AI Stack for Paid Media Reporting

Google Ads API + LinkedIn Ads API → Claude → Slack + Sheets
Matt Danese
Senior Demand Generation Manager. These stacks are built and used in production — not generated for a listicle.

Most paid media reporting is a manual slog — export the data, paste it into a spreadsheet, write the narrative, format the deck. This stack replaces that loop with a structured workflow. Pull your actual campaign performance from Google Ads and LinkedIn Ads, run it through a Claude prompt designed for weekly paid media analysis, and post the formatted summary to Slack before your first Monday call. No template maintenance. No reformatting. You review the output — you don't build it from scratch every week.

The Stack

Input
Google Ads API LinkedIn Ads API Google Sheets
AI
Claude
Output
Slack Google Sheets

The Prompt

This stack is built around the Weekly Paid Media Summary Prompt. Here's the abbreviated version — the full prompt with all variables and usage notes is on its own page.

Claude Prompt — Abbreviated
You are a B2B paid media analyst preparing a weekly performance summary.

Review the channel data below and produce a structured weekly summary.
For each active channel, report: total spend, CPL, MQL volume, and trend vs. prior week.
Flag any anomalies — cost spikes, conversion drops, or CTR outliers — that require action.
Identify the top-performing campaign and the campaign most at risk.
End with 3 specific, concrete recommendations for the coming week.
[ ... continued — see full prompt ]

The Workflow

  1. Export channel data

    Pull the past 7 days from Google Ads and LinkedIn Ads — spend, clicks, conversions, CPL by campaign. Include prior-week data for trend comparison. Export as CSV or pull via the Ads API.

  2. Populate the prompt template

    Paste the raw data into the Weekly Paid Media Summary prompt. Add any context you know upfront — budget changes, new campaigns launched, known tracking issues.

  3. Run the prompt

    Submit to Claude. The prompt structures the analysis, flags anomalies, identifies top and at-risk campaigns, and produces a channel-by-channel summary with trend callouts.

  4. Review and correct

    Scan the output for hallucinations or miscalculations — especially CPL math. Adjust any numbers that need correction before distribution.

  5. Distribute the summary

    Paste the formatted output into your Slack reporting channel. Tag relevant stakeholders. Flag any items that need a discussion or decision this week.

What This Replaces

Related Stacks

New stacks drop weekly.

Each one includes the tools, the Claude prompt, and the workflow logic. Free — built for in-house B2B demand gen managers.

← Back to Stack Library

© 2026 The Demand Engineer · thedemandengineer.com