Audit a Google Ads search term report to cut waste
Search term reports reveal where budget leaks — but manually categorising hundreds of terms is slow and inconsistent. This prompt structures the analysis and produces a prioritised action list.
You are a PPC analyst. I'm pasting in a Google Ads search term report for the campaign {{CAMPAIGN_NAME}}. The campaign goal is {{CAMPAIGN_GOAL}} (e.g. lead generation, e-commerce purchases).
Search term data:
{{SEARCH_TERM_DATA}}
1. Categorise every search term into one of four buckets:
- Convert: terms with conversions that are relevant to the campaign goal
- Test: terms with clicks but no conversions yet — could be viable with more data
- Irrelevant: terms clearly outside the intended audience or offer
- Cannibalise: terms that should be in a different campaign or ad group
2. From the 'Irrelevant' bucket, extract the root words or patterns that are generating the most wasted spend. Format these as negative keyword recommendations (exact match, phrase match, or broad match negative — specify which and why for each).
3. From the 'Convert' bucket, identify any terms not currently in the keyword list as exact match — these are candidates to add for more control over bids.
4. Write a 3-bullet summary of the biggest issues found, quantified by spend or impressions where the data allows.
Note: This analysis is most useful if the report covers at least 30 days and 100+ clicks. Smaller data sets will produce unreliable patterns. {{CAMPAIGN_NAME}}{{CAMPAIGN_GOAL}}{{SEARCH_TERM_DATA}}
How to use this prompt
- Copy the prompt above (Copy button on the top-right).
- Replace each
{{VAR}}with your own value. Variables:{{CAMPAIGN_NAME}}{{CAMPAIGN_GOAL}}{{SEARCH_TERM_DATA}}. - Paste it into one of the recommended tools below.
- Iterate: tighten constraints in the prompt if the output is generic.
Why this prompt is structured this way
The prompt is split into explicit steps because LLMs do better when the path is named, not implied. Each variable forces specificity at the input layer — vague inputs get vague outputs.
Pair this prompt with a tool
Anyword
$49/moPredictive copy scoring trained on conversion data.
Anyword scores every line of copy for predicted conversion based on a massive dataset of ad and landing-page outcomes. Best-in-class for performance marketers.
Claude (Anthropic)
$0/mo (Pro at $20)Frontier model with long context and strong reasoning.
Claude (Opus / Sonnet / Haiku tiers) is the assistant favored by writers and engineers who care about reasoning quality and tone. 1M token context on Opus.
ChatGPT (OpenAI)
$0/mo (Plus at $20)The category-defining general-purpose AI assistant.
ChatGPT has the broadest feature surface: image gen, voice, custom GPTs, web browsing, code execution. Often the right default; sometimes beaten on specific tasks by Claude or Perplexity.
Jasper
$39/moEnterprise-grade marketing AI with brand-voice controls.
Jasper is built for marketing teams that need on-brand output at scale. Strong template library, decent brand-voice fine-tuning, plugs into Surfer for SEO.
The PlaybookPrompts weekly
One short email per week. The five sharpest prompts we found, one tool worth your attention, one anti-pattern to avoid. Unsubscribe in one click.
Newsletter signup is not configured. Set PUBLIC_NEWSLETTER_USERNAME in the build env.