Prompt Almanac

Audit intermediate Works with: Any AI

Meta Ads Audience Overlap and Targeting Audit

Table output Has example

Check whether audiences compete or exclude too much.

Open in ChatGPTOpen in Claude

The Open buttons send the prompt text as currently shown below to that site only when you click. Fill in the placeholders first.

[VERIFY] is an editorial flag, not a blank to fill. Wherever the prompt shows [VERIFY], check that item against a reliable source before you use it.

Rate this prompt

Loading ratings…

Audit audiences in Meta ads. Ad sets with targeting (locations, ages, interests, custom audiences, exclusions), audience sizes, spend and results: [AD_SET_DATA].

Check for overlapping ad sets competing in the same auctions, which can raise costs [VERIFY]; audiences too narrow to learn from; missing exclusions (customers, recent leads); vague interests; poor lookalike sources; and delivery problems. Show spend share by audience and cost per result, with sample sizes, and avoid conclusions from tiny audiences. Example (invented): ad set 1 with 120,000 people, spend 210 and 21 results is 10.00 per result.

Propose a simpler structure and tests, one change at a time. Interest options and categories change and have rules, including special categories [VERIFY]. Treat every cost, rate and volume as an assumption to test. Return a table. Rank the changes by how much spend they affect, and say which single change to make first. If the audiences I gave are too few to judge overlap, list the extra information you need, such as audience sizes and the exclusions in place, rather than guessing.

Fill in before use

Optional: type your details and the prompt above updates. Nothing is saved or sent.

Replace each bracketed placeholder with your own details, then paste into Any AI or another assistant.

See an example result (fictional data)
Invented account. Ad set 1: interests A, 120,000 people, spend 210, results 21, cost per result 10.00. Ad set 2: interests B, 140,000 people, spend 190, results 14, cost 13.57. Estimated overlap between the two: 55 percent [VERIFY with the platform tool]. Ad set 3: lookalike from customers, 2,000,000 people, spend 150, results 8, cost 18.75. Exclusions missing: customers and recent leads.
Action: merge sets 1 and 2 into one with a combined budget, add exclusions, test the lookalike at a narrower size. Spend shares: 38, 35, 27 percent.

Illustrative only, made-up data. Your results will differ and must be reviewed.

Related prompts