Audit websites for SEO issues with a browsing agent
Web page · https://agentusecases.ai/use-case/audit-websites-for-seo-issues-with-a-browsing-agent
Done with Claude. An open-source agent visits each URL in a real Chromium browser, extracts SEO tags, checks broken links, pauses for human login input, and writes a summary report.
First seen by Oriel on .
AI summary
An open-source Python agent audits URLs in Chromium, uses Claude to extract SEO metadata, checks broken links, handles login interruptions, and produces resumable reports.
- Users provide URLs through input.csv, while Browser Use opens each page and httpx checks same-domain links.
- The tool records titles, descriptions, H1s, canonical tags, redirects, and errors, saving progress continuously to report.json.
- Testing found a homepage-competing title, a query ranking at position 9.5 with 0% CTR, missing internal links, and an orphan page.
- A 20-URL Sonnet audit costs about $0.12, with --tiered reducing costs; visible browsing and deliberate two-second delays make it unsuitable for server-side CI.
- Reports provide plain-English PASS/FAIL results per URL, while interactive mode pauses for 404s, redirects, or login walls and auto mode logs them instead.
#seo #browser automation #claude #web auditing
Generated by gpt-5.6-sol. Check the original for details.
Aliases
| Source | External ID | URL |
|---|---|---|
| Agent Use Cases | https://agentusecases.ai/use-case/audit-websites-for-seo-issues-with-a-browsing-agent | https://agentusecases.ai/use-case/audit-websites-for-seo-issues-with-a-browsing-agent Read discussion |