Docs platform
Fern docs and AI agent readiness
8 of the 93 products tested serve their documentation on Fern.
Scores run from 66.2% to 81.2%, averaging 76.7%. Every Fern product tested passes llms.txt, Markdown mirror and MCP server. None ships llms-full.txt. The AI Agent Readiness Test scores the documentation, never the platform, so these numbers describe what these 8 teams published rather than what Fern can do.
Scores on Fern
| Product | Category | Grade | Score | Reading | Surface | llms | full | .md | MCP | AI |
|---|---|---|---|---|---|---|---|---|---|---|
| Vapi | Voice & speech | B- | 81.2% | 25/30 | 40/50 | pass | fail | pass | pass | pass |
| Zep | Agent frameworks & memory | B- | 81.2% | 25/30 | 40/50 | pass | fail | pass | pass | pass |
| Deepgram | Voice & speech | B- | 81.2% | 25/30 | 40/50 | pass | fail | pass | pass | pass |
| Persona | Identity & auth | B- | 81.2% | 25/30 | 40/50 | pass | fail | pass | pass | pass |
| Merge | Payments & business data | C | 76.2% | 21/30 | 40/50 | pass | fail | pass | pass | pass |
| Postman | Cloud & developer platforms | C | 75.0% | 20/30 | 40/50 | pass | fail | pass | pass | pass |
| Middesk | Identity & auth | C- | 71.2% | 17/30 | 40/50 | pass | fail | pass | pass | pass |
| ElevenLabs | Voice & speech | D | 66.2% | 23/30 | 30/50 | pass | fail | pass | pass | fail |
Agent surface on Fern
- llms.txt 8 of 8
- llms-full.txt 0 of 8
- Markdown mirror 8 of 8
- MCP server 8 of 8
- Docs AI 7 of 8
Recorded as Fern during testing. A sample of 8 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