Meta ads diagnostics

Stop asking ChatGPT "how are my ads doing?": 25 Meta ads audit prompts for Claude, ChatGPT and Grok

A vague question gets a vague answer. Each of these 25 prompts asks one narrow question, names the one Ads Manager export that can answer it (level, date range, breakdown, columns), gives the AI your target cost per purchase and break-even ROAS, and tells it to use only the file, show its sums and stop if a column is missing. Ten of the 25 run on a single ad-level export. Paste a prompt into Claude, ChatGPT or Grok with the file attached, then re-check the key number before you pause or scale anything.

Stop typing "how are my ads doing?" into ChatGPT.

The AI can't see your account. It doesn't know your margin, what a good cost per purchase is for you, or which date range you mean. So it fills the gap with general advice: test more creative, watch your frequency, consider broad targeting. None of it is wrong, and none of it tells you where your money went last month.

The fix isn't a smarter AI. It's a narrower question and the right file. This guide gives you 25 audit prompts that work in Claude, ChatGPT and Grok. Each one asks one question, names the exact Ads Manager export that can answer it, and tells the AI to use only that file and show its sums. It is written for business owners who run their own Meta ads (Facebook and Instagram), and it's specific enough for a performance marketer to hand to a junior.

The workbook has the 25 prompts with your business, targets and date range filled in automatically, the steps for each export, a Check tab that re-does the AI's sums with formulas, and a log for what you find. The account numbers in this article are a fictional worked example; nobody's real account was audited for it.

Why the vague question fails

Ask "how are my ads doing?" and three things are missing:

  1. The data. Without a file the AI has nothing to read. With a file but no instruction, it picks whatever columns look interesting.
  2. The yardstick. "Good" or "bad" only means something against your target cost per purchase and your break-even ROAS (return on ad spend). Leave them out and the AI compares you with averages it half-remembers.
  3. The rules. Nothing stops it rounding, estimating a missing column or inventing a benchmark. It will sound just as confident either way.

Comparison of two prompts. What most people type: "How are my ads doing?", with no date range or level, no target, no rule against inventing numbers, and a generic pep talk as the answer. A prompt from the pack has five parts: Context (online store, target CPA $40, break-even ROAS 2.5), Data (attached ad-level export, last 30 days, 7-day click), Question (rank every ad by spend with 0 purchases), Rules (use only the file, show the sum, flag missing columns) and Output (a table, then one action, biggest money first).

Every prompt in the pack has the same five parts.

The template every prompt uses

Here is the full prompt behind prompt 1, with our example settings. The workbook builds all 25 this way from your own Settings tab.

I run an online store selling coffee subscriptions. Target cost per purchase: $40. Break-even ROAS: 2.5. Target ROAS: 3.3. Attached: Ad level · last 30 days · Amount spent, Purchases, Purchase conversion value (last 30 days, attribution 7-day click, 1-day view, USD). Task: List every ad with zero purchases, sorted by amount spent, and give the total spent on them. Mark the ones that spent more than 1.5 times my target cost per purchase. Rules: Use only the attached file. Show the numbers and the sum behind every claim. If a column you need is missing, name it and stop; don't guess or estimate it. Answer with a table first, then one action per finding, biggest money first.

Three settings matter most:

  • Target cost per purchase: the most you want to pay for one sale.
  • Break-even ROAS: 1 ÷ your margin after product cost, shipping and fees. A 40% margin breaks even at 2.5. The ROAS target calculator works it out with returns included.
  • Attribution setting: the window Ads Manager uses to credit purchases (7-day click, 1-day view is the usual default). Say which one the export uses so the AI doesn't mix them.

How to run it

Four steps. 1. Export: the table the prompt names, with its level, date range and breakdown. 2. Fill the prompt: your target CPA, margin and dates, which the workbook does. 3. Ask: Claude, ChatGPT or Grok, with the file attached and the prompt pasted. 4. Check: re-do the key sum in the workbook before you act. Below: one question per prompt, one export per question; the AI only reads the file you attach and can't see or change your account.

  1. Export the table the prompt names. Ads Manager exports the table you're looking at, with your filters, columns, breakdown and date range applied, as CSV or Excel. Select the rows, then use Export table data. We couldn't find a Meta Help Center page that spells this out; third-party guides such as this one from Coinis walk through it.
  2. Paste the filled-in prompt from the workbook's Prompts tab.
  3. Attach the file and send. Claude, ChatGPT and Grok all accept CSV and Excel uploads. Upload limits differ by app and plan, so keep each export small: one level, one date range.
  4. One prompt per message, same chat. Prompt 25 summarises the answers above it, so run it last in the same conversation.

All three AIs only read the file you attach. They can't log in to your ad account and can't change anything in it.

Six exports cover all 25 prompts

You don't need 25 exports. Ten prompts run on the same ad-level table, so pull that one first.

Bar chart of the 25 prompts by the export they need. Ad-level table: 10 prompts (1, 2, 7, 8, 11, 14, 18, 20, 21, 24). Breakdowns by placement, age, country or device: 5 (3, 9, 15, 16, 19). Ad set level: 4 (4, 17, 22, 23). Campaign or account level by day: 2 (10, 13). Outside Ads Manager: 3 (5, 6 and 12: audience overlap, Events Manager and Shopify). Everything above: 1 (prompt 25, the summary).

ExportHow to pull itPrompts
Ad-level tableAds tab, your date range, Columns: Amount spent, Purchases, Purchase conversion value, Link clicks, CTR (link click-through rate), Landing page views, Website URL, Frequency, Impressions, 3-second video plays. For prompt 2, export it a second time with Breakdown, By time: Week, over the last 8 weeks1, 2, 7, 8, 11, 14, 18, 20, 21, 24
BreakdownsAd sets or Campaigns tab, Breakdown, By delivery: Placement, Age, Country or Impression device. One breakdown per file3, 9, 15, 16, 19
Ad set levelAd sets tab, add Delivery, Budget, Bid strategy, Reach, Frequency, Results4, 17, 22, 23
By dayCampaigns tab, Breakdown, By time: Day10, 13
Outside Ads ManagerAudience overlap screenshot, Events Manager screenshots, Shopify sales by day5, 6, 12
Your earlier answersNothing to export25

The 25 prompts

Each row is the question, the export it needs and what to ask. The workbook wraps each "what to ask" in the template above.

#QuestionExport it needsWhat to ask
1Rank every ad by spend with 0 purchasesAd level, last 30 days: spend, purchases, purchase valueList every ad with zero purchases, sorted by spend, with the total. Mark those that spent over 1.5x target cost per purchase
2Which ads are past 4.0 frequency and losing CTR?Ad level, last 8 weeks, by week: frequency, link CTR, impressions, spendFind the week each ad's frequency first passed 4.0; compare link CTR before and after. List ads down 25% or more
3Where is the dead money by placement?Ad set level, 30 days, placement breakdownList placements with over 5% of spend and zero purchases or cost per purchase over 1.5x target
4Which ad sets never left learning?Ad set level, 7 days: Delivery, Results, spend, budgetList ad sets in Learning or Learning limited with their purchases; suggest merges so each gets closer to 50 a week
5Does retargeting overlap prospecting?Audience overlap screenshot (if your account shows it) plus ad set namesWhich audience pairs overlap by over 20%, which ad sets use them, and which exclusion to add
6Is the Conversions API double-counting purchases?Events Manager screenshots of the Purchase event, plus your store's daily ordersAre browser and server events deduplicated? What's the match quality? Gap between Events Manager and store orders, in percent
7Which hooks win across all my ads?Ad level, 30 days, hook type in the ad nameGroup by hook type; compare spend-weighted ROAS and cost per purchase. Only groups with 3x target cost per purchase in spend
8What share of spend sits on 3 ads?Ad level, 30 daysShare of spend on the top 3 ads, and each one's ROAS against break-even
9Which age bands lose money?30 days, age breakdownSpend, purchases, cost per purchase and ROAS by age band; flag bands under break-even with over 10% of spend
10Did my last budget raise break anything?Campaign level, 30 days, by dayFind days spend jumped 20%+ over the prior 7-day average; compare cost per purchase 3 days after with 7 days before
11Which creatives are 30+ days old?Ad level, 30 days, plus each ad's launch dateAds launched over 30 days ago, share of spend, cost per purchase; the 3 to refresh first
12What is my real blended ROAS?Campaign level by day, plus Shopify sales by dayBy day and in total: store sales ÷ Meta spend next to Meta's reported ROAS, with the gap explained
13Which days of the week burn cash?Account level, 8 weeks, by dayCost per purchase by weekday; flag days 30%+ above average and say if there are enough purchases to trust it
14Which ads have the best thumb-stop?Ad level, 30 days, video: impressions, 3-second plays, ThruPlaysHook rate = 3-second plays ÷ impressions. Rank ads with 1,000+ impressions; what do the top 3 share?
15Are Reels or Feed cheaper per purchase?Ad set level, 30 days, placement breakdownCost per purchase in Reels vs Feed, Facebook and Instagram separately; only placements with 10+ purchases
16Which countries convert worst?Campaign level, 30 days, country breakdownRank countries by cost per purchase; flag those with over 5% of spend above 1.5x target
17Grade my campaign structure A to FCampaign and ad set level, 30 daysCount overlapping campaigns, ad sets under 50 purchases a week and ad sets whose names suggest the same audience; grade it in 5 lines
18Which landing pages lose the click?Ad level, 30 days: link clicks, landing page views, purchases, plus each ad's landing pageBy page: clicks, page views, purchases, click-to-view rate, purchases per click; flag the weakest
19Did iOS users stop converting?This month and last month, impression device breakdownCost per purchase by device across the two months; flag rises of 20%+
20Which ads to scale tomorrow?Ad level, last 7 days, with frequencyAds above target ROAS, frequency under 2.5, spend of 3x target cost per purchase; rank them for a 20% budget step
21What should my next 5 tests be?Ad level, 90 daysWhat separates the best and worst ads; 5 one-variable tests ranked by money at stake
22Am I bidding on cost cap too tight?Ad set level, 30 days: bid strategy, cap, budget, spendCost cap and bid cap ad sets: spend vs budget, cost per purchase vs cap; which are starved?
23Which audiences are exhausted?Ad set level, 8 weeks, by week: reach, frequencyAd sets with flat or falling reach for 2+ weeks while frequency rises, with their cost per purchase trend
24Where am I paying for clicks, not sales?Ad level, 30 days: link clicks, link CTR, purchases, spendAds with above-average CTR but under half the average purchases per click, with their spend
25Write my audit summary for my bossYour answers above, same chatA 10-line summary: grade, the 3 biggest leaks in dollars a month, the first 3 fixes. No new numbers

A few notes on the less obvious ones:

  • Prompt 4 uses Meta's learning phase. An ad set usually needs about 50 optimization events in 7 days to leave it (Meta: About the learning phase). Many small ad sets that never get there are a common, fixable leak.
  • Prompts 5 and 6 work from screenshots, because those views don't export cleanly. All three AIs read images. If your account no longer shows the audience overlap view, skip prompt 5.
  • Prompt 12 is the one owners care about most. Our Meta vs Shopify attribution guide explains why the two numbers never match and which one to budget on.
  • Prompt 7 only works if your ad names say what each ad is. If they don't, fix the naming first.

Check the AI's sums before you act

AIs are good at reading tables and bad at being reliably exact. Before you pause, cut or scale anything, re-do the one number the decision rests on.

Bar chart of a fictional 12-ad account's 30-day spend. The three biggest ads (Founder_story_15s $5,200, Review_carousel $4,100, UGC_unboxing_v4 $3,100) are dark. Three ads with zero purchases are red: UGC_hook3_v2 $1,020, Gift_guide_static $690, Carousel_bundle_v1 $430. Callouts: prompt 8, 62% of spend on 3 ads ($12,400 of $20,000); prompt 1, 3 ads spent $2,140 with 0 purchases.

Fictional account. The Check tab works these out with formulas from the same export.

In our worked example, the account spent $20,000 in 30 days across 12 ads. The workbook's Check tab, with the export pasted in, gives:

AnswerFormula result
Prompt 1: ads with zero purchases3 ads, $2,140
Prompt 8: share of spend on the top 3 ads62% ($12,400 of $20,000)
Account ROAS2.63 (break-even 2.5)
Cost per purchase$45.15 (target $40)

If the AI's number differs, ask it to list the rows it summed. The usual culprits are a totals row at the bottom of the export, a filter you forgot, or two exports with different attribution settings.

Log what you find

The Findings tab is one row per answer you'll act on: the prompt number, what the AI found, the dollars a month at stake, whether you checked the sum, the action, an owner and a status. Unchecked rows stay amber. Sort by dollars at stake and work top down.

In the example, the first three rows are the $2,140 on zero-purchase ads (checked, done), Audience Network at 9% of spend with no purchases ($1,800, still to check), and Sunday costs per purchase of $61 against $38 on weekdays (to check: are there enough Sunday purchases to trust it?).

Which AI should you use?

Any of the three. We haven't run a side-by-side test of Claude, ChatGPT and Grok on real accounts, so we won't claim one wins. What decides the quality of the answer here is the prompt and the file, and those are the same in all three. If you want the same audit run the same way every week, the Claude Meta Ads audit skill turns a fixed rubric into a reusable skill that grades every ad A to F.

Or let GaaS ask the questions

GaaS is an AI agent that creates, launches and optimises Meta and Google ads from three inputs: your website, a spend limit and a one-line goal. It reads your account directly, every day, and asks before anything that changes spend. If you'd rather run the audit yourself, the pack and workbook are free.

Limits

  • The AI only sees the file you attach. Anything not in the export (your margin, stock levels, a sale you ran) has to be in the prompt.
  • Ads Manager numbers depend on the attribution setting and are modelled in part. Platform-reported purchases rarely match your store's orders exactly.
  • The thresholds in the prompts (1.5x target, 4.0 frequency, 25% CTR drop, 20% budget jump) are our starting points, not Meta rules. Change them in the "What to ask" column.
  • Small numbers mislead. A weekday or country with 6 purchases can't prove much; prompts 13, 15 and 16 ask the AI to say so.
  • Don't paste customer names, emails or other personal data into an AI. Ads Manager exports don't contain them; Shopify exports can.

Sources

The Meta Ads audit skill for Claude: grade every ad A to F from one export

A free, open-source Claude skill that grades a Meta Ads Manager export: every ad scored out of 100 and graded A to F, an account grade, and one action per ad. Includes the full SKILL.md, install steps for Claude and Claude Code, a 10-ad worked example and a workbook that checks Claude's maths.

The Kill / Hold / Scale rulebook for Meta ads

Simple, exact rules for every Meta ad and ad set, built from your own margin: break-even ROAS, target CPA, a minimum-spend rule, scale steps, fatigue checks and a 10-ad worked example. Includes a workbook that gives each ad a verdict.

Meta says 120 sales, Shopify says 70: why they disagree and which number to trust

Meta and Shopify count sales from your ads differently, so their numbers never match. See the six reasons for the gap, a step-by-step bridge from one number to the other, and which number to use for which decision. Free Excel reconciler included.

The Monday report: 8 numbers to check every week

A 15-minute weekly ad check-in for business owners: MER, CAC, ROAS, hook rate, hold rate, frequency, CPM and CTR, plus spend vs budget. What each means, how to calculate it, where to find it, and what to do when it's off.

Have a correction or a question about the workflow? Contact GaaS. Read our editorial standards for sourcing and example conventions.