Building GTM AI Agents: Lessons from Deploying to 6,000 Users
- Day
- Day 4 — Session Day 3 · Thu, Jul 2
- Time
- 3:20pm-3:40pm
- Room
- Track 6 · Room 2014
- Track
- AI in GTM
AI in GTM — practitioner talks from Clay, Notion, Ramp, Exa, Cloudflare and others on go-to-market with AI.
Accessible with the Engineering pass and above.
About this session
Building an enterprise AI agent for GTM teams isn't just an LLM problem—it's a product, engineering, and adoption challenge. In this session, I'll share how we built and scaled Snowflake's internal GTM AI Assistant from MVP to a production system serving more than 6,000 employees and answering over one million questions. We'll cover how we scoped the MVP, evolved the architecture over time, balanced quality versus coverage, adopted emerging technologies like MCP, and continuously adapted as the AI landscape rapidly changed. You'll leave with practical lessons for building enterprise AI products that users actually trust and use.
