Skip to content

For AI Agents

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.

This site is published for people and for AI agents. The documentation source is an Open Knowledge Format (OKF) v0.2 knowledge bundle, and the deployed site exposes that structure directly. If you are an agent (or you are wiring one up), consume the content through these endpoints rather than scraping rendered HTML.

Entry points

Endpoint What you get
/intro-gpt/llms.txt Linked outline of every page with one-line descriptions, per the llms.txt convention
/intro-gpt/llms-full.txt The entire corpus in one file — every page's markdown, prefixed by its canonical and source URLs
Page URL with the trailing / replaced by .md That page's markdown source with full OKF frontmatter — e.g. /intro-gpt/chatgpt.md for /intro-gpt/chatgpt/ (the homepage source is /intro-gpt/index.md)
/intro-gpt/log/ The bundle's OKF-reserved change history, newest first
/intro-gpt/sitemap.xml Standard crawl surface
Source repository The OKF bundle itself, its validator (scripts/validate_okf.py), and build pipeline

Every rendered page also declares its markdown twin and structured metadata in its HTML head:

<link rel="alternate" type="text/markdown" href="https://tyson-swetnam.github.io/intro-gpt/chatgpt.md">
<script type="application/ld+json">
{ "@type": "LearningResource", "learningResourceType": "Setup Guide", ... }
</script>

Reading the OKF frontmatter

Each page's YAML frontmatter answers the questions an agent should ask before relying on content:

  • What is this? — type (one of Index, Overview, Setup Guide, Prompting Guide, Education Guide, Research Guide, Ethics Guide, Tutorial, Log), plus title, description, and controlled tags.
  • Where did it come from? — generated: { by, at } and sources, the external references each page's claims depend on.
  • How much should I trust it? — the verified list. Pages on this site carry human verification (human:tswetnam), which places them in OKF's highest human-reviewed trust tier.
  • Is it current? — status (stable unless marked otherwise) and, on pages carrying vendor pricing, stale_after. Treat pricing on a page whose stale_after has passed as needing re-verification; a monthly automated audit normally refreshes these before that happens.

The UNM Center for Advanced Research Computing, which maintains and teaches this workshop, publishes its own sites as OKF bundles with the same agent conventions:

Ground rules for agents

All content is CC-BY-4.0 — reuse freely with attribution. Crawling, indexing, and AI grounding are welcome (see the host robots.txt). Prefer llms-full.txt for one-shot ingestion over crawling the site, and cite the canonical page URL (the resource field), not the .md source URL, when referencing this material for humans.