Cerebras Inference scores 96/100 (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 — Cerebras Inference URL: https://inference-docs.cerebras.ai Score: 96/100 (Grade A) I need help improving the AI-readiness of the documentation at https://inference-docs.cerebras.ai. Agent Score found 2 failing checks and 3 warnings. ## Failing Checks (2) - [page-size] Page Size Html: 1 of 10 sampled pages convert to over 100K chars (max 194K, 3% boilerplate) - [observability] Markdown Content Parity: 2 of 9 pages have substantive content differences between markdown and HTML (avg 10% missing) ## Warnings (3) - [content-discoverability] Llms Txt Valid: llms.txt contains parseable links but doesn't fully follow the proposed structure: https://inference-docs.cerebras.ai/llms.txt: No blockquote summary found - [content-discoverability] Llms Txt Directive: llms.txt directive found in 9 of 10 sampled pages (1 missing) - [url-stability] Redirect Behavior: 1 of 10 sampled pages use cross-host redirects ## Fix Instructions For each issue above, please: 1. Analyze the documentation site at https://inference-docs.cerebras.ai 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://inference-docs.cerebras.ai --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
auth-gate-detectionAll 10 sampled pages are publicly accessible
auth-alternative-accessAll docs pages are publicly accessible; no alternative access paths needed
tabbed-content-serialization1 tab group(s) across 1 of 10 sampled pages; all serialize under 50K chars
markdown-code-fence-validityAll 24 code fences properly closed across 10 pages
section-header-quality1 page(s) with tabs found, but no section headers inside tab panels to evaluate
markdown-content-parity2 of 9 pages have substantive content differences between markdown and HTML (avg 10% missing)
llms-txt-freshnessllms.txt covers 100% of 72 sitemap doc pages; 6 llms.txt links not in sitemap (may indicate stale links or incomplete sitemap)
cache-header-hygieneAll 11 endpoints have appropriate cache headers
page-size-html1 of 10 sampled pages convert to over 100K chars (max 194K, 3% boilerplate)
rendering-strategyAll 10 sampled pages contain server-rendered content
page-size-markdownAll 9 pages under 50K chars (median 8K, max 16K)
content-start-positionContent starts within first 10% on all 10 sampled pages (median 0%)
redirect-behavior1 of 10 sampled pages use cross-host redirects
http-status-codesAll 10 sampled pages return proper error codes for bad URLs
llms-txt-validllms.txt contains parseable links but doesn't fully follow the proposed structure: https://inference-docs.cerebras.ai/llms.txt: No blockquote summary found
llms-txt-directivellms.txt directive found in 9 of 10 sampled pages (1 missing)
llms-txt-existsllms.txt found at 1 location(s)
llms-txt-sizellms.txt is 13,012 characters (under 50,000 threshold)
llms-txt-links-resolveAll 10 same-origin sampled links resolve (80 total links)
llms-txt-links-markdown10/10 same-origin sampled links point to markdown content (100%) (2 external links excluded)
markdown-url-support9/10 sampled pages support .md URLs (90%)
content-negotiation9/10 sampled pages support content negotiation (90%)
