Documentation

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

Workflow prompts — Google 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 Google 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 check (5 min)

The problem

You need a quick daily health check to spot campaigns that need attention before spending more.

What you get

A ranked list of campaigns flagged by low ROAS, impression share lost to budget, or abnormal pacing — sorted by spend.

2 — Search term audit (waste hunt)

The problem

Wasted spend on irrelevant queries — job seekers, competitors, informational searches with zero intent to buy.

What you get

Categorized waste report + ready-to-paste negative keyword list at the right level (campaign or ad group).

3 — Quality Score diagnostic

The problem

Low Quality Score keywords are silently inflating your CPC — but you don't know which lever (CTR, ad relevance, landing page) to pull first.

What you get

Top 10 keyword fixes ranked by impact = (CPC saving) × (impression volume), grouped by root cause.

4 — Budget pacing

The problem

Some winning campaigns are capped by budget while losing ones keep burning cash — you need to rebalance.

What you get

A 3-bucket classification (cap-starved winners / overspending losers / rank-limited) + revenue projection if budgets shifted.

5 — CPA spike root cause

The problem

Cost per acquisition suddenly jumped and you need to find out what changed — settings, audience, device mix, external factor.

What you get

Top 3 contributing factors with impact percentage, cross-referenced with the change history (who touched what, when).

6 — RSA ad strength audit

The problem

Ads with Poor/Average strength are bleeding impressions, and you don't know which ad groups lack creative variation.

What you get

Flagged underperformers + specific headline/description improvement suggestions per ad group theme.

7 — Auction insights

The problem

You're losing impression share but don't know if it's a budget issue or a competitive ranking issue — bidding blindly.

What you get

Per-campaign bid direction (increase / decrease / hold) + top 3 competitor domains across your account.

8 — New campaign buildout

The problem

You need to launch a new Search campaign from scratch with proper themed ad groups, match types, and RSA copy.

What you get

A ready-to-review JSON plan (4-6 ad groups × 3 match types × 15 headlines × 4 descriptions) in dry-run mode.

💡
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