AI Score
Jamdesk scores how well AI agents can read your docs against the open AFDocs standard on every build. See your grade, fix issues, and track it over time.
AI assistants answer questions about your product from your documentation. They can only do that when they can read it. AI Score measures how well they can. Jamdesk scans your published site after every build against the open AFDocs agent-readiness standard. You get a 0-100 score, a letter grade, and a per-issue breakdown.
Try it on any site first. The free AI Score tool grades any documentation URL against the same standard. The AI Score Chrome extension grades sites as you browse. Inside Jamdesk, the score runs automatically on your docs.
How scoring works
AI Score runs automatically, with no setup. Jamdesk waits for each successful build to go live. Then it scans your published docs and records the result.
- Runs on every build: each deploy re-scores your site. A regression shows up the moment it ships.
- 0-100 score and a letter grade (A+ down to F), measured against the open AFDocs standard. It's the same engine as the free public tool.
- Re-run any time: open your project's AI Score page and click Run score now. It scores the live site again without waiting for a build.
Find it in the dashboard under your project → AI Score.
Read your score
The AI Score page has three parts:
- Score donut: your current score and grade, plus the change since your last build.
- Trend line: your score across recent builds. A drop shows up at a glance.
- Category cards: your checks grouped into seven areas, with a grade per area. Expand one to see its checks and whether they passed, warned, or failed.
A footer notes what was scanned, how many pages were sampled, and the AFDocs spec version.
What the score measures
Each category groups related agent-readiness checks:
| Category | What it covers |
|---|---|
| Content Discoverability | llms.txt and the signals that point agents at your content |
| Markdown Availability | A clean Markdown version of every page for agents to read |
| Page Size & Truncation Risk | Pages small enough to fit an agent's context window |
| Content Structure | Headings, ordering, and content that starts early on the page |
| URL Stability & Redirects | Stable URLs and proper same-host redirects |
| Observability & Content Health | Status codes, caching, and parity between what readers and agents see |
| Authentication & Access | Whether pages are reachable by agents at all |
Fix issues
Every check that warns or fails has a plain-language explanation. Its fix is written in terms of your MDX and docs.json. Findings come in two kinds:
- Things you fix in your content: for example, a page whose content starts too far down, an oversized page to split, or content rendered by an interactive component that doesn't appear in the page's Markdown. The fix text names the next step and the pages it applies to.
- Things Jamdesk does for you: Jamdesk generates
llms.txt, Markdown export, status codes, and caching. A failure here usually means a transient build issue. Re-run the score after your next build. Contact support if it persists.
Copy the fix prompt
Each fixable check has a Copy prompt to fix button. It copies a prompt that names the check, the finding, and the fix in your MDX or docs.json. Paste it into an AI coding agent (Claude Code, the Jamdesk Claude plugin, Cursor, or Codex) to make the edit. Push to rebuild and re-score.
Get emailed when your score changes
Jamdesk emails your project members the new score and the most important issue to fix. It sends the email when a build produces your first score, moves your score by 3 or more points, or brings you back up to 100.
- Toggle it per project: the Email team when score changes switch sits at the top of the AI Score page. It's on by default.
- Small changes stay quiet: a one- or two-point move doesn't send an email. Jamdesk compares each new score against the last one it emailed you about. Gradual drift adds up. You get an email when the total change reaches 3 points.
Manual re-runs and build-triggered scores can send the email. Backfilled and public-tool scans never do.
Troubleshooting
A scan comes back empty when your site was briefly unreachable, returned an error, or blocked the scanner. Jamdesk does not save these results. A transient blip won't pin a wrong score or dent your trend line. Your last good score stays on the page. Click Run score now to try again.
AI agents can't read pages behind a password. The score reflects that. A low score is expected when the gate is intentional, as with internal or pre-release docs.
A noindex project has no sitemap for Jamdesk to scan. Jamdesk skips AI Score for it. AI agents can still read your docs through llms.txt. It stays published regardless of noindex. Remove noindex from seo.metatags.robots in docs.json to get a score again.
Some checks cover platform behavior Jamdesk owns (llms.txt, Markdown export, status codes, caching). These pass by design. A failure almost always means a transient build issue. Re-run the score after your next build. Contact support if it persists.