Vapi
Last scanned docs.vapi.aiFern15 pages tested
AI agents can find, read and use these docs well. Vapi scores 96 out of 100 (grade A), passing 21 of 27 checks. 6 still need work.
Developer docs
Kind of site
21/27
Checks passed
4
Partly passed
2
Failed
Access
Content discoverability4 passed3 partly
llms.txt follows the standard structure
llms.txt contains parseable links but doesn't fully follow the proposed structure: https://docs.vapi.ai/llms.txt: No blockquote summary found
Your llms.txt contains parseable links but doesn't follow the standard structure. Add an H1 title as the first line and a blockquote summary (lines starting with >) to improve agent parsing.
Check your fix: llms.txt starts with a
# Title, then a> summaryline, then##sections of links.llms.txt fits in an agent's context
llms.txt is 87,222 characters (between 50,000 and 100,000; consider splitting)
Your llms.txt is 87,222 characters, which may be truncated on some agent platforms. If it grows further, split into nested llms.txt files with a root index under 50,000 characters.
Check your fix:
curl -s https://docs.vapi.ai/llms.txt | wc -cprints less than 50000.Markdown pages point agents to llms.txt
llms.txt directive found in markdown of 14 of 15 sampled pages (1 missing)
An llms.txt directive was found in the markdown of some pages but is missing from others, or is buried deep in the page. Ensure the directive appears near the top of every markdown page.
Check your fix: The Markdown version of https://docs.vapi.ai/advanced/sip (its .md URL, or the page fetched with
Accept: text/markdown) has the llms.txt line in its first few lines.llms.txt exists
llms.txt found at 2 locations; using https://docs.vapi.ai/llms.txt as canonical
llms.txt links work
All 15 same-origin sampled links resolve (452 total links)
llms.txt links point to Markdown
14/15 same-origin sampled links point to markdown content (93%)
Pages point agents to llms.txt
llms.txt directive found in HTML of all 15 sampled pages, near the top of content
Markdown availability2 passed
Pages are available as Markdown
15/15 sampled pages support .md URLs (100%)
Server returns Markdown when asked
15/15 sampled pages support content negotiation (100%)
Page size and truncation2 passed2 failed
Markdown pages fit in context
1 of 15 pages exceed 100K chars (max 683K)
1 of 15 markdown pages exceed 100K characters and will be truncated by agents. Break these into smaller pages or restructure serialized tabbed content.
HTML pages fit in context
1 of 15 sampled pages convert to over 100K chars (max 6761K HTML → 148K markdown (93% boilerplate))
1 of 15 pages convert to over 100K characters of markdown. Break large pages into smaller units, reduce navigation boilerplate, or provide markdown versions that bypass the HTML conversion overhead.
Content is in the HTML without JavaScript
All 15 sampled pages contain server-rendered content
Content starts near the top
Content starts within first 10% on all 15 sampled pages (median 0%)
Content structure3 passed
Tabs don't bloat the page
No tabbed content detected across 15 sampled pages
Headings inside tabs name their variant
No tabbed content found; header quality check not applicable
Code blocks are well-formed
All 41 code fences properly closed across 17 pages
URL stability2 passed
Missing pages return a real 404
All 15 sampled pages return proper error codes for bad URLs
Redirects stay on the same host
No redirects detected across 15 sampled pages
Content health2 passed1 partly
Markdown matches the HTML page
2 of 15 pages have minor content differences between markdown and HTML
2 pages have minor content differences between their markdown and HTML versions.
llms.txt covers the whole site
llms.txt covers 100% of 629 sitemap doc pages; 2 llms.txt links not in sitemap (may indicate stale links or incomplete sitemap)
Cache headers allow timely updates
All 17 endpoints have appropriate cache headers
Authentication and access1 passed
Gated docs offer another way in
All docs pages are publicly accessible; no alternative access paths needed
Docs are readable without logging in
All 15 sampled pages are publicly accessible
Crawler access2 passed
Crawlers and AI assistants may read the docs
robots.txt lets Googlebot, Bingbot, OAI-SearchBot, PerplexityBot, Claude-SearchBot and Claude-User read the docs.
Sitemap lists the docs pages
The sitemap at https://docs.vapi.ai/sitemap.xml lists 453 of the 454 docs pages found through llms.txt and page links.
Freshness
Maintenance3 passed
Pages say when they were last changed
15 of 15 sampled pages state when they were last changed.
Links and section anchors work
All 39 links and 15 section anchors checked on the sampled pages work. 2 more could not be verified (timeouts or blocked requests) and are not counted.
Sitemap entries still exist
All 10 sitemap entries sampled still exist.
Consistency with the API specNot applicable
Endpoints in the docs exist in the API spec
No OpenAPI description was found, so the docs could not be compared with a spec.
CurrencyNot applicable
Deprecated operations are marked as such
No OpenAPI description was found, so deprecation notices could not be compared with a spec.
Additional checks
Not part of the score: optional extras that help agents use your docs.
MCP server is discoverable
No MCP server was found for these docs.
Offer a read-only MCP server with a search tool over your docs, and link it from llms.txt, so agents in Cursor, Claude and ChatGPT can query your docs directly.
llms-full.txt is available
llms-full.txt found at https://docs.vapi.ai/llms.txt (87,222 characters).
Agent skills are published
No agent skills index was found at /.well-known/agent-skills/index.json.
Publish an Agent Skills index at /.well-known/agent-skills/index.json with a SKILL.md for your main tasks, so agents can load task instructions without reading every page.
About this scan
- Scanned
- Oct 21, 2026
- Pages tested
- 15 of 632 found
- Platform
- Fern
- Kind of site
- Developer docs
- AFDocs score, on its own
- 95 (A), 16 of 23 checks pass
- Based on 15 sampled pages, chosen deterministically from the sitemap and llms.txt. Pages outside the sample were not read.
- Pages were fetched without running JavaScript, the way most AI agents read the web.
- robots.txt stopped the scanner from reading 1 URL; checks that needed them are unverified.
- Answerability, where an AI agent answers real questions written from these pages, runs in the open-source scanner with your own API key. This web score is made of Access and Freshness.
Methodology 2026-09.6 · AFDocs 0.20.0
Pages we sampled (15)
- https://docs.vapi.ai/advanced/sip
- https://docs.vapi.ai/api-reference/campaigns/campaign-controller-find-all-v-2
- https://docs.vapi.ai/api-reference/observability-scorecard/scorecard-controller-get
- https://docs.vapi.ai/api-reference/simulation-suites/simulation-suite-controller-update
- https://docs.vapi.ai/assistants/examples/support-escalation
- https://docs.vapi.ai/chat/non-streaming
- https://docs.vapi.ai/free-telephony
- https://docs.vapi.ai/outbound-campaigns/voicemail-and-call-screening
- https://docs.vapi.ai/providers/transcriber/openai
- https://docs.vapi.ai/security-and-privacy/soc
- https://docs.vapi.ai/tools/custom-tools
- https://docs.vapi.ai/whats-new/2024/11/14
- https://docs.vapi.ai/whats-new/2025/3/19
- https://docs.vapi.ai/whats-new/2025/5/26
- https://docs.vapi.ai/whats-new/2025/8/29
Show your score
Add the badge to your docs or README. It updates each time the site is scanned.
Markdown
[](https://documentation.ai/agent-score/vapi)HTML
<a href="https://documentation.ai/agent-score/vapi"><img src="https://documentation.ai/agent-score/badge/vapi.svg" alt="Agent Readiness Score: 96 (A)" height="20"></a>Agent-ready docs by default
Live in under 5 min · No credit card required