Pylon scores 95/100 (Grade A), placing it among the most AI-agent-ready documentation sites evaluated. It passes 16 of 23 checks (70%), demonstrating strong support for AI coding agents. 6 items require attention to reach a perfect score.
# Agent Score Fix Report — Pylon URL: https://docs.usepylon.com Score: 95/100 (Grade A) I need help improving the AI-readiness of the documentation at https://docs.usepylon.com. Agent Score found 3 failing checks and 3 warnings. ## Failing Checks (3) - [page-size] Page Size Markdown: 1 of 10 pages exceed 100K chars (max 109K) - [page-size] Content Start Position: 7 of 10 sampled pages have content starting past 50% (worst 86%) - [observability] Markdown Content Parity: 3 of 10 pages have substantive content differences between markdown and HTML (avg 20% missing) ## Warnings (3) - [content-discoverability] Llms Txt Valid: llms.txt contains parseable links but doesn't fully follow the proposed structure: https://docs.usepylon.com/llms.txt: No blockquote summary found - [content-discoverability] Llms Txt Directive Html: llms.txt directive found in HTML of 10 of 10 sampled pages, but buried deep in the page (past 50%) - [page-size] Page Size Html: 1 of 10 sampled pages convert to 50K–100K chars (max 1712K HTML → 54K markdown (98% boilerplate)) ## Fix Instructions For each issue above, please: 1. Analyze the documentation site at https://docs.usepylon.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 check https://docs.usepylon.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
page-size-html1 of 10 sampled pages convert to 50K–100K chars (max 1712K HTML → 54K markdown (98% boilerplate))Learn more
auth-alternative-accessAll docs pages are publicly accessible; no alternative access paths neededLearn more
markdown-content-parity3 of 10 pages have substantive content differences between markdown and HTML (avg 20% missing)Learn more
llms-txt-coveragellms.txt covers 99% of 196 sitemap doc pages; 2 llms.txt links not in sitemap (may indicate stale links or incomplete sitemap)Learn more
llms-txt-validllms.txt contains parseable links but doesn't fully follow the proposed structure: https://docs.usepylon.com/llms.txt: No blockquote summary foundLearn more
llms-txt-directive-htmlllms.txt directive found in HTML of 10 of 10 sampled pages, but buried deep in the page (past 50%)Learn more
llms-txt-directive-mdllms.txt directive found in markdown of all 10 sampled pages, near the top of contentLearn more
