Best AI Prompts for SEO Site Auditing (2026)
Crawl findings, heading hierarchy, links and schema, using real data from Google tools
How to use: click Copy, replace the [amber fields] with your own material, and read the check under each set.
Prompts for SEO auditing#
Five starting points#
5 promptsAct as an expert SEO technical auditor. Write a Python script using Beautiful Soup and Requests to crawl a website, extract all H1-H3 heading hierarchies, check meta descriptions, and flag missing alt tags.Act as a principal search engine architect. Formulate a comprehensive programmatic audit checklist for evaluating core web vitals, server response latency, and mobile responsiveness across large publishing networks.Act as an advanced technical SEO strategist. Write an automated audit script to detect broken internal links, redirect chains, and orphaned pages within a Next.js static site generation (SSG) deployment.Act as an enterprise SEO specialist. Construct an automated schema markup validator script that checks JSON-LD structured data for article, product, and organization entities across all site URLs.Act as a site performance engineer. Design an automated monitoring pipeline script that tracks page load bottlenecks, unoptimized image assets, and CSS stylesheet bloat.Feed the model real data#
- Export crawl results from a crawler or your own scripts.
- Run Lighthouse (
lighthouse <url> --output json --output-path <file>after installing it with npm) and paste the report. - Use Search Console and the URL Inspection API for index status and queries.
- For field data, the PageSpeed Insights API combines Chrome User Experience Report data with Lighthouse lab data; Google notes plans to discontinue real-world data in that API, so check its current page.
The full prompt library is on our prompt library page.
Key context and caveats#
Auditing needs measurements, and a language model has none until you provide them. Google's tools supply the data: the URL Inspection API returns the index status Google holds for a page, Lighthouse measures performance, accessibility and SEO from the command line or DevTools, and the PageSpeed Insights API adds field data to lab data.
Google's own pages set the limits. The URL Inspection API reports the indexed version and cannot test the indexability of a live URL, and its published quota is 2,000 queries per day per site. Google's SEO starter guide recommends descriptive, unique titles and meta descriptions and says keyword stuffing violates its spam policies. Its generative-AI guidance says to manually fact-check and review AI-generated content for accuracy.
At a Glance#
| Need | Tool | Note |
|---|---|---|
| Index status | URL Inspection API | Indexed version only; quota limits apply |
| Performance, accessibility, SEO scores | Lighthouse | DevTools or CLI |
| Field plus lab data | PageSpeed Insights API | Check current data availability |
| Prioritising and explaining | A language model | Only on data you supply |
Sources & Further Reading#
Every source below was fetched on 2026-10-21 unless a row says otherwise.
| Claim | Source | Section or date |
|---|---|---|
| Descriptive titles and meta descriptions; keyword stuffing violates spam policies | SEO Starter Guide (Google Search Central) | Last updated 2025-12-10 |
| Fact-check and review AI-generated content | Google Search's guidance on using generative AI content | Last updated 2026-10-01 |
| Scaled content abuse includes using generative AI to generate many pages without adding value | Spam policies (Google Search Central) | Scaled content abuse; last updated 2026-08-28 |
| Index status only; cannot test a live URL | URL Inspection API: index.inspect | Last updated 2024-07-23 |
| 2,000 queries per day and 600 per minute per site | Usage limits (Search Console API) | URL inspection; last updated 2025-08-28 |
| Audits for performance, accessibility, SEO; CLI and DevTools | Lighthouse overview (Chrome for Developers) | Last updated 2025-06-02 |
| PageSpeed Insights API combines field and lab data | Get started with the PageSpeed Insights API | Last updated 2025-08-28 |
Direct answer
What are the best AI prompts for an SEO site audit?
A model can help interpret an SEO audit but cannot crawl your site or measure rankings. Give it real data from Search Console, Lighthouse or a crawler. Google says AI-generated content needs fact-checking, and that mass pages without added value break its spam policies.
How we sourced this
Model names, features and limits change often. The prompts below are our own untested starting points, and we did not measure which wording performs best. Facts are as printed on each provider page on the date shown.
Need a different task?
Browse all 36 tasks and 180 prompts, with search and level filters.
How we weigh evidence, and what terms like AGI and ASI mean on this site, is explained in our methodology.
Frequently asked questions
What are the best AI prompts for an SEO site audit?
A model can help interpret an SEO audit but cannot crawl your site or measure rankings. Give it real data from Search Console, Lighthouse or a crawler. Google says AI-generated content needs fact-checking, and that mass pages without added value break its spam policies.
Can AI audit my website for SEO?
It can analyse data you supply, such as crawl exports, Lighthouse reports and Search Console results, and turn them into a prioritised list. It cannot see your live site on its own. Use Google tools for measurements, and treat the model as an analyst, not a source of facts.
Does Google penalise AI-generated content?
Google says it focuses on quality, not how content is made, but its spam policies list using generative AI to produce many pages without adding value as scaled content abuse. Its guidance asks you to fact-check and review AI-generated content for accuracy before publishing.