Built to be read by machines, too.

minglabs.com serves every page in three forms: HTML for people, Markdown for language models, and JSON for programs. This page documents the machine-readable surface so developers and AI agents can consume it without guessing. Everything listed here is live; the counts are generated from the content at build time.

  • llms.txt Machine-readable site guide following the llms.txt convention: what MING Labs is, when to use it, and every indexable page with a one-line summary. Scoped deep index for the editorial layer at /insights/llms.txt.
  • Markdown twins Every content page has a Markdown twin: append .md to the URL, or request the page with the header Accept: text/markdown. Twins carry frontmatter (title, description, canonical, last-updated) and open with the page's H1. The homepage twin lives at /index.md.
  • JSON siblings Structured JSON for the Insights surface: /insights.json is the full inventory; every article, concept, and answer page has a sibling at the same URL with .json appended. Careers roles have JSON siblings too. Currently 14 Insights pages (4 articles, 4 concepts, 6 answers) and 2 roles.
  • AI briefing A curated Markdown briefing on MING Labs written for AI evaluation: positioning, frameworks, evidence, and contact paths in one document. Maintained by hand, byte-stable between content changes.
  • Sitemap with real change dates XML sitemap of every indexable URL. Content pages carry a lastmod taken from the page's own published dateModified; pages without a content date carry none. The build date is never used as a stand-in.
  • Crawler policy Explicit allowlist for search and AI assistant crawlers (GPTBot, ClaudeBot, PerplexityBot, Google-Extended and others) with content-signal preferences. Being read and cited by assistants is the point of this site.
  • Structured data Every page emits schema.org JSON-LD in the initial HTML: one canonical Organization entity, DefinedTerm pages for MING Labs' vocabulary (Agent Experience, Hybrid Organisation, the ABC Framework), Article and FAQPage where applicable.
  • Honest 404 Unknown paths return HTTP 404 with recovery links, and a Markdown body when requested with Accept: text/markdown. No soft redirects, no error pages pretending to be content.

Try it from a terminal

# The site guide, with a when-to-use section
curl https://www.minglabs.com/llms.txt

# Any page as Markdown, two equivalent ways
curl https://www.minglabs.com/about.md
curl -H "Accept: text/markdown" https://www.minglabs.com/about

# The Insights inventory as JSON, then one page's sibling
curl https://www.minglabs.com/insights.json
curl https://www.minglabs.com/insights/concepts/what-is-agent-experience.json

There is no separate API beyond these read-only surfaces, and no key or registration. If you are building something that needs more, talk to us.