AI Stack for Pipeline Gap Analysis

"We need more pipeline" is not a diagnosis — it's a symptom. A pipeline shortfall can be a volume problem, a velocity problem, a deal mix problem, or a conversion problem. Each requires a different response. Throwing more spend at a conversion problem doesn't help. Adding more pipeline to a velocity problem just means more deals stalling at the same stage. This stack runs the actual diagnosis. Pull your Salesforce pipeline, close rates by stage and segment, and quota data. Feed them into Claude and get back a structured analysis that identifies where the breakdown actually is — and recommends the specific lever that will move the number.

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 revenue analyst diagnosing a pipeline shortfall.

Using the Salesforce pipeline data, historical close rates, and quota data below,
diagnose the gap. Classify the primary problem as one of:

- Volume problem: not enough pipeline entering the funnel
- Velocity problem: deals are stalling in a specific stage
- Mix problem: the wrong deal types or segments are dominating pipeline
- Conversion problem: pipeline-to-close rate is below the model assumption

For the primary problem type, identify the specific stage or segment where the
breakdown is occurring and recommend the single most impactful lever to pull.

The Workflow

1. Pull pipeline data from Salesforce

   Export total 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 prior year. This gives Claude the volume and velocity picture.

2. Pull historical close rates by stage and segment

   Export win rate by stage, average sales cycle length by segment, average deal size by lead source, and what close rate assumptions your current forecast model is using versus what's actually happening.

3. Pull quota and forecast data

   Document the current period quota, what's already closed, what amount needs to come from existing pipeline to hit the number, and whether there's an end-of-period concentration that might distort the conversion rate.

4. Paste pipeline, close rates, and quota data into the prompt

   Give Claude all three datasets together. Claude diagnoses the gap type — volume, velocity, mix, or conversion — and identifies the specific stage or segment where the breakdown is occurring. One root cause, not five contributing factors.

5. Implement the recommended action in Notion

   Take the single most impactful recommended lever and build it into a Notion action plan with owner, timeline, and success metric. Fixing one real problem beats half-measures on three.

What This Replaces

• Pipeline reviews that conclude with 'we need more pipeline' without diagnosing why the gap exists
• Coverage ratio analysis that doesn't account for the close rate assumptions baked into the forecast model
• Gap responses that treat a velocity or conversion problem as a volume problem and add spend instead of fixing the funnel

Related Stacks

• AI Stack for Demand Gen Planning →
• AI Stack for Demand Gen Forecasting →
• AI Stack for Campaign Brief Creation →