AnalyticsGoogle Ads analysisIntermediateAnalyses your data

Google Ads campaign diagnostic against CPA or ROAS targets

Compares campaigns against your target, separates volume, efficiency and conversion-rate drivers, and highlights what the data cannot explain.

For: Performance marketers, Marketing analysts, Growth marketers · Works with: Google Ads, Any capable chat model (ChatGPT, Claude, Gemini, others)

Public beta. This prompt was drafted with AI assistance and checked by automated rules, but it has not been reviewed or tested by a person yet. Treat it as a starting point and check the output. It is hidden from search engines while in beta. Use the “Was this prompt useful?” box to tell us what works.

Your prompt

Act as a paid-media analyst. Diagnose campaign performance for 1-31 Aug 2026 against the target of CPA of 45 or ROAS of 4.0 using ONLY the data below. Currency: USD. Conversion definition: purchase conversion action with every-conversion counting. Data (campaign | cost | impressions | clicks | conversions | conversion value): Campaign | Cost | Impressions | Clicks | Conversions | Conv value Brand | 1200 | 40000 | 4100 | 150 | 11000 Non-brand search | 5200 | 210000 | 6900 | 85 | 9500 Performance Max | 3800 | 380000 | 5200 | 70 | 8300 Tasks: 1. State assumptions (for example whether conversion value is revenue or margin, and any data you suspect is incomplete). 2. Compute for each campaign: CTR, CPC, conversion rate, CPA and ROAS, from the raw columns only, and show the formulas. 3. Decompose gaps to target into drivers: traffic cost (CPC), click-to-conversion (conversion rate), and value per conversion. Show which driver explains the most difference. 4. Flag campaigns whose volume is too small for reliable conclusions. 5. Suggest 3-5 next checks as hypotheses (search terms, audience, bidding, landing page, tracking), with the specific report to pull for each. 6. List data that is missing for a full diagnosis (impression share, device split, time period over time). Rules: do not invent benchmarks, quality scores or auction data. If a column is missing or not provided, say so. Verify arithmetic by recomputing totals. Keep correlation and causation separate.

Customize

The fields start with example values so you can see how the prompt works. Everything stays in your browser.

Period.

Your goal.

Currency.

What counts.

Paste your table. The default is small fictional sample data so the preview works; replace it with your own export.

Example of what to expect

Illustrative only. It describes the kind of result this prompt aims for; real output varies by tool, model and run.

Computed CTR, CPC, conversion rate, CPA and ROAS per campaign, a driver decomposition of the gap to target, low-volume flags, hypotheses with the report to pull for each, and missing data. (Illustrative.)

Expected format: Assumptions, metrics table, driver decomposition, hypotheses, missing data.

How to use it

  1. Use consistent definitions across campaigns.
  2. Pull the suggested reports to test hypotheses.
  3. Recompute headline metrics yourself.

Limitations

  • Brand and non-brand campaigns are not directly comparable; interpret with care.
  • Platform attribution may differ from your backend numbers.

Platform notes

Google Ads

Official docs read · checked 2026-10-11

Google Ads field names and units (for example cost expressed in micros in the API) must be confirmed in Google's reference; the GAQL overview page we read does not list them.

General notes on Google Ads
  • GAQL uses SELECT/FROM/WHERE/ORDER BY/LIMIT. Confirm resource and field names (for example cost fields, which are expressed in micros) in the API reference; the overview page does not list them.

Any capable chat model (ChatGPT, Claude, Gemini, others)

Official docs read · checked 2026-10-11

Works in any capable chat model. Paste a small anonymised export and recompute the key numbers yourself: chat models can misread columns or miscalculate.

General notes on Any capable chat model (ChatGPT, Claude, Gemini, others)
  • These prompts are plain text and work in any chat assistant. For analytics prompts, paste a small, anonymised export; a chat model can misread columns or miscalculate, so recompute key numbers yourself.

Source, license and attribution

Origin
Original by MarketerTools
Publisher
MarketerTools
License
Original work by MarketerTools, free to copy and use. Informed by the linked documentation; no third-party text is reproduced.
Platform assumptions checked
2026-10-11

Documentation and references behind this prompt

These informed the structure and the platform notes. A reference is not a license, and no third-party prompt text is copied here.

Spotted an attribution error, or are you a source owner with a request? Use the chat button at the bottom right and quote prompt ID ana-010. We will correct or remove it.

Related prompts

  • AnalyticsIntermediateAnalyses your data

    Google Ads search-terms report: wasted spend and negative keywords

    Groups search terms by pattern, estimates wasted spend from your data and proposes negatives, with a protected 'do not negate' list and match-type cautions.

    Google Ads · Any capable chat model (ChatGPT, Claude, Gemini, others)

  • AnalyticsIntermediateAnalyses your data

    Budget pacing and impression-share analysis

    Checks whether a budget is on pace for the month and whether lost impression share is budget-limited or rank-limited, using the figures you provide.

    Google Ads · Any capable chat model (ChatGPT, Claude, Gemini, others)

  • AnalyticsIntermediateAnalyses your data

    ROAS vs contribution margin: break-even and target ROAS

    Translates ROAS into profit terms using margin and variable costs, so a campaign is judged against break-even rather than a generic ROAS target.

    Any capable chat model (ChatGPT, Claude, Gemini, others) · Google Sheets / Excel

  • AnalyticsIntermediateAnalyses your data

    Responsive search ad asset performance review

    Reviews headline and description asset reports for patterns and proposes new assets, while flagging how little asset-level data can prove.

    Google Ads · Any capable chat model (ChatGPT, Claude, Gemini, others)