Account audits

Check whether AI crawlers can actually reach and read your site

Resolves robots.txt for each AI crawler by role, checks status codes, redirects and blocking headers, and measures what each page shows without JavaScript. Ends with a ranked fix list and changes nothing.

When to use it

Your site is never cited in AI answers, or you are not sure whether a firewall, CDN setting or robots.txt rule is quietly blocking AI crawlers.

What you get

A robots.txt decision for every AI crawler with its role, the status code, redirects and no-JavaScript content of every key page, and a ranked, evidence-backed fix list. Nothing on the site changes.

Does it change anything in my account?

No. The assistant only reads your data and reports back.

Works with

SEO Intelligence, Search Console

Fill in before sending

[site URL][Search Console property, or "none"][5 to 10 page URLs]

Check whether my site [site URL] can serve content to AI search such as ChatGPT, Claude, Perplexity, Gemini and Copilot. My Search Console property is [Search Console property, or "none"]. My most important pages are: [5 to 10 page URLs]. This is a read-only audit, do not change anything. 1. robots.txt. Read [site URL]/robots.txt with site_read_url and note the status code. If the file returns 5xx or loops through redirects, say at the top that crawlers may not crawl the site at all. Then work out which rule group applies to each of these crawlers and whether my key pages are allowed: OAI-SearchBot, ChatGPT-User, GPTBot, Claude-SearchBot, Claude-User, ClaudeBot, PerplexityBot, Perplexity-User, Googlebot, Google-Extended, Bingbot, Applebot, Applebot-Extended, CCBot, meta-externalagent. When a crawler has a group under its own name, only that group applies and the `User-agent: *` rules do not, so account for that. 2. Sort the crawlers by role. The ones that crawl for search and citations are OAI-SearchBot, Claude-SearchBot, PerplexityBot, Bingbot and Googlebot. The ones that fetch a page live when a user asks a question are ChatGPT-User, Claude-User and Perplexity-User. The ones that collect training data are GPTBot, ClaudeBot, Google-Extended, Applebot-Extended, CCBot and meta-externalagent. Flag any blocked search crawler at the highest severity, because the site cannot be cited in that assistant's answers. Do not treat a blocked training crawler as an error, describe it as a choice. Note that Google-Extended does not affect Google Search or AI Overviews and only controls whether the content is used for Gemini models. 3. Status codes and headers. Read each key page with site_read_url and max_bytes=0. Report only the status code, the redirect chain (redirects), the `x-robots-tag` and `content-type` headers and the `server` value, not the full header dump. Flag redirect chains longer than two hops, a final URL that differs from the canonical, and any noindex or nosnippet header. If a page returns 403, 429 or 503 and the server value shows a protection layer such as Cloudflare, Sucuri or Akamai, say it may be a bot block. 4. Content without JavaScript. Read the key pages with site_read_url and text=true. This view is extracted from the HTML the server sends, which is what an AI crawler that does not run JavaScript sees. If the reply says truncated is true, read the page again with max_bytes=1000000, otherwise you will think content near the bottom is missing. For each page, say whether the H1, the first paragraph of the main content, the price or service details and the contact details are in that text, and whether internal_links contains links to the main menu pages. 5. Content with JavaScript. Measure the three most important pages with seo_technical_audit, which renders the page with JavaScript. Flag separately any page where the title, H1 or language differs between the two views. A language difference usually comes from an automatic redirect based on the visitor's country or browser language, and because most AI crawlers come from servers in the United States, it can make them see the wrong language version. 6. What Google sees. If I have a Search Console property, inspect the key pages in one gsc_inspect_urls call: coverage state, last crawl date and Google's chosen canonical. List any key page blocked by robots.txt or shown as "Crawled, currently not indexed". List the submitted sitemaps with their warnings and errors using gsc_sitemaps. 7. Discovery files. Read sitemap.xml and llms.txt with site_read_url. Check that my key pages are in the sitemap and that the lastmod values look real, and say so if every URL carries the same date. If llms.txt is missing, note it as a gap but not a critical one, because none of the major AI search engines has officially said it uses this file as a ranking or citation signal. State the limits of the tools plainly. site_read_url sends its request as a browser and cannot pose as GPTBot or ClaudeBot, so a firewall rule that blocks only by crawler name will not show up in this audit. If I use a CDN or firewall, remind me to check its panel for a setting that blocks AI crawlers (in Cloudflare, "AI Crawl Control" or "Block AI bots"). If the site is hosted on Opus Growth, do not send me to any CDN panel, and if you see a block, suggest reporting it with report_issue. Format the output like this. First a three-sentence summary: is my site open to AI search, and if not, what is the biggest blocker. Then a crawler table: crawler, role, robots.txt decision, the rule line that decides it, severity. Then a page table: URL, status code, redirects, x-robots-tag, H1 and first paragraph in the no-JavaScript text (yes or no), difference from the JavaScript view, Google coverage state. End with a fix list ranked by severity, each with its evidence and who should do it (me, a developer, the hosting provider). Where the data is not enough for a conclusion, do not guess, say what is missing.

1. robots.txt. Read [site URL]/robots.txt with site_read_url and note the status code. If the file returns 5xx or loops through redirects, say at the top that crawlers may not crawl the site at all. Then work out which rule group applies to each of these crawlers and whether my key pages are allowed: OAI-SearchBot, ChatGPT-User, GPTBot, Claude-SearchBot, Claude-User, ClaudeBot, PerplexityBot, Perplexity-User, Googlebot, Google-Extended, Bingbot, Applebot, Applebot-Extended, CCBot, meta-externalagent. When a crawler has a group under its own name, only that group applies and the `User-agent: *` rules do not, so account for that.
2. Sort the crawlers by role. The ones that crawl for search and citations are OAI-SearchBot, Claude-SearchBot, PerplexityBot, Bingbot and Googlebot. The ones that fetch a page live when a user asks a question are ChatGPT-User, Claude-User and Perplexity-User. The ones that collect training data are GPTBot, ClaudeBot, Google-Extended, Applebot-Extended, CCBot and meta-externalagent. Flag any blocked search crawler at the highest severity, because the site cannot be cited in that assistant's answers. Do not treat a blocked training crawler as an error, describe it as a choice. Note that Google-Extended does not affect Google Search or AI Overviews and only controls whether the content is used for Gemini models.
3. Status codes and headers. Read each key page with site_read_url and max_bytes=0. Report only the status code, the redirect chain (redirects), the `x-robots-tag` and `content-type` headers and the `server` value, not the full header dump. Flag redirect chains longer than two hops, a final URL that differs from the canonical, and any noindex or nosnippet header. If a page returns 403, 429 or 503 and the server value shows a protection layer such as Cloudflare, Sucuri or Akamai, say it may be a bot block.
4. Content without JavaScript. Read the key pages with site_read_url and text=true. This view is extracted from the HTML the server sends, which is what an AI crawler that does not run JavaScript sees. If the reply says truncated is true, read the page again with max_bytes=1000000, otherwise you will think content near the bottom is missing. For each page, say whether the H1, the first paragraph of the main content, the price or service details and the contact details are in that text, and whether internal_links contains links to the main menu pages.
5. Content with JavaScript. Measure the three most important pages with seo_technical_audit, which renders the page with JavaScript. Flag separately any page where the title, H1 or language differs between the two views. A language difference usually comes from an automatic redirect based on the visitor's country or browser language, and because most AI crawlers come from servers in the United States, it can make them see the wrong language version.
6. What Google sees. If I have a Search Console property, inspect the key pages in one gsc_inspect_urls call: coverage state, last crawl date and Google's chosen canonical. List any key page blocked by robots.txt or shown as "Crawled, currently not indexed". List the submitted sitemaps with their warnings and errors using gsc_sitemaps.
7. Discovery files. Read sitemap.xml and llms.txt with site_read_url. Check that my key pages are in the sitemap and that the lastmod values look real, and say so if every URL carries the same date. If llms.txt is missing, note it as a gap but not a critical one, because none of the major AI search engines has officially said it uses this file as a ranking or citation signal.

State the limits of the tools plainly. site_read_url sends its request as a browser and cannot pose as GPTBot or ClaudeBot, so a firewall rule that blocks only by crawler name will not show up in this audit. If I use a CDN or firewall, remind me to check its panel for a setting that blocks AI crawlers (in Cloudflare, "AI Crawl Control" or "Block AI bots"). If the site is hosted on Opus Growth, do not send me to any CDN panel, and if you see a block, suggest reporting it with report_issue.

Format the output like this. First a three-sentence summary: is my site open to AI search, and if not, what is the biggest blocker. Then a crawler table: crawler, role, robots.txt decision, the rule line that decides it, severity. Then a page table: URL, status code, redirects, x-robots-tag, H1 and first paragraph in the no-JavaScript text (yes or no), difference from the JavaScript view, Google coverage state. End with a fix list ranked by severity, each with its evidence and who should do it (me, a developer, the hosting provider). Where the data is not enough for a conclusion, do not guess, say what is missing.

Open in Claude Open in ChatGPT Discuss in the forum

Example result

An example of the output this prompt produces. Its structure comes from the tools' real output; numbers and names are fictional.

Example output (based on a fictional site, not real customer data)

Summary. northworkshop.example is open to most search-role AI crawlers, but robots.txt has a separate PerplexityBot group that closes the whole site. On the service pages the price table loads only with JavaScript, so crawlers that do not run JavaScript never see the prices. These two problems are the biggest blockers, and both can be fixed in a day.

Crawler	Role	Decision	Deciding line	Severity
OAI-SearchBot	Search	Allowed	User-agent: * / Allow: /	OK
PerplexityBot	Search	Blocked	User-agent: PerplexityBot / Disallow: /	High
ChatGPT-User	User fetch	Allowed	User-agent: *	OK
GPTBot	Training	Blocked	User-agent: GPTBot / Disallow: /	Choice
Google-Extended	Training	Allowed	User-agent: *	Choice

URL	Status	Redirects	x-robots-tag	No-JS H1 / first paragraph	Difference from JS view	Google
/services/kitchen-cabinets/	200	none	none	yes / yes	Price table only in the JS view	Indexed
/contact	200	308 to /contact/	none	yes / no	Address and phone only in the JS view	Indexed
/tr/	200	none	noindex	yes / yes	Turkish title, as expected	Excluded: noindex

Fix order
1. Remove the PerplexityBot group from robots.txt (you). Evidence: the group disallows the whole site.
2. Move the price table and contact details into the server HTML (developer). Evidence: missing from the text=true view.
3. Confirm the noindex header on /tr/ is intentional (you).

Not measurable: whether the firewall blocks by crawler name cannot be seen with these tools, so check your CDN panel.

More prompts

Account auditsRead-only

Full Google Ads account audit with the three fixes to make first

Reviews the whole account in one pass, from measurement and bidding to structure and landing pages. Ranks the findings by impact and names the first three fixes without changing anything.

When to use itWhen you inherit or doubt a Google Ads account and want to know what is actually wrong and where to start fixing it.

Audit my Google Ads account [account name] end to end. If the account is younger than 90 days use every day available, otherwise use the last 90 days. This is a read-only review, do not change anything.

Start with account_snapshot to get each campaign's status, budget, bidding strategy, age and results since it started. Separate the campaigns that bring results from the ones that spend without converting. Then work through these areas in order:

1. Measurement. List the primary conversion actions with list_conversion_actions. Flag any primary action that recorded nothing in the last 30 days. Look for setups that can count the same person twice, for example a phone click and a WhatsApp click on the site set up as two separate primary actions, or the Google Ads tag and an imported GA4 event both primary for the same form. Check how many clicks went to the call button in the ads and whether those calls were actually recorded, using google_ads_query on call_view.
2. Bidding and budget. Use impression_share_analysis to show, per campaign, the impression share lost to budget and to rank. Use keyword_quality_report to find keywords below the first page bid or rarely shown because of low quality. For campaigns on Smart Bidding, say whether the last 30 days hold enough conversions for the target they use.
3. Structure. Check whether brand searches share a campaign with generic searches, whether every ad group sends people to the page for its own service, and whether the same keyword sits in more than one ad group.
4. Search terms. Use search_terms_report to separate terms that spend without converting, competitor brands and informational searches. Never count a term with at least one conversion as waste.
5. Ads and assets. Review ad strength, disapproved assets and whether sitelinks point to the right page. Flag separately any copy or asset that describes a service the business does not offer: [services not offered, or write "none"].
6. Landing pages. Pull clicks, cost and conversion rate per page from landing_page_view with google_ads_query. On the pages that take the most spend, check that a phone and a WhatsApp button exist and check mobile speed with core_web_vitals.
7. Location, schedule and device. Show whether the location option is set to "Presence", how much spend goes outside the target area, and the spend and conversions outside [business hours].

Format the output like this: first a five-sentence summary of where the account stands. Then a findings table ranked by importance: problem, evidence, estimated impact, recommendation. At the end, the three fixes to make first and why each one comes first. Where the data is not enough for a conclusion, do not guess, say what is missing.

Account auditsRead-only

Full Meta Ads account audit with the three fixes to make first

Reviews measurement, delivery issues, the learning phase, targeting, placements and creative fatigue in one pass. Ranks the findings and names the first three fixes without changing anything.

When to use itWhen your Meta ads results have slipped or stalled and you need to know what is wrong in the account before touching anything.

Audit my Meta ad account [ad account] end to end. Use the last 30 days as the main period and the 30 days before that as the comparison. This is a read-only review, do not change anything.

Start with account_snapshot for platform meta to get each campaign's status, budget, objective, age and results since it started. Meta has no single conversion count, so use the result each campaign actually optimizes for (leads, messaging conversations started, purchases). Then work through these areas in order:

1. Measurement. Check the pixel's last event time with list_meta_pixels. Confirm that the event each campaign optimizes for is actually recording. Flag setups that can count the same result twice, for example leads collected by both the pixel and an instant form.
2. Delivery. List ad sets that are rejected, stuck in review, have no active ad left, or spend less than half of their budget. Give Meta's stated reason for each.
3. Learning phase. Find ad sets split so thin that they cannot reach 50 results a week. Use meta_change_history to show edits in the last 14 days that reset learning.
4. Targeting and audiences. Flag ad sets that target the same audience and ad sets whose frequency is above [maximum frequency].
5. Placements and devices. With get_report, compare cost per result by publisher_platform and by device against the account average. Do not decide on segments with fewer than 20 results.
6. Creatives. Treat an ad as fatigued when frequency rises while click-through rate falls and cost per result climbs. Briefly describe the angle the winning ads share.
7. Destination. Check that the page or WhatsApp link the ads send people to works and matches the objective.

Account auditsChanges after your approval

Merge phone and WhatsApp enquiries into one reliable conversion

Stops one person being counted twice when they both call and message. Ties the two buttons on the site to a single conversion and checks whether the call button in the ads is measured at all.

When to use itWhen people call and message you from the same site and you suspect one visitor is being counted as two conversions, making your cost per conversion look better than it is.

In my Google Ads account [account name], prospects reach us through the phone and WhatsApp buttons on the site. If one person pressing both buttons counts as two conversions, my cost per conversion looks cheaper than it is and the bidding algorithm learns the wrong thing. Fix this.

1. Map the current setup. List the primary actions, their categories and counting types with list_conversion_actions. In my Tag Manager container [GTM container ID], use list_gtm_tags to show which tag fires which conversion label. Estimate with numbers how often one ad click may have produced more than one contact conversion in the last 30 days.
2. The call button in the ads. With google_ads_query, check how many clicks and how much spend went to the call button in the ads, and use call_view to check whether those calls were recorded. If there are clicks but no records, say so clearly and offer two options: remove the call asset, or accept those clicks as unmeasured traffic.
3. Show the plan. Propose a single conversion action named "Contact click (Phone + WhatsApp)" with counting set to one. Tie it to one tag that fires on both the phone and the WhatsApp trigger. Make the two old actions secondary. Say whether campaigns on Smart Bidding need their target reviewed, because the conversion count will drop.
4. Apply after my approval. Create the conversion action, set counting to one, update the tag in Tag Manager and show me the list of changes before publishing. After publishing, write down which version can be restored.

Finish with a short test plan: how to see in preview mode that only the new tag fires when both buttons are pressed, and how many days it takes for the fix to show in real data.

Account auditsRead-only

Run a full SEO, AEO and GEO audit and get an evidence-backed scorecard

Scores access, technical health, structured data, quotability of content, trust signals and measured AI visibility in six areas of five concrete checks each. Shows the evidence for every point and orders the fixes by impact and effort, without changing anything.

When to use itYou want one evidence-backed report showing where your site stands in Google and in AI search, and a clear task list to hand to an agency or developer.

Audit my site [site URL] end to end for classic search, answer engines (AEO) and AI search (GEO). My Search Console property: [Search Console property]. Main competitor: [competitor domain, or "none"]. Market: [country], language: [language code]. The 3 searches that bring me the most business: [3 commercial queries]. My most important page templates: [homepage, one service page, one blog post URL]. This is read-only.

Credit rule: before starting, check earlier runs with seo_history and call the reusable ones again with the same arguments. Show me once the list of new calls that will spend credits and get my approval.

Data collection:
1. Run the bundled analysis with seo_full_analysis, passing domain, competitor, location and language. Its AI visibility section measures the single keyword the site ranks for most, which may have nothing to do with my business; do not use that section for scoring, and instead measure my 3 commercial queries with seo_ai_overview and target=[domain]. If references is empty, count the domains of the links inside ai_answer.
2. Run seo_site_crawl with max_pages close to the site's page count (at most [page limit]). It returns a task_id; call it again with the same task_id after 60 to 90 seconds and wait until the summary arrives. Pull the full URL list of an issue with the issue parameter when needed. If the crawl limit does not cover the whole site, say the results are a sample.
3. Read robots.txt, sitemap.xml and llms.txt with site_read_url. Read my template pages with text=true (if truncated is true, again with max_bytes=1000000) and with outline=true. For JSON-LD, read the same pages with max_bytes=1000000 and extract the blocks.
4. Measure the homepage and the service page with seo_audit and strategy='mobile'. For Core Web Vitals use real-user (field) data where it exists, otherwise the lab value, and say which one you used.
5. Use get_report with platform='search_console' and breakdown 'query by impressions' and 'page by impressions' for the last 90 days. Inspect the 10 pages with the most impressions with gsc_inspect_urls. Get the sitemap status with gsc_sitemaps.
6. Remember that different tools can see different versions of the same page: if seo_technical_audit or seo_site_crawl measures a title in a different language from what site_read_url shows, record it as a finding, because the site may be redirecting visitors by country.

Scorecard: six areas, five checks each, each check pass (1) or fail (0). If a check has no data, write "not measured" and drop it from the denominator; never score by guessing.
1. Access and crawlability: robots.txt is open to search-role AI crawlers; key pages return 200 with at most one redirect; no noindex on key pages; the sitemap has no errors and contains the key pages; the main content is visible without JavaScript.
2. Technical health and speed: mobile LCP under 2.5 seconds; CLS under 0.1; INP under 200 ms; no broken pages or broken internal links in the crawl; no duplicate titles or descriptions.
3. Structured data and entity: an Organization or LocalBusiness node exists; nodes are linked by @id; the schema fits the page type (Service, Article, Product); schema facts match the visible text; sameAs URLs work.
4. Quotability of content: the first paragraph of key pages answers the question directly; headings name the topic or question clearly; comparable facts are in a table; a page-specific FAQ exists; there are concrete numbers and dates.
5. Trust signals: the about page is concrete (who, where, since when); contact details are on the site and consistent; posts show an author or publisher; publish and update dates are visible; legal pages are reachable from the footer through static links.
6. Measured AI visibility: cited in Google's AI answer for at least one of the 3 commercial queries; cited for the brand query; llms.txt exists and is accurate; Search Console shows clicks from non-brand queries; if the main competitor is cited on these queries, there is at least one where I am cited too.

Format the output like this. First a five-sentence executive summary. Then the score table: area, score (e.g. 3/5), failed checks. Then the evidence table: area, check, result, evidence (tool name and returned value), affected URLs. Then the fix list: for each item the impact (high, medium, low), the effort (hours, days, weeks) and who does it; high impact and low effort first. At the end, the first three fixes and why they come first. Do not pass judgement on anything that was not measured.