AI Stack for Marketing ROI Reporting

Salesforce + ad spend data + GA4 → Claude → ROI summary Google Slides + Slack
Matt Danese
Senior Demand Generation Manager. These stacks are built and used in production — not generated for a listicle.

Calculating marketing ROI sounds simple. In practice it means pulling from at least three systems, reconciling attribution models that contradict each other, defending assumptions that get challenged every time, and presenting the result to an audience that will immediately ask why the number doesn't match what they saw in a different dashboard. This stack automates the painful part: pull the data, run it through a Claude exec summary prompt that connects spend to pipeline to revenue, and produce a defensible ROI narrative you can post to Slack and present in slides without spending four hours building it.

The Stack

Input
Salesforce pipeline + revenue Ad spend data GA4
AI
Claude
Output
ROI summary Google Slides Slack report

The Prompt

This stack is built around the Exec Summary Generator 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 marketing analyst preparing a marketing ROI report for leadership.

Review the marketing spend, pipeline attribution, and closed revenue data below.
Calculate overall marketing ROI and ROI by channel.
Connect spend to pipeline generated and pipeline to closed revenue.
Identify the 2–3 channels with strongest ROI and flag any channel where spend is not
producing attributable pipeline. End with 3 specific recommendations.
[ ... continued — see full prompt ]

The Workflow

  1. Export total marketing spend for the reporting period

    Pull ad spend by channel from your ad platforms plus any program spend (events, content, tools). This is the denominator — get it right before building the model.

  2. Pull Salesforce pipeline and closed-won data

    Export marketing-sourced and marketing-influenced pipeline and revenue for the same period. Include both first-touch and multi-touch fields if your instance tracks them.

  3. Add GA4 conversion data

    Pull marketing-sourced sessions, form fills, and conversion rates by channel from GA4. This bridges the gap between ad platform data and CRM revenue.

  4. Run through the Exec Summary Generator prompt

    Paste all three datasets with ROI reporting framing. Claude calculates overall and channel-level ROI, connects spend to pipeline to revenue, and produces a narrative with recommendations.

  5. Build the slide deck and post to Slack

    Use Claude's structured output to build the Google Slides deck — one section per channel plus an overall summary. Post the executive summary paragraph to your leadership Slack channel before the meeting.

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