AI Stack for Campaign Performance Analysis

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

Campaign performance analysis usually happens at two moments: when you launch, to see if it's working, and when leadership asks, to explain what happened. Neither is proactive. This stack runs a structured cross-channel performance analysis on a regular cadence — covering paid media and marketing automation in a single pass. Pull data from Google Ads, LinkedIn Ads, and Marketo, run the combined view through a weekly performance prompt, and produce a campaign debrief ready to log in Notion and share with stakeholders before they have to ask.

The Stack

Input
Google Ads LinkedIn Ads Marketo
AI
Claude
Output
Google Sheets analysis Notion debrief

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 demand generation analyst producing a cross-channel campaign performance debrief.

Review the performance data from Google Ads, LinkedIn Ads, and Marketo provided below.
For each channel, report: spend, CPL, MQL volume, and week-over-week conversion rate trend.
Identify the campaigns generating the most pipeline-qualified leads across all channels in the period.
Flag any campaigns showing performance decay over the past 4 weeks — sustained decline vs. single-week anomaly.
End with a campaign debrief summary including 3 specific actions for the next campaign cycle.
[ ... continued — see full prompt ]

The Workflow

  1. Export paid media performance

    Pull the past 30 days of campaign performance from Google Ads and LinkedIn Ads — spend, clicks, CPL, and conversion volume by campaign. Include a 4-week trend for each metric.

  2. Export Marketo program performance

    Pull email engagement and program conversion data from Marketo for the same period — open rates, click rates, and lead progression by program.

  3. Align on a shared MQL definition

    Before combining the data, confirm the MQL definition used across all three sources is consistent. Map Marketo program conversions to Google Ads and LinkedIn Ads lead events.

  4. Run the campaign performance prompt

    Paste the combined dataset into the Weekly Paid Media Summary prompt adapted for cross-channel debrief. Claude produces a channel-by-channel analysis with decay flags and top performers identified.

  5. Log the debrief in Notion

    Save the Claude output as a campaign debrief in Notion — with the period, key findings, and action items for the next cycle. Post the summary to Slack for stakeholder visibility.

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