AI Stack for Demand Gen Planning

Most quarterly demand gen plans are built by reviewing last quarter's numbers, adjusting a spreadsheet, and rerunning the same channel mix with a slightly different budget. The result is a plan that's disconnected from pipeline math and doesn't account for which channels actually produced pipeline at what cost. This stack builds a quarterly plan from the data that matters: current pipeline coverage, historical channel performance, and the budget you have to work with. Claude does the synthesis — channel allocation, program recommendations, expected pipeline contribution — and outputs a structured framework you can model in Google Sheets.

The Stack

The Prompt

This stack is built around the Pipeline Gap Analysis Prompt. Here's the abbreviated version — the full prompt with all variables and usage notes is on its own page.

You are a B2B demand gen strategist building a quarterly plan from pipeline data.

Using the Salesforce pipeline data, historical channel performance, and available budget
below, generate a quarterly demand gen plan with:

1. Pipeline gap this quarter needs to close (vs. current forecast and quota)
2. Channel mix recommendation with rationale (based on historical CPL and close rates)
3. Program type recommendations by channel with expected pipeline contribution
4. Budget allocation by channel and program type
5. Month-by-month pipeline build expectation
6. Key assumptions (close rate, ASP, MQL-to-SQL rate by channel)

The Workflow

1. Pull pipeline data from Salesforce

   Export current pipeline by stage, pipeline-to-quota coverage ratio, pipeline by segment and rep, and new pipeline created in the last 30/60/90 days versus the same period last year. This establishes the gap Claude needs to plan against.

2. Pull historical campaign performance

   Export the last two to four quarters of campaign data: channel, program type, spend, leads generated, MQL-to-SQL rate, pipeline influenced, and cost per pipeline dollar. Use actuals from your CRM — not estimated attribution.

3. Document available budget and hard constraints

   Total budget for the upcoming quarter, any locked commitments (events already paid, contracts in place), headcount limits that affect execution capacity, and channels that are off the table for any reason.

4. Paste pipeline data, historical performance, and budget into the prompt

   Give Claude all three inputs together. Claude generates a quarterly plan: recommended channels, program types, budget allocation by channel, expected pipeline contribution per program, and a month-by-month pipeline build across the quarter.

5. Build the model in Google Sheets and validate with finance

   Move Claude's output into Google Sheets. Adjust the close rate, ASP, and channel mix assumptions to match your targets. Validate the pipeline math with your finance partner before presenting the plan as your operating baseline.

What This Replaces

• Quarterly planning that copies last quarter's channel mix without tying it to pipeline math
• Budget allocation decisions made without benchmarking against historical cost per pipeline dollar
• Planning decks that don't document the close rate and ASP assumptions that drive the pipeline projection

Related Stacks

• AI Stack for Pipeline Gap Analysis →
• AI Stack for Demand Gen Forecasting →
• AI Stack for Campaign Brief Creation →