Working now
What already works.
- LLMS TXT exists
- Markdown parity exists
- LLMS TXT is structured
Benchmark report
Docs benchmark report.
Report for
kitaru-site-preview-303.zenml-migration.workers.dev/docskitaru-site-preview-303.zenml-migration.workers.dev/docs
This report shows where agents can use these docs cleanly and where the biggest points of friction still are.
Benchmark score
97Grade Excellent
This report passes 15 of 17 checks, with 0 warnings, 2 failed checks, and 0 skipped checks still shaping the next score lift.
- Checks passed
- 15/17
- Warnings
- 0
- Failed checks
- 2
Key takeaways
What stands out first.
Start with what already works, then move to the fixes most likely to lift the score.
Improve next
What to improve next.
- List key constraints and requirements
Check results
Full score breakdown
Open each category to review the checks behind the score and see exactly where agents still hit friction.
Discovery and delivery3 passedCan an agent find the docs and fetch readable text?
Discovery and delivery
3 passed
Can an agent find the docs and fetch readable text?
This area is already easy for agents to work through.
LLMS TXT exists
Found llms.txt at https://kitaru-site-preview-303.zenml-migration.workers.dev/docs/llms.txt (19000 chars)
LLMS Full exists
Found llms-full.txt at https://kitaru-site-preview-303.zenml-migration.workers.dev/docs/llms-full.txt (618695 chars)
Markdown parity exists
5/5 sampled pages have valid .md versions. No llms.txt links found - checked common paths. Checked: ✓ https://kitaru-site-preview-303.zenml-migration.workers.dev/docs/quickstart.md, ✓ https://kitaru-site-preview-303.zenml-migration.workers.dev/docs/getting-started.md, ✓ https://kitaru-site-preview-303.zenml-migration.workers.dev/docs/guide.md, ✓ https://kitaru-site-preview-303.zenml-migration.workers.dev/docs/api.md, ✓ https://kitaru-site-preview-303.zenml-migration.workers.dev/docs/reference.md
Content structure4 passedCan an agent understand how the page is organized?
Content structure
4 passed
Can an agent understand how the page is organized?
This area is already easy for agents to work through.
LLMS TXT is structured
✓ Has H1 title; ✓ Has blockquote description; ✓ Has 4 H2 sections; ✓ Has list items with links
Links include descriptions
173/173 links have descriptions
Docs sections are structured
Found 5 recognized section types in H2 headings. Your sections: "getting started", "guides", "api reference", "optional"
Optional sections are separated
Has an ## Optional section - AI tools can skip this content when context window is limited
Task readiness3 passed2 failedCan an agent follow the instructions without guessing?
Task readiness
3 passed2 failed
Can an agent follow the instructions without guessing?
This area is still slowing agents down and needs attention.
Product description is clear
Blockquote description has 24 words
Constraints are documented
No constraints, requirements, or important notes found in opening
Integrations are documented
Found integration references: integration, connect, sdk
Error handling is documented
Found error/troubleshooting references: error, troubleshoot, problem
Examples are included
No code examples or example sections found
Access and recovery5 passedCan an agent complete the task without getting blocked?
Access and recovery
5 passed
Can an agent complete the task without getting blocked?
This area is already easy for agents to work through.
Markdown routes resolve
5/5 markdown pages return valid markdown content
Pages respond quickly
Average response time: 112ms across 7 requests
Content is readable without JS
Content is present in the initial HTML response (server-rendered)
Markdown negotiation works
3/3 pages return markdown when requested with Accept: text/markdown. Checked: ✓ https://kitaru-site-preview-303.zenml-migration.workers.dev/docs/quickstart, ✓ https://kitaru-site-preview-303.zenml-migration.workers.dev/docs/getting-started, ✓ https://kitaru-site-preview-303.zenml-migration.workers.dev/docs/guide
Markdown output stays clean
Markdown content is clean (no navigation, footer, or cookie elements)
Next steps
Get this report in your inbox or track the score over time.
Save the report to a work email now, or tell us what kind of ongoing monitoring would be useful for this docs site.
Built by DocsAlot
Need help improving the score?
DocsAlot helps teams improve help centers, developer docs, API docs, and CLI docs so they are easier for humans to use and easier for agents to read.