Reading Ad Performance Data with AI
Paste raw campaign metrics and ask AI to find the story in the numbers — which angle, audience, or creative is actually winning, and what to do next..
The prompt
Here is last week's ad performance data (CTR, CPC, CPA, spend by ad set): [paste table]. Identify: (1) the best and worst performing ad set and why, (2) one clear action to take this week, (3) one thing to keep testing. Be specific, not generic advice.
What to replace
Swap these placeholders for your own details before running the prompt:
[paste table]your own value
Pro tip: Always ask for "one clear action" — open-ended analysis prompts tend to produce a wall of observations with no decision.
How to use this prompt
- Copy the prompt using the button above.
- Replace [paste table] with your own details — the more specific you are, the better the output.
- Paste it into Claude and run it.
- If the answer feels generic, add constraints: audience, length, tone, and what to avoid. That single change fixes most weak output.
Learn the technique
Reading Ad Performance Data with AI
Module 2 — Targeting & Performance Analysis · AI Ad Manager
Related prompts
Generating High-Variance Ad Sets — ChatGPT
Ad platforms reward variety for testing.
GrokGenerating High-Variance Ad Sets — Grok
Ad platforms reward variety for testing.
ChatGPTCreative Testing Systems (Not One-Off Tests)
Scaling accounts run a creative system: a backlog of angles ranked by hypothesis strength, batches of 3-5 new creatives weekly, and a kill/scale rule applied without emotion (e.g., kill under 0.8× account-average CTR after 2k impressions; scale winners into new formats).
ClaudeLanding Page ↔ Ad Message Match
Half of "ad fatigue" is actually message mismatch: the ad promises one thing, the landing page opens with another, and CVR dies.
ChatGPTProject: Design, Launch (or Simulate) and Read a Test
Deliverable: a complete documented ad test — real if you have an account, fully simulated if not. Steps: 1.
ChatGPTCold Email Opener Generator
Outbound sales / partnership outreach
Related across the site
AI Ad Manager
Generate ad copy variants at scale, brainstorm targeting angles, and use AI to analyze ad performance data for Google and Meta campaigns.
AI YouTube Management
Script videos faster, write titles and thumbnails that actually get clicked, and use AI to plan a channel content calendar and read your analytics.
Fine-tuning
Fine-tuning continues training a pre-trained model on your own examples to specialise its behaviour. It is the right tool for teaching consistent style, format or classification behaviour — not for adding knowledge.
Multimodal model
A multimodal model accepts or produces more than one type of data — commonly text plus images, and increasingly audio and video. It processes them in a shared representation rather than through separate pipelines.
Prompt injection
Prompt injection is an attack where malicious instructions hidden in content the model processes override the developer's intended behaviour. It is the most serious unsolved security issue in LLM applications.
The Wrong Chart Challenge
Deliberately visualise the same data four wrong ways to learn why the right one is right. Faster and more memorable than reading chart-selection guidance.