Cohere scores 90/100 (Grade A), placing it among the most AI-agent-ready documentation sites evaluated. It passes 15 of 22 checks (68%), demonstrating strong support for AI coding agents. 5 items require attention to reach a perfect score.
# Agent Score Fix Report — Cohere URL: https://docs.cohere.com Score: 90/100 (Grade A) I need help improving the AI-readiness of the documentation at https://docs.cohere.com. Agent Score found 3 failing checks and 2 warnings. ## Failing Checks (3) - [content-discoverability] Llms Txt Directive: No llms.txt directive found in any of 10 sampled pages - [observability] Llms Txt Freshness: llms.txt covers 118/221 sitemap doc pages (53%); 103 missing - [observability] Markdown Content Parity: 4 of 10 pages have substantive content differences between markdown and HTML (avg 19% missing) ## Warnings (2) - [content-discoverability] Llms Txt Valid: llms.txt contains parseable links but doesn't fully follow the proposed structure: https://docs.cohere.com/llms.txt: No H1 heading found, No blockquote summary found, No heading-delimited sections found; https://docs.cohere.com/docs/llms.txt: No blockquote summary found - [page-size] Content Start Position: 1 of 10 sampled pages have content starting at 10–50% (worst 12%) ## Fix Instructions For each issue above, please: 1. Analyze the documentation site at https://docs.cohere.com 2. Implement the specific fix 3. Verify the fix would cause the check to pass ### Common fixes: - **No llms.txt**: Create /llms.txt following https://llmstxt.org — list all doc pages in markdown format - **No .md URL support**: Configure your docs platform to serve pages at equivalent .md URLs (e.g. /docs/quickstart.md) - **No content negotiation**: Return markdown when request includes Accept: text/markdown header - **Large page size**: Reduce nav boilerplate, inline scripts, and repetitive markup - **No sitemap**: Generate /sitemap.xml listing all documentation URLs - **Auth walls**: Ensure docs pages return 200 without requiring login cookies or tokens - **No Last-Modified header**: Configure your server/CDN to include Last-Modified response headers - **Tab content hidden**: Ensure tabbed content is rendered in the HTML (not JS-only) so agents can read all variants ## Run afdocs Locally for More Detail To get deeper visibility into what's failing, run afdocs against your docs: npx afdocs https://docs.cohere.com --fixes --verbose - **--fixes**: Adds "Fix:" lines to the output for each warn/fail check with actionable remediation steps - **-v, --verbose**: Shows per-page details (specific URLs, character counts, error codes) for checks with issues — useful for per-URL visibility into what's failing
CHECK RESULTS
How your docs scored
llms-txt-freshnessllms.txt covers 118/221 sitemap doc pages (53%); 103 missing
markdown-content-parity4 of 10 pages have substantive content differences between markdown and HTML (avg 19% missing)
cache-header-hygieneAll 12 endpoints have appropriate cache headers
auth-gate-detectionAll 10 sampled pages are publicly accessible
auth-alternative-accessAll docs pages are publicly accessible; no alternative access paths needed
tabbed-content-serialization3 tab group(s) across 1 of 10 sampled pages; all serialize under 50K chars
markdown-code-fence-validityAll 31 code fences properly closed across 12 pages
section-header-quality1 page(s) with tabs found, but no section headers inside tab panels to evaluate
llms-txt-directiveNo llms.txt directive found in any of 10 sampled pages
llms-txt-validllms.txt contains parseable links but doesn't fully follow the proposed structure: https://docs.cohere.com/llms.txt: No H1 heading found, No blockquote summary found, No heading-delimited sections found; https://docs.cohere.com/docs/llms.txt: No blockquote summary found
llms-txt-existsllms.txt found at 2 location(s)
llms-txt-sizellms.txt is 23,921 characters (under 50,000 threshold)
llms-txt-links-resolveAll 10 same-origin sampled links resolve (120 total links)
llms-txt-links-markdown10/10 same-origin sampled links point to markdown content (100%)
content-start-position1 of 10 sampled pages have content starting at 10–50% (worst 12%)
rendering-strategyAll 10 sampled pages contain server-rendered content
page-size-markdownAll 10 pages under 50K chars (median 5K, max 23K)
page-size-htmlAll 10 sampled pages convert under 50K chars (median 5K, 0% boilerplate)
markdown-url-support10/10 sampled pages support .md URLs (100%)
content-negotiation10/10 sampled pages support content negotiation (100%)
http-status-codesAll 10 sampled pages return proper error codes for bad URLs
redirect-behaviorNo redirects detected across 10 sampled pages
