be confirmed as one

A detail from the same measurement that gets underestimated in practice: of 5,728 requests from a system presenting itself as a major provider's agent, **six** could be verified. With systems that genuinely belong to assistants, the ratio is the other way round — for GPTBot, 684 out of 815.

Anyone opening their discovery surface should therefore know who they are opening it to. For many major providers, identity is verifiable, and verifying it is the difference between openness and loss of control.

## The honest limit: being read is not the same as being recommended

This website was fetched by machines 23,520 times in 30 days (as of August 2026). In the same period, there were at least **four** counted citations and **four** referrals.

That gap is the most honest sentence in this article. A clean discovery surface makes sure an assistant can find your facts correctly when it needs them. It does not make the assistant recommend you. That is decided by what you offer and what others say about you.

Anyone promising you otherwise is selling you a number they cannot prove.

## How to tell whether it works for you

Three checks you can run without tools. Open the text version of one of your most important pages and read it: is your offer there in full, or is half of it missing because it loads later? Ask an assistant about your business and check whether the facts it cites are correct. And look at whether your opening hours and address exist as annotated data — or only as running text.

If you find something that doesn't hold up, it is not a detail: a machine repeats a wrong value until it is corrected.

If you want to know what these four interfaces look like for your business, [talk to us](https://btlabs.dev/en/contact) — a short plain-talk conversation is enough for an honest assessment.

## Sources

- Jeremy Howard (Answer.AI), proposal for machine-readable website profiles, September 2024
- [Ahrefs, June 2026 analysis](https://ahrefs.com/blog/llmstxt-study/): 28% of domains had an llms.txt; 97% of those saw no request at all in May 2026
- Own measurement, btlabs.dev, 30-day window up to August 2026: 23,520 machine requests, 77% of them verified

Which of these interfaces you actually encounter on the open web is something we count: 37 routes are in the running measurement, and 5 of them returned not a single response across the entire panel. It is all in the [ai-discovery radar](https://btlabs.dev/en/ai-discovery-radar).

## Frequently asked questions.

**How does an AI read my website — and what does that mean for my content?**

An AI doesn't read your website top to bottom; it breaks it into individual text passages and, at the moment of the question, retrieves only the fitting ones ([Retrieval-Augmented Generation](https://btlabs.dev/en/glossary/rag-retrieval-augmented-generation) , RAG). What matters is therefore not the whole page, but whether individual passages answer a concrete question on their own and machine-readably. Content loaded only via script or buried in long prose often doesn't reach the AI.

**What does my business gain if AI assistants can talk directly to my website?**

Your details are ready exactly where people increasingly ask. Instead of an AI scraping your page and guessing, it reads exactly the content you've provided through an open interface — [MCP (Model Context Protocol)](https://btlabs.dev/en/glossary/mcp-model-context-protocol) : services, opening hours, contact details. The aim: fewer incorrect statements about your business and correctly sourced citations — whether an AI uses this route is up to its provider. You stay in control — you decide which content is accessible, and every access is logged.

**Do I absolutely need an llms.txt?**

It is not a Google ranking signal (Google says so itself) — but it takes minutes to create and is useful as orientation for AI agents. A cheap addition, not a miracle cure.

[How widespread it really is](https://btlabs.dev/en/posts/cloudflare-ai-training-radar-november-2026), we measure ourselves: as of November 2026, 14.8% of the domains probed in the 10,000-domain panel serve an llms.txt. The measurement is open in the [ai-discovery-radar](https://btlabs.dev/en/ai-discovery-radar).

Next step

## Want to look at it together?

No pitch, no standard package — an honest take on your project. A reply, usually within 24h.

[Start a conversation →](https://btlabs.dev/en/contact#cta)

## You might also like

- [· From SEO to GEO: the technical architecture of an AI-readable website · RAG, llms.txt, JSON-LD, TDM and MCP — how to build a website technically so that AI search engines can read and cite it correctly. With code, standards and lessons learned.](https://btlabs.dev/en/posts/from-seo-to-geo-architecture)
- [· What an AI agent finds on your website: a five-step self-check · Before an AI agent reads your pages, it checks a handful of agreed addresses. You can check five of them yourself with a browser in a few minutes — with what each one means and how common it is.](https://btlabs.dev/en/posts/ai-agent-website-self-check)
- [· The vocabulary machines share · Schema.org is not a format, it is a dictionary — a finite public list of things machines agreed to call by the same name. Invent a word and nobody reads it.](https://btlabs.dev/en/posts/schema-org-vocabulary-explained)

---
Source: https://btlabs.dev/en/posts/how-ai-agents-read-your-business
Languages: [de](https://btlabs.dev/llms/de/posts/wie-ki-agenten-deinen-betrieb-lesen) · [it](https://btlabs.dev/llms/it/posts/come-gli-agenti-ia-leggono-la-tua-azienda)
See also: [llms.txt](https://btlabs.dev/llms.txt) · [ai.txt (Policy)](https://btlabs.dev/ai.txt) · [identity.json](https://btlabs.dev/identity.json)
