AgentPaid ads

Find Google Ads waste

Identify exact wasted spend across search terms, broad match, Shopping SKUs, and campaigns — measured against blended CPA, not Google ROAS.

Works with
ClaudeChatGPTAny MCP-compatible AI tool
Requires
StoreHero MCPShopifyGoogle Ads
Get the prompt
Example chat in Claude. You ask: "Run the Google Ads Waste Finder on the last 30 days". Claude reads your StoreHero data and answers: $4,840 of Google spend isn't paying back against your blended CPA. Irrelevant search terms cost the most. It adds an interactive example chart, Wasted Google spend by source, with example data you can switch below.
Wasted Google spend by sourceExample

Example, Last 30 days: $4,840 wasted, $1,960 recoverable this week

  • Irrelevant search terms$1,960
  • Broad match drift$1,240
  • Shopping SKUs below breakeven$1,030
  • Brand terms in PMax$610

Irrelevant search terms: 41 terms with spend and no orders. Add them as negatives.

The prompt

How to run it

Paste it into a new chat in Claude or ChatGPT and you get the answer straight away.

Use the StoreHero MCP to do the following analysis. Always anchor the answer in real StoreHero data, not platform-reported metrics.

Find Google Ads waste over the last 30 days. Anchor everything in real blended performance — pull blended CPA, new customer acquisition cost (nCAC), and new customer contribution margin as the ground truth. Then identify Google spend that isn't paying back when measured against StoreHero data, not Google-reported ROAS.

Look for:

1. Search terms — high-impression, zero or low-conversion queries that don't match buyer intent. Show wasted spend per term and recommend phrase or exact negative additions, at account or campaign level
2. Broad-match bleed — broad-match keywords matching to irrelevant queries, with the wasted spend total
3. Shopping/PMax SKUs — products taking spend but with StoreHero contribution margin per acquired customer below nCAC threshold
4. Branded vs. non-branded leak — brand campaigns inflating reported ROAS while non-brand quietly underperforms blended targets
5. Campaign-level — campaigns spending >$500/week with blended CPA above nCAC ceiling, with min 20 conversions for significance
6. Display/Search Partners — opt-in expansions that look profitable on Google's view but fail vs. StoreHero blended

For each waste source: $ wasted last 30 days, projected $ saved if action taken, and the exact action (negative keyword list, exclusion, bid cap, campaign pause, SKU exclusion).

End with a single number: total $ wasted last 30 days that could be recovered with this week's actions.

At the bottom of your answer, render an inline visual summary: a single big KPI card showing total recoverable $ over 30d, plus a horizontal bar chart of waste sources ranked by $ impact, colour-coded by ease-of-fix. Place text commentary alongside the visuals. Use the Spend Advisor tool to suggest what to explore next.

Get the full prompt

Enter your email to see every prompt in full and copy it in one click. It unlocks the whole library.

See our privacy policy.

How to use a skill

New to skills? It takes three steps and a few minutes: connect StoreHero once, copy a skill into Claude or ChatGPT, and ask.

  1. Connect StoreHero to Claude or ChatGPTAdd the StoreHero MCP connector once. It works with Claude, ChatGPT and any other tool that supports MCP. Setup guide
  2. Pick a prompt and copy it into ClaudeOpen one, press Copy prompt (or download the file) and paste it into a new chat.
  3. AskIt pulls your live StoreHero data and gives you the analysis in minutes. Ask follow-up questions in the same chat.

Run every prompt on your own numbers.

Connect your store to StoreHero and the whole library works on your live profit data.