Page Deep Audit (Vision + AI Render)

Page Deep Audit is the deepest analysis Rankion runs on a single URL. Instead of content signals like Content Audit (Site Crawl), Page Deep Audit looks at the landing page as a visual product: a desktop screenshot, Lighthouse metrics for mobile and desktop, a multimodal AI analysis on layout, trust, CTA, persona fit and critical issues, plus an optional gpt-image-2 render that shows what the optimal desktop variant could look like. This is the tool for CRO and landing-page iteration, not for SEO bulk work.

What it can do

• Source screenshot: the page as it looks on desktop.
• Lighthouse for mobile and desktop: Performance, SEO, Accessibility and Best Practices, measured per strategy by Google PageSpeed Insights. The card names the source and the time of measurement; each category has a short explanation. A missing value means "not measured" (for example when the quota is used up) and is shown as a dash, never as 0.
• AI vision analysis: user_intent, persona_fit, trust_score, layout_score, cta_score, problem_solution_clarity, above_the_fold_quality, mobile_friendliness_visual.
• Personas + pain points: derived from the visual, not from assumptions.
• Critical issues: prioritized by severity (high / medium / low) with evidence snippet.
• Improvement suggestions: per area (headline, cta, trust, layout, copy, visuals, forms, navigation, seo, accessibility) with a before/after example.
• AI render (desktop): gpt-image-2 generates the ideal desktop version as a visual reference.
• Headline rewrite: a ready-to-paste H1 drop-in suggestion.
• Check again: one click on the detail page starts a new audit of the same URL; the previous one is kept for comparison.

When to use

• You want to CRO-audit a landing page before pouring money into ads.
• You want to give a designer an objective visual reference ("this is how it should look").
• You're iterating a variant: audit, adjust, "Check again", compare the scores of both runs.
• You need persona-driven copy suggestions based on the real page, not on briefing theory.

Workflow

1. Start audit: POST /page-audit with {url, tracking_project_id?, persona?}. Returns 202 + {id, status:"pending", url}.
2. Poll until completed: main flow about 1–3 minutes (scraping → screenshotting → analyzing → completed). The AI render then runs for up to 9 minutes in a separate background job.
3. Read reports: GET /page-audit/{id} returns 2 image URLs (desktop screenshot and desktop AI render), the analysis block with scores, personas, issues, suggestions and headline rewrite, and lighthouse (the flat fields are mobile, lighthouse.strategies.desktop is desktop).
4. Iterate: apply suggestions in priority order, deploy the page, then "Check again" on the detail page or POST /page-audit/{id}/refresh. The new audit takes over URL, project and persona; the old one stays.

Polling example:

ID=$(curl -s -X POST $BASE/page-audit \
  -H "Authorization: Bearer $TOKEN" -H "Content-Type: application/json" \
  -d '{"url":"https://example.com/landing"}' | jq -r '.id')

while true; do
  R=$(curl -s -H "Authorization: Bearer $TOKEN" $BASE/page-audit/$ID)
  STATUS=$(echo "$R" | jq -r '.status')
  IDEAL=$(echo "$R" | jq -r '.ideal_screenshot_url // "null"')
  [ "$STATUS" = completed ] && [ "$IDEAL" != null ] && break
  sleep 30
done

API

Pipeline status: pending → scraping → screenshotting → analyzing → completed. The desktop AI-render field (ideal_screenshot_url) populates after completed.

Credits & Limits

• Main audit: 30 credits, also for "Check again".
• Desktop AI render: 15 credits.
• Full audit with desktop render: 45 credits per run.
• Async: main flow about 1–3 min, render up to 9 min after that.
• Not enough credits: 402 with the required amount; on the detail page the message appears right at the button, with a link to buy credits.
• url is required and capped at 500 characters; 422 on validation fail.
• Cross-team and cross-project access returns 403.

Related modules

• Content Audit: site-wide inventory instead of single deep audit.
• Content Optimizer: optimize the content layer; Page Deep Audit targets visual + UX.
• AI Content Editor: apply the headline rewrite suggestion directly in the editor.