AnalyticsGoogle Ads analysisIntermediateAnalyses 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.

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-search analyst. Analyse the search-terms export below for last 60 days. Business: a commercial cleaning service for small offices in Chicago. Target CPA (or margin-based limit): 60 USD. Conversion definition: a submitted quote request. Data (search term | cost | clicks | conversions | match type): Search term | Cost | Clicks | Conversions | Match type office cleaning service chicago | 310 | 140 | 9 | phrase cleaning jobs chicago | 95 | 60 | 0 | broad how to clean office carpet | 70 | 52 | 0 | broad commercial cleaners near me | 180 | 77 | 6 | exact Do this: 1. List your assumptions (currency, conversion counting, data completeness, whether terms with zero clicks are omitted). 2. Group terms into patterns (for example informational, job-seekers, competitor, free/DIY, wrong product, relevant) and show per group: cost, clicks, conversions and CPA computed from the rows. 3. Identify groups with spend and no or poor conversions, estimating spend at risk from the data only. Say how confident the estimate is given the volume. 4. Propose negative keywords with a suggested match type for each (broad, phrase or exact negative) and the reason; avoid broad negatives that could block relevant searches. 5. Provide a separate "do NOT negate" list of terms that look similar to wasteful ones but convert or show intent. 6. Suggest 3 relevant terms worth adding as keywords, if the data supports it. Rules: do not invent costs, conversion values or volumes. Missing or unavailable columns must be flagged, not guessed. Treat pattern-level findings as hypotheses, not proof of cause. Recompute every total and verify group sums match the data. A zero-conversion term with a few clicks is not proof of waste; explain the volume needed to judge it without stating a number as a fact.

Customize

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

Period.

What you sell.

Your acceptable cost per conversion.

Currency of cost.

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.

Pattern groups with computed spend, clicks, conversions and CPA; spend-at-risk with a confidence note; negative keywords with match types; a protected 'do not negate' list; terms to add. (Illustrative.)

Expected format: Assumptions, group table, negatives with match types, protected list, additions.

How to use it

  1. Review negatives manually before adding them.
  2. Start with the clearest irrelevant groups.
  3. Re-check after a few weeks.

Limitations

  • The model lacks your margins, offers and customer context; review every recommendation.
  • Over-negating can remove real demand; the protected list reduces but does not eliminate this.

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-009. We will correct or remove it.

Related prompts

  • AnalyticsIntermediateAnalyses 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.

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

  • AnalyticsIntermediateAnalyses your data

    Keyword structure and match-type audit

    Reviews keyword lists and match types for overlap, intent mixing and cannibalisation, with the data you need to confirm each finding.

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

  • AnalyticsAdvancedWrites SQL / queries

    Google Ads Query Language (GAQL) query builder

    Gets a GAQL query for a specific report, with explicit instructions to confirm field names, unit conventions and segment compatibility.

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

  • 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)