Weekly AI Search Health Check (10 Minutes)
A 10-minute weekly checklist prompt that scans your homepage and top 3 money pages for the four AEO regressions that quietly kill citations: schema disappearing after a deploy, robots.txt accidentally blocking AI crawlers, FAQ answers drifting from JSON-LD, and Rich Results errors appearing in Google Search Console. Run every Monday morning.
Pro tip
AEO regressions are silent — a CMS update strips schema, a Cloudflare rule blocks GPTBot, a content edit unsyncs a visible FAQ from its JSON-LD — and you don't notice until your citation share drops weeks later. A 10-minute weekly check catches all four common regressions before they compound. Pin this prompt to your Monday-morning calendar.
How to use this prompt
- Pick your AI model. Choose the tab for Claude, ChatGPT, Gemini or Copilot — each variant is tuned for that model.
- Copy the full prompt. Click Copy Full Prompt to copy the text to your clipboard.
- Paste into your AI tool. Open your chosen model and paste the prompt into a new chat.
- Replace the
[placeholders]. Swap any bracketed fields for your company name, audience, product or tone. - Run and refine. Review the output. If anything is off, ask the AI to tighten tone, length or format.
Prompt Variants by Model
Claude
Claude 4.x
FRESH APR 2026
You are my AEO health monitor. Run a 10-minute weekly check on my site for the four regressions that quietly kill AI-search citations. I''ll paste the inputs; you run the checklist and tell me what...You are my AEO health monitor. Run a 10-minute weekly check on my site for the four regressions that quietly kill AI-search citations. I''ll paste the inputs; you run the checklist and tell me what changed since last week and what to fix this week.
<my_site>
Homepage URL: [https://YOUR-DOMAIN.COM]
Top 3 money pages (the URLs you most want cited): [URL1], [URL2], [URL3]
Last week''s scorecard from this same prompt (paste if running for the 2nd+ week, else leave blank): [PASTE OR BLANK]
</my_site>
<inputs_to_paste>
For each of the 4 URLs (homepage + 3 money pages), paste:
1. The HTML source (view source, select all, copy).
2. The current robots.txt content (fetch from /robots.txt at the domain).
3. Any new Google Search Console "Enhancements" errors or warnings appearing in the last 7 days (paste verbatim, or "no new errors").
4. Recent CMS / theme / plugin updates in the last 7 days (one-line summary each, or "none").
</inputs_to_paste>
<weekly_checklist>
Walk through these four regression checks. For each, mark ✅ PASS / ⚠️ ATTENTION / 🚨 REGRESSION:
**CHECK 1 — Schema didn''t disappear**
For each of the 4 URLs, count the JSON-LD blocks present and list each @type. Compare to last week''s scorecard if provided. If any block is missing vs last week, that''s a 🚨 REGRESSION (likely caused by a CMS update or theme change).
**CHECK 2 — robots.txt didn''t block AI crawlers**
Read the robots.txt content. Verify it still explicitly allows GPTBot, OAI-SearchBot, ChatGPT-User, PerplexityBot, Perplexity-User, ClaudeBot, Claude-Web, anthropic-ai, Google-Extended, Applebot-Extended, CCBot, Bingbot. Verify no new Disallow lines target these user-agents. Verify the sitemap directive is still present and points to a valid URL.
**CHECK 3 — Visible FAQs match FAQPage JSON-LD**
For any URL with FAQPage JSON-LD, compare the questions and first-sentence-of-answer to what''s in the visible FAQ section on the page. Flag any drift — common after content edits where the visible copy gets updated but the JSON-LD doesn''t. Also flag any new microdata (itemscope/itemtype/itemprop) added to the visible FAQ that would duplicate the JSON-LD (Rich Results killer).
**CHECK 4 — No new Rich Results errors in GSC**
For each new error/warning I pasted, identify which page it''s on and which schema field caused it. Map to a one-line fix.
</weekly_checklist>
Output exactly four parts:
**PART 1 — This Week''s Scorecard**
Markdown table: Check · URL · Status (✅ / ⚠️ / 🚨) · One-line evidence.
**PART 2 — Diff vs Last Week**
What changed for better or worse since last week''s scorecard. If this is the first run, say "baseline established — no diff to show".
**PART 3 — This Week''s Fix List**
Numbered, in order of urgency. Each fix gets:
- What to fix
- Why it matters
- Time to do it
- Which AlignAI prompt to use if applicable
🚨 items get fixed this week. ⚠️ items get fixed this month. ✅ items get a 1-line "leave alone".
**PART 4 — Save This Scorecard**
Output this week''s scorecard in a copy-friendly block I can paste back as input next week so you can compute the diff.
Format the saved scorecard as:
WEEK OF: [today''s date]
HOMEPAGE — JSON-LD blocks: [@type, @type, @type] — robots.txt allow-list: [PASS/ISSUES] — FAQ sync: [PASS/N/A/DRIFT] — GSC new errors: [N]
MONEY PAGE 1 — [same fields]
MONEY PAGE 2 — [same fields]
MONEY PAGE 3 — [same fields]
Notes: Claude is the strongest variant for the diff-vs-last-week step. Pin this prompt to a Monday calendar reminder; the saved scorecard makes the next run faster every week.
ChatGPT
GPT-5
FRESH APR 2026
Act as my AEO health monitor. Run a 10-minute weekly check on my site for the four regressions that quietly kill AI-search citations.
My site:
- Homepage URL: [https://YOUR-DOMAIN.COM]
- Top 3 money...Act as my AEO health monitor. Run a 10-minute weekly check on my site for the four regressions that quietly kill AI-search citations.
My site:
- Homepage URL: [https://YOUR-DOMAIN.COM]
- Top 3 money pages: [URL1, URL2, URL3]
- Last week''s scorecard from this prompt (paste if 2nd+ week, else blank): [PASTE or BLANK]
For each of the 4 URLs paste:
1. HTML source.
2. Current robots.txt content (fetch /robots.txt at the domain).
3. New Google Search Console "Enhancements" errors/warnings in the last 7 days (verbatim or "no new errors").
4. CMS / theme / plugin updates in the last 7 days (one-line each or "none").
Run four checks. Mark each ✅ PASS / ⚠️ ATTENTION / 🚨 REGRESSION:
CHECK 1 — Schema didn''t disappear: per URL, count JSON-LD blocks + list each @type. Compare to last week. Missing block vs last week = 🚨.
CHECK 2 — robots.txt didn''t block AI crawlers: still explicitly allows GPTBot, OAI-SearchBot, ChatGPT-User, PerplexityBot, Perplexity-User, ClaudeBot, Claude-Web, anthropic-ai, Google-Extended, Applebot-Extended, CCBot, Bingbot? No new Disallow targeting these? Sitemap directive present?
CHECK 3 — Visible FAQs match FAQPage JSON-LD: for any URL with FAQPage, compare visible Q + first-sentence-of-A to the JSON-LD. Flag drift. Flag any new microdata (itemscope/itemtype/itemprop) duplicating the JSON-LD (Rich Results killer).
CHECK 4 — No new GSC Rich Results errors: per new error/warning, identify page + schema field + one-line fix.
Output:
1. This Week''s Scorecard table: Check · URL · Status (✅ / ⚠️ / 🚨) · One-line evidence.
2. Diff vs Last Week — what changed for better or worse. If first run, "baseline established".
3. This Week''s Fix List — numbered by urgency: what · why · time · which AlignAI prompt. 🚨 this week, ⚠️ this month, ✅ leave alone.
4. Save This Scorecard — copy-friendly block to paste back next week:
WEEK OF: [date]
HOMEPAGE — JSON-LD blocks: [list] — robots.txt allow-list: [PASS/ISSUES] — FAQ sync: [PASS/N/A/DRIFT] — GSC new errors: [N]
MONEY PAGE 1, 2, 3 — same fields
Notes: GPT-5 with browsing can fetch robots.txt + verify URLs directly — replace the paste steps if browsing is enabled. Pin this to a Monday calendar reminder.
Gemini
Gemini 2.5 Pro
FRESH APR 2026
You are my AEO health monitor. Run a 10-minute weekly check on my site for the four regressions that quietly kill AI-search citations.
MY SITE:
• Homepage URL: [https://YOUR-DOMAIN.COM]
• Top 3...You are my AEO health monitor. Run a 10-minute weekly check on my site for the four regressions that quietly kill AI-search citations.
MY SITE:
• Homepage URL: [https://YOUR-DOMAIN.COM]
• Top 3 money pages: [URL1, URL2, URL3]
• Last week''s scorecard from this prompt (paste if 2nd+ week, else blank): [PASTE or BLANK]
For each of the 4 URLs paste:
1. HTML source.
2. Current robots.txt content.
3. New Google Search Console "Enhancements" errors in the last 7 days (verbatim or "no new errors").
4. CMS / theme / plugin updates in the last 7 days (one-line or "none").
Run four checks. Mark each ✅ PASS / ⚠️ ATTENTION / 🚨 REGRESSION:
CHECK 1 — Schema didn''t disappear: per URL, count JSON-LD blocks + list @types. Compare to last week. Missing block vs last week = 🚨.
CHECK 2 — robots.txt didn''t block AI crawlers: still allows GPTBot, OAI-SearchBot, ChatGPT-User, PerplexityBot, Perplexity-User, ClaudeBot, Claude-Web, anthropic-ai, Google-Extended, Applebot-Extended, CCBot, Bingbot? No new Disallow? Sitemap directive present?
CHECK 3 — Visible FAQs match FAQPage JSON-LD: compare visible Q + first-sentence-of-A to JSON-LD. Flag drift. Flag any new microdata duplicating JSON-LD.
CHECK 4 — No new GSC Rich Results errors: per error, identify page + schema field + one-line fix.
OUTPUT:
1. This Week''s Scorecard table: Check | URL | Status | One-line evidence.
2. Diff vs Last Week. If first run, "baseline established".
3. This Week''s Fix List — numbered by urgency: what | why | time | which AlignAI prompt. 🚨 this week, ⚠️ this month, ✅ leave alone.
4. Save This Scorecard — copy-friendly block:
WEEK OF: [date]
HOMEPAGE — JSON-LD blocks: [list] — robots.txt allow-list: [PASS/ISSUES] — FAQ sync: [PASS/N/A/DRIFT] — GSC new errors: [N]
MONEY PAGE 1, 2, 3 — same fields
Notes: Gemini 2.5 Pro is reliable for the weekly cadence. The diff step is its strongest contribution.
Copilot
Copilot (GPT-5)
FRESH APR 2026
Run a 10-minute weekly AEO health check on my site for the four regressions that quietly kill AI-search citations.
My site:
• Homepage URL: [https://YOUR-DOMAIN.COM]
• Top 3 money pages: [URL1,...Run a 10-minute weekly AEO health check on my site for the four regressions that quietly kill AI-search citations.
My site:
• Homepage URL: [https://YOUR-DOMAIN.COM]
• Top 3 money pages: [URL1, URL2, URL3]
• Last week''s scorecard (paste if 2nd+ week, else blank): [PASTE or BLANK]
For each of the 4 URLs paste:
1. HTML source.
2. Current robots.txt.
3. New Google Search Console "Enhancements" errors in the last 7 days (verbatim or "no new errors").
4. CMS / theme / plugin updates in the last 7 days (one-line or "none").
Run four checks. Mark each ✅ PASS / ⚠️ ATTENTION / 🚨 REGRESSION:
CHECK 1 — Schema didn''t disappear: count JSON-LD blocks + @types per URL. Compare to last week. Missing block = 🚨.
CHECK 2 — robots.txt didn''t block AI crawlers: still allows GPTBot, OAI-SearchBot, ChatGPT-User, PerplexityBot, Perplexity-User, ClaudeBot, Claude-Web, anthropic-ai, Google-Extended, Applebot-Extended, CCBot, Bingbot? No new Disallow? Sitemap present?
CHECK 3 — Visible FAQs match FAQPage JSON-LD: flag drift between visible content and JSON-LD. Flag microdata duplicating JSON-LD.
CHECK 4 — No new GSC Rich Results errors: per error, page + schema field + one-line fix.
Output:
1. This Week''s Scorecard table: Check · URL · Status · One-line evidence.
2. Diff vs Last Week. First run = "baseline established".
3. This Week''s Fix List — numbered by urgency: what · why · time · which AlignAI prompt. 🚨 this week, ⚠️ this month, ✅ leave alone.
4. Save This Scorecard — copy-friendly block:
WEEK OF: [date]
HOMEPAGE — JSON-LD blocks: [list] — robots.txt allow-list: [PASS/ISSUES] — FAQ sync: [PASS/N/A/DRIFT] — GSC new errors: [N]
MONEY PAGE 1, 2, 3 — same fields
Notes: Copilot integrates well with Microsoft 365 calendar — pin a Monday recurring task that opens this prompt. Bing-side regressions are this variant's strongest signal.
Frequently Asked Questions
What does the Weekly AI Search Health Check (10 Minutes) prompt do?
A 10-minute weekly checklist prompt that scans your homepage and top 3 money pages for the four AEO regressions that quietly kill citations: schema disappearing after a deploy, robots.txt accidentally blocking AI crawlers, FAQ answers drifting from JSON-LD, and Rich Results errors appearing in Google Search Console. Run every Monday morning.
Which AI models is this prompt tested on?
This prompt is field-tested on Claude, ChatGPT, Gemini and Copilot. Each model has its own optimized variant above.
Do I need a paid AI account to use this prompt?
No. This prompt is written to run on the free tier of Claude, ChatGPT, Gemini and Copilot. Paid tiers simply give you longer context windows and faster responses.
Can I customize this prompt for my business?
Yes. Any text inside square brackets is a placeholder you replace with your own business details, such as company name, audience, product or tone. You can also ask the AI to adjust format, length or style after the first output.
When was this prompt last verified?
Each model variant above shows its own freshness stamp. AlignAI re-verifies every prompt at least monthly and rebuilds when a major model changes.
Don’t see what you need? tailored to your use case.