Docs platform
GitBook docs and AI agent readiness
4 of the 97 products tested serve their documentation on GitBook.
Scores run from 76.2% to 95.0%, averaging 86.9%. Every GitBook product tested passes llms.txt, llms-full.txt, Markdown mirror and Docs AI. The AI Agent Readiness Test scores the documentation, never the platform, so these numbers describe what these 4 teams published rather than what GitBook can do.
Scores on GitBook
| Product | Category | Grade | Score | Reading | Surface | llms | full | .md | MCP | AI |
|---|---|---|---|---|---|---|---|---|---|---|
| Felt | Geospatial & maps | A | 95.0% | 26/30 | 50/50 | pass | pass | pass | pass | pass |
| n8n | Workflows & automation | A | 93.8% | 25/30 | 50/50 | pass | pass | pass | pass | pass |
| CARTO | Geospatial & maps | B- | 82.5% | 16/30 | 50/50 | pass | pass | pass | pass | pass |
| Roboflow | AI models & inference | C | 76.2% | 21/30 | 40/50 | pass | pass | pass | fail | pass |
Agent surface on GitBook
- llms.txt 4 of 4
- llms-full.txt 4 of 4
- Markdown mirror 4 of 4
- MCP server 3 of 4
- Docs AI 4 of 4
Recorded as GitBook during testing. A sample of 4 shows what these teams shipped and does not establish a platform default.
All docs platforms · Every score in one table
Put another docs site through the battery.
Nominate a docs site