Thally
Product

Updated · 5 min read

Learn what AI-native documentation means, how it differs from AI-assisted writing, and how to test discovery, structure, freshness, and agent access.

By Published Updated

AI-native documentation is documentation published in machine-readable structures (JSON, JSON-LD, Markdown) alongside the human-readable page, from the same URL, with discovery files and live endpoints that let AI agents find, read, and cite it without scraping. It is not documentation written by AI. It is documentation that machines can read as reliably as people can.

Why the definition matters now

Many documentation requests now come through coding assistants, research agents, and answer engines. These systems resolve API questions, compare products, and decide which sources to cite without rendering your CSS.

Traditional HTML makes that audience do extra work. An agent has to strip navigation, locate the main content, reconstruct code blocks, and handle client-rendered pages. Each reconstruction step creates another opportunity to lose context.

AI-native documentation removes the guesswork by serving structure on request.

The three layers of AI-native docs

1. Structured output per page

The same URL that renders HTML for a person returns structured data for a machine, selected by an Accept header or a query parameter:

curl https://docs.example.com/quickstart \
  -H "Accept: application/json"

The response carries the page as data: title, description, section, body as both MDX and plain text, code blocks with languages, and provenance dates. JSON-LD gives answer engines the same content as schema.org markup, and Markdown serves agents that want prose.

2. Discovery files

Machines need a map. AI-native sites publish:

  • llms.txt: a concise, plain-markdown overview of the product with links to key pages
  • per-page manifests: metadata about formats, freshness, and structure
  • sitemap.xml and robots.txt that explicitly welcome AI crawlers

These files are inexpensive to generate and give crawlers a direct map to your primary documentation. Without them, an agent may find a secondary source before it finds your quickstart.

3. Live endpoints

The strongest form is an API the agent can call. With MCP (Model Context Protocol), a docs site exposes tools like search_docs, read_page, and list_pages. An agent attached to the endpoint queries your documentation the way your own search does, with no scraping and no stale index.

Thally ships all three layers on every deploy, self-hosted included; that is the design goal behind the platform. But the definition is bigger than any one product, and you can meet it with your own stack if you are willing to build and maintain the pieces.

What AI-native documentation is not

  • Not AI-generated content. Who wrote the words is orthogonal. AI-native describes how the published result is served.
  • Not a chatbot bolted onto docs. A chat widget helps humans on your site. It does nothing for the agent reading your docs from inside an IDE.
  • Not separate "AI pages." Serving different content to machines than to people is cloaking, and search engines penalize it. AI-native means the same content in more formats.

How to tell if your docs are AI-native

Run these five checks against your own site:

  1. Does curl -H "Accept: application/json" on a docs URL return structured data?
  2. Does /llms.txt exist and describe your product accurately?
  3. Can an agent list and read your pages through an API or MCP endpoint?
  4. Do pages carry machine-legible last-updated and last-verified dates?
  5. Does your robots.txt allow the AI crawlers you want citing you?

If you can answer yes to all five, your docs give agents a reliable path to the source. Each "no" identifies a point where an agent may have to infer structure or use an indirect source.

A deterministic version of this checklist is what Thally's agent-readiness score grades on every build, from 0 to 100, so CI can enforce it. You can start free and see your own score in minutes.

Primary references

This article follows the Thally editorial policy and was last reviewed July 19, 2026.

Published under the Thally editorial policy. Technical conformance is defined in the agent-readiness methodology.

Frequently asked questions

How is AI-native different from AI-assisted documentation?
AI-assisted means a model helps you write. AI-native means the published docs themselves are structured for machine readers: JSON, JSON-LD, and Markdown served next to the HTML, plus discovery files like llms.txt and an MCP endpoint.
Do I need AI-native docs if my readers are human?
Increasingly, yes. A growing share of documentation traffic is agents answering questions on a developer's behalf. If an agent cannot parse your docs, its answer cites someone else's.

Build docs that stay close to your product.

Create a managed site, or use the open-source engine to run Thally yourself.

Create your docs siteRead the docs

Keep reading