Documentation

Connect your marketing data to Claude, ChatGPT and other LLMs.

Workflow prompts — Meta Ads

Battle-tested workflows scoped to your data. Log in to launch them from the hub with your own account / campaign selection, or copy the resolved prompt into Claude, ChatGPT or Cursor.

The actual prompt templates are reserved to logged-in users with a connected Meta Ads account. They resolve to your real account / campaign IDs so the AI has the right context.

Open a connected account under /accounts/{id}/insights, then click "AI analysis" — pick a workflow template or write your own question. The AI answers with your live data.

Open my accounts → Create a free account

Each workflow below tells you the concrete problem it solves and the deliverable you get. The exact prompt is revealed once you're logged in.

1 — Morning ROAS check

The problem

You need a 2-minute daily scan to catch campaigns with fatigued creatives or dropping ROAS before budget is wasted.

What you get

ROAS / frequency / CPM summary with flagged campaigns (ROAS < 1.5 or frequency > 4).

2 — Creative fatigue scan

The problem

Creatives burn out after 1-2 weeks but you can't tell which ones to pause vs which to keep running.

What you get

List of ads with week-over-week ROAS drop > 30% + clear recommendation (pause or refresh).

3 — Audience breakdown ROAS

The problem

Your targeting is broad and you suspect some age/gender segments are ROAS killers — but can't prove it.

What you get

Top 3 winners + top 3 losers by ROAS with specific bid-adjust or exclusion recommendations.

4 — Placement optimization

The problem

Advantage+ placements mix Feed, Stories, Reels, Marketplace — some are expensive and bad at converting.

What you get

Placement-level performance with exclusion candidates (CPM > 2× avg AND ROAS below average).

5 — Budget shift recommendation

The problem

Hard to see momentum at the campaign level — who's rising, who's falling, where to reallocate.

What you get

Risers vs decliners classification + dry-run simulation of +50% budget on top risers.

6 — Ad set vs ad set comparison

The problem

Inside a single campaign, one ad set carries most of the performance but budget is spread evenly across all of them.

What you get

Winner identification + recommendation to pause underperforming ad sets (ROAS gap > 30%).

💡
Combine multiple MCP servers in the same Claude session for cross-channel analyses: "Compare my Google Ads vs Meta Ads ROAS over the last 30 days, by product category."
Need help? Ask me 💬
Ask gadspilot
Free AI assistant · Try me