Loading pattern preview
BlocksTools & Utilities
Jev AEO Audit
Jev AEO Audit
Paste a URL. Firecrawl fetches the page, then Jev scores whether the answer block is worth citing.
Use this when auditing a page for AEO and you want title, canonical, and noindex checks in code while Jev judges the citation-worthiness.
Loading pattern preview
Problems solved
Technical challenges this implementation handles out of the box.
- Score a fetched page for answer-engine citation
- Keep title, canonical, and noindex checks in application code
- Queue only the checks that missed their floors
Use cases
Products and workflows this pattern is designed to support.
- Citation checks on a single URL
- Separating deterministic SEO facts from model judgments
- Teaching a multi-question Jev audit
Compare with
Similar patterns, and when each one is the better fit.
SEO AuditUse this when a marketing team needs exportable SEO scorecards that check title, meta description, and Open Graph tags and list top fixes for a page.
Jev Output VerifierUse this when you want your own code to hold the confidence floor a draft answer must clear before display, with at most one retry on a miss.
Jev + Web ContextUse this when you want leave-one-out weights showing which retrieved web source changed a typed Jev decision, with no chat UI involved.
Jev Composite ScorecardUse this when one blended rubric hides which factor failed and you want atomic Jev scores merged into a single weighted score in your app.
Setup
Requirements, wiring steps, and what this pattern adds to your project.
Getting started
Pick how you want to pull this pattern in. Then wire env vars and routes the same way.
- 1
Download → Next.js app
Use Download → Next.js app in the preview toolbar. You get a zip scaffold (Pro downloads rewrite preview `/view/.../api/*` paths to `/api/*` automatically).
- 2
Extract the zip and install dependencies
Unzip the archive, then run `pnpm install` (or npm / yarn) in the project folder.
- 3
Fill .env.local
The download includes .env.local placeholders when needed. Add real values for: AI_GATEWAY_API_KEY, FIRECRAWL_API_KEY.
- 4
Customize the agent and tool files
Adapt prompts, tools, and stop conditions in the generated project for your product.
- 5
Run the app and open the pattern route
Run `pnpm dev`, open the setup/checklist page if present, then navigate to the generated pattern route and verify responses.
Environment variables
Capabilities
AI SDK APIs
experimental_evaluateProviders
Jev
External services
gatewayvercel-ai-gatewayFirecrawlUpstash
Files added
17 files
app/page.tsxapp/layout.tsxapp/api/audit/route.tscomponents/aeo-audit-demo.tsxcomponents/typesafe-ai.tsxcomponents/probability-bar.tsxcomponents/score-track.tsxcomponents/cite-result.tsxhooks/use-aeo-audit.tslib/audit-policy.tslib/audit-questions.tslib/extract-page.tslib/scrape-page.tslib/rate-limit.tslib/request-utils.tslib/cite-brief.tsREADME.md
Dependencies
8 total
npm packages
6@mendable/firecrawl-jsUpstashAISDKlucide-reactNext.jsReact
Registry components
buttoninput
Critical files
4 files
lib/audit-policy.tsdecideAudit returns cite-ready only when extractable and evidenced are >= 0.90, stuffed and thin are <= 0.10, query fit is >= 2, and intent probability is >= 0.70 with confidence present. Missing scores or ambiguous intent go to review. Failed checks go to queue. Unit-test with Experimental_EvaluationMockModelV4 — do not call Jev or Firecrawl from tests.
lib/audit-questions.tsSix atomic questions on { query, title, metaDescription, h1, passage, jsonLd }: extractable, evidenced, stuffed, thin (boolean), queryFit (score), intent (choice). Floors live next to the questions.
lib/extract-page.tsextractAuditPage pulls a short passage and JSON-LD plus title, meta, H1, canonical, and noindex. Those facts stay in application code and are not Jev questions.
audit/route.tsRate-limited Firecrawl scrape, then experimental_evaluate through AI Gateway model typesafe-ai/jev. zeroDataRetention is on. Reject private hosts before scraping.
Requirements
- Complexity
- Beginner
- Setup time
- ~5 minutes
- Node
- 24+
- Memory
- 256MB
Upstash Redis for deployed demo rate limiting
