Skip to content
Is Agentic

weaviate.io

Ready with a few material gaps

84/ 100

Technical readiness score

What should the prompt cover?

8 findings · 5 selected

Failures (1)

Warnings (7)

How the score adds up

29 checks

The agent completed the observed task

One run shows how an agent performed, but it does not determine the technical score.

Task

What does weaviate.io do and who is it for? Explain it back to me.

22 steps2 reasoning steps8 searches

home
docs
docs
/enterprise
search
search
/case-studies/stack-ai
search
search
docs
search
search
search
docs
/platform
/product/query-agent
/product/embeddings
/comparison
/use-cases
search
1 observed runView journey ↗

Critical access needs attention

These checks describe whether an ordinary agent can enter, read, and operate the public site.

  • Agents can reach the site

    Crawler access, bot defenses, and explicit agent policy.

    3 / 3 passed

  • Core content is available

    Useful content remains accessible without a fragile browser-only path.

    0 / 1 passed

  • Navigation fails safely

    Redirects and missing pages give agents a recoverable path.

    1 / 2 passed

  • Controls are understandable

    Forms and interactive controls expose usable names and structure.

    2 / 2 passed

Advertised capabilities have material gaps

Optional surfaces appear only when the scan finds positive evidence that the site offers them.

Public website

Strong

90%

15 of 19 mature checks passed

API

Ready with gaps

76%

6 of 9 mature checks passed

MCP

Blocked

33%

0 of 1 mature checks passed

Fix these gaps first

Critical access gaps come first, followed by gaps in capabilities the site advertises.

  1. 01

    Agent-friendly 404s

    Return a real HTTP 404 (or 410) status for nonexistent paths - never a 200 with your app shell, which makes agents believe every path exists. For full credit, give the 404 response a short markdown body pointing agents at your sitemap, llms.txt, or docs index. Verify with `curl -s -o /dev/null -w "%{http_code}" https://yourdomain.com/some-path-that-does-not-exist` - it must print 404.

    Critical access
  2. 02

    Content without JavaScript

    Server-side render your homepage so AI crawlers see meaningful content without JavaScript. Ensure an H1 and 500+ chars of text in raw HTML.

    Critical access
  3. 03

    JSON error responses

    Return structured JSON error responses with error codes, messages, and resolution hints. Agents can't parse HTML error pages.

    Advertised capabilities
  4. 04

    MCP server / manifest

    Build an MCP (Model Context Protocol) server exposing your API as tools. Use Streamable HTTP transport for full score. This lets Claude, ChatGPT, and other AI agents call your product natively.

    Advertised capabilities
  5. 05

    Multi-language SDK packages

    Publish official SDK packages across multiple language ecosystems (npm, PyPI, Go modules, RubyGems). Auto-generate them from your OpenAPI spec using tools like openapi-generator. For each package set the project URL or homepage to your product domain (package.json `repository`/`homepage`, PyPI `Home-Page` or `project_urls`, RubyGems `homepage_uri`) - this is how agents verify the package is your official SDK.

    Advertised capabilities

Audit the checks behind the score

Applicable evidence is grouped by how it contributes to this preview model. Bonus checks appear only when they add points.

Essential5 of 8 passed · 61.7 / 80 points
  • Content without JavaScriptPartial (67%)
  • Not blocked by bot detectionPassed
  • robots.txt agent-user policyPassed
  • Redirect hygienePassed
  • OpenAPI spec publishedPassed
  • Agent crawler reachabilityPassed
  • JSON error responsesFailed
  • Agent-friendly 404sPartial (50%)
Recommended16 of 21 passed · 17.3 / 20 points
  • Developer resource discoverabilityPassed
  • Brand name discoverabilityPassed
  • robots.txt AI crawler policyPartial (50%)
  • Sitemap existsPassed
  • Content efficiencyPartial (50%)
  • Content crawl depth signalsPassed
  • JSON-LD structured dataPassed
  • Public API/docs linked from homepagePassed
  • Agent instruction / when-to-usePassed
  • Metadata completenessPassed
  • Organization schema completenessPassed
  • Trust anchor pagesPassed
  • Page token budgetPassed
  • Code fence validityPassed
  • Developer portalPassed
  • Public API with reachable endpointsPassed
  • MCP server / manifestPartial (33%)
  • CLI tool availablePassed
  • Multi-language SDK packagesPartial (33%)
  • API schema complexity analysisPartial (50%)
  • Function calling compatibilityPassed
Bonus signals22 positive · +5 points
  • ARD / ai-catalogPassed
  • ARD entry validityPassed
  • NPM/PyPI SDK packagePassed
  • Agent platform configsPassed
  • Listed on skills.shPassed
  • Agent discovery filePassed
  • pricing.md existsPartial (50%)
  • MCP well-known discoveryPassed
  • Markdown URL fallbackPartial (50%)
  • Modular llms.txt per product areaPassed
  • llms.txt existsPassed
  • llms.txt formattingPassed
  • Skills.sh skill qualityPartial (50%)
  • JSON-LD entity linking (sameAs)Passed
  • Schema type breadthPartial (50%)
  • llms.txt links resolvePassed
  • Markdown alternate linkPassed
  • Markdown frontmatter metadataPassed
  • Markdown agent docsPassed
  • Native interactive controlsPassed
  • Accessible names on controlsPassed
  • Accessibility-tree injection safety (bonus)Passed

Inspect the underlying audit

The complete Ora audit uses evidence from the scan on . After applying changes, run another scan from the homepage to refresh these recommendations.

Score alerts

A weekly report with ranking changes, new agent feedback, and score alerts for weaviate.io.

Source: Ora API

Snapshot 2026-08-19T18-33-00-855+00-00