Skip to content

Daily losing ad cutter

Checks yesterday's ad results every day and lists the ads that cost too much. You approve which ones to turn off and which winners get more budget.

MarketingWorks with Claude Code · Claude Desktop with MCP+1Community example
Build your promptSee requirements

What it does

  • Pulls ad results from your ads account or data warehouse
  • Ranks ads by cost per result and CPM
  • Lists losers past your cutoff
  • Lists winners worth moving to a bigger campaign

Your approval boundaries

Creates drafts

These actions always wait for your yes:

  • Turning off any ad
  • Moving or raising any budget

You decide what happens next.

More about this workflow

This setup is for marketers and solo creators who need steady output without losing their voice. It takes a repeat chore off your plate and hands back something you can check quickly.

First, it pulls ad results from your ads account or data warehouse. Next, it ranks ads by cost per result and CPM. Then it lists losers past your cutoff. Finally, it lists winners worth moving to a bigger campaign. It works with your ads manager, analytics and spreadsheets, each on its own login with limited access.

You get the prep work done and waiting for you. The agent stops and asks for your yes before turning off any ad and moving or raising any budget, and says plainly if a step cannot be undone.

“turn off losing ads based on the data analysis”
Cody Schneider @codyschneider · Feb 20, 2026
Before you startAds manager · Analytics accessScoped permissionsClaude Code or Claude Desktop with MCP
Explore required tools and model recommendations

Tools and access

  • Ads manager

    Handles the ads manager part of this job. Grant read-only reporting access.

    API required: Yes. Ad platforms need a developer app and approved access to read reports.

    No sign-up needed

  • Google Analytics

    Handles the analytics part of this job. Grant Viewer role.

    API required: Yes. Needs a Google Cloud project with the Analytics Data API and an OAuth app or service account.

    Sign up: Google Analytics

  • Google Sheets

    Handles the spreadsheets part of this job. Grant access to the single sheet it needs.

    API required: Yes. Needs a Google Cloud OAuth app or a service account with the Sheets API turned on.

    Sign up: Google Workspace

Official links only. Not sponsored, no affiliate links.

Model recommendations

Best pick

GPT-6.1 Sol

Strong general writer at a mid price.

$2 per million input tokens, $10 per million output tokens, for prompts up to 272K tokens. Longer prompts cost $4 in and $15 out.

OpenAI docs as of October 11, 2026

Cheaper backup

GPT-6 Luna

Very low cost for first drafts and digests.

$0.10 per million input tokens, $0.50 per million output tokens, for prompts up to 272K tokens.

OpenAI docs as of October 11, 2026

Our own picks. Not sponsored, no affiliate links.

Build your prompt

Add your details, then copy the prompt into your tool.

1Your details

Fill these in and the prompt updates as you type.

e.g. CPM over $40

e.g. 8 AM daily

2Your prompt

4 of 4 still empty
Fill these in before you run it: [YOUR ADS ACCOUNT] [CUTOFF FOR A LOSER: e.g. CPM over $40] [MIN SPEND BEFORE JUDGING] [WHEN TO RUN: e.g. 8 AM daily] You are the Daily losing ad cutter agent. Checks yesterday's ad results every day and lists the ads that cost too much. You approve which ones to turn off and which winners get more budget. Use only the details filled in above. If any [BRACKETED] item is still blank or unclear, stop and ask for it first. Do not guess. What you do on your own: - Pulls ad results from your ads account or data warehouse - Ranks ads by cost per result and CPM - Lists losers past your cutoff - Lists winners worth moving to a bigger campaign What you must never do without a yes from a person: - Turning off any ad - Moving or raising any budget Rules: - Before any step on the list above, stop and ask. Say in plain words what you want to do, who it affects, and whether it can be undone. - If something cannot be undone, say so first, in one short line. - Write drafts, not final actions. A person sends, pays, posts, or deletes. - Keep a short log of every action you took and every source you read. - If you are unsure, ask instead of guessing.
View run instructionsPaste into: Claude Code, Claude Desktop with MCP, n8n

Your answers stay in this browser only.

Run your workflow

Connect your tools with only the access this setup needs, then follow these steps.

Steps

Do these in order. Test on old data before it touches live work.

  1. 1Set up Ads manager. Keep it to read-only reporting access.
  2. 2Connect Google Analytics with its own login, not yours. Grant Viewer role.
  3. 3Connect Google Sheets with its own login, not yours. Grant access to the single sheet it needs.
  4. 4Paste the prompt where your harness takes instructions. See the note under the Copy button.
  5. 5Do a dry run on old or test data first. Check every draft and every stop point by hand before you let it near live work.
  6. 6Read its log after the first real run. Only widen access once a week of runs looks clean.

Safeguards and trust score

The score describes this example setup’s access, approval boundaries, ability to undo changes, and scope.

Access24 / 30

Writes drafts and notes inside your tools, nothing leaves on its own.

Human approval30 / 30

Waits for a yes on: turning off any ad, moving or raising any budget.

Undo and logs14 / 20

Proposes changes to live records, so the setup needs a change log and a way back.

Scope16 / 20

Runs on its own login across 3 tools. Fewer connections means a smaller blast radius.

How to raise it

  • Undo and logs: Stop it from editing live records. Have it write the change as a proposal you apply, and keep a log of every change with a way to roll it back +3
  • Scope: Cut it down from 3 connected tools to the 2 it needs most, each with its own limited login instead of your full account +2

Do all of these to reach 89, up from 84.

Want help getting there? Get an AI Trust Audit from Pixeldesigns

Reviewed by Trustcase (example setup). How scoring works

Embed badge

Show this trust score on your site or README. It links back here.

Trustcase trust score badge
Markdown
[![Trustcase trust score for Daily losing ad cutter](https://trustcase.dev/badge/daily-losing-ad-cutter.svg)](https://trustcase.dev/use-cases/daily-losing-ad-cutter)
HTML
<a href="https://trustcase.dev/use-cases/daily-losing-ad-cutter"><img src="https://trustcase.dev/badge/daily-losing-ad-cutter.svg" alt="Trustcase trust score for Daily losing ad cutter" height="20"></a>

More marketing workflows

  • Weekly marketing report digest

    Reads the week's marketing reports, decks and meeting notes, and tells you what actually changed. It keeps a log so slow trends stand out.

  • New page internal link suggester

    Once a week it finds the pages you published and suggests where your older pages should link to them. You approve the links before they go live.

  • One idea to a full post package

    Turns rough notes or a draft into a folder of ready to review posts, a blog draft and images for each platform. Nothing is published for you.

  • Review request texts after a sale

    When a sale or service is marked done, it waits two days and texts the customer a link to leave a review, then one reminder. It checks opt outs first and tells the owner if a text fails.