Using AI Agents with Printago Docs

These docs ship a few machine-readable artifacts so an AI agent (Claude, ChatGPT, a custom LangChain/OpenAI tool-use loop, etc.) can understand the product and navigate the documentation efficiently instead of crawling page-by-page.

What's Available

File	URL	What it's for
llms.txt	docs.printago.io/llms.txt	Single-fetch index of every doc page with a one-line description, following the llms.txt convention. Start here.
docs_map.md	docs.printago.io/docs_map.md	Hierarchical map of every page with all its section headings. Fetch this when the agent needs to decide which pages to read.
sitemap.xml	docs.printago.io/sitemap.xml	Standard sitemap listing every page URL.
OpenAPI spec	docs.printago.io/printago-api-swagger.json	OpenAPI 3.1 spec for the REST API. Feed this to an agent that needs to call Printago endpoints.
Developers site	developers.printago.io	Interactive API reference and guides.

All of these are plain text or JSON, live at stable URLs, and are regenerated whenever the docs are rebuilt.

Recommended Workflow

For an agent answering questions about Printago:

1. Fetch /llms.txt — gives the agent the full list of pages and what each one covers in under a few KB.
2. Fetch /docs_map.md if needed — when the one-line descriptions aren't enough to pick a page, the map shows every heading inside every page.
3. Fetch the specific page URLs from docs.printago.io/docs/… for full content. Most agents with a web-fetch tool will convert the rendered HTML to markdown automatically.

For an agent integrating with the Printago API:

1. Fetch /printago-api-swagger.json for the endpoint shapes.
2. Reference Authentication & Quotas for the authorization and x-printago-storeid headers.
3. See API Examples for copy-pasteable patterns.

Pointing Claude Code at the Docs

If you're using Claude Code to build on top of Printago, drop a line like this into your project's CLAUDE.md:

For Printago documentation, fetch https://docs.printago.io/llms.txt first.
Follow up with https://docs.printago.io/docs_map.md or specific pages from
https://docs.printago.io/docs/* as needed. The OpenAPI spec lives at
https://docs.printago.io/printago-api-swagger.json.

Pointing a Custom Agent at the Docs

Any agent with a web-fetch tool can use the files directly. A minimal Claude API example:

import anthropic

client = anthropic.Anthropic()

response = client.messages.create(
    model="claude-opus-4-6",
    max_tokens=1024,
    tools=[{"type": "web_search_20250305", "name": "web_search"}],
    messages=[{
        "role": "user",
        "content": (
            "Using https://docs.printago.io/llms.txt as your starting point, "
            "explain how SKU variants map onto OpenSCAD parameters in Printago."
        ),
    }],
)

The same pattern works with any model that supports web fetching or tool use — give it the llms.txt URL and let it pull in whichever pages it needs.

Freshness

Both llms.txt and docs_map.md are regenerated on every docs build from the same source sidebar and markdown that produce this site, so they won't drift out of sync.

Feedback

If you're building something on top of Printago and want different discovery formats (e.g. llms-full.txt with the entire corpus inlined, per-section indexes, embeddings), let us know in Discord.