← Portfolio
A
AskGTMAI-Powered

GTM Performance Intelligence

Ask plain-English questions about pipeline, bookings, rep performance, and churn · Powered by Claude

Smart Summary — Q1 2025
📈 Q1 vs Q4 Bookings
Won revenue up 3.3% quarter-over-quarter.
🏆 Top Producer
Chen leads with $885K in closed-won ACV (8 deals).
🎯 Best Specialty
Ophthalmology has the highest win rate at 55% across 80 deals.
⚠️ Churn Watch
Gastroenterology has the highest churn at 9.1%. Top reasons: Switched to competitor, Budget cuts.
Quarterly Won Revenue
Q3 2024Q4 2024Q1 2025
Try asking
Powered by Claude API · Queries synthetic Salesforce-style GTM data (280 deals, 6 reps, 4 specialties)
How this works — architecture & limits

Grounding: The server-side system prompt contains a flattened text summary of the synthetic GTM dataset (deals by rep × specialty × source × quarter, the marketing funnel, churn cohorts). Claude reasons over the summary directly — no tool use, no SQL generation, no vector retrieval. The Smart Insights tiles above use the same seeded dataset client-side so the panel and the assistant stay aligned.

In production: this would be a tool-using agent over a governed metric registry (the kind documented in NorthStar). The assistant would issue queries against live warehouse tables; the metric definitions in the registry would constrain what aggregations and joins it can perform, so two analysts asking the same question always get the same answer. Text prompt-stuffing is a demo simplification, not the recommended pattern.

Limits: Synthetic data only — questions outside the dataset (e.g. "what's our YoY ARR?") will get a polite "I don't have that data" response. Rate-limited to 10 requests per IP per minute. The system prompt lives server-side and never accepts client-supplied overrides.