AI in Production: Key Lessons
summary
Sixsense runs tens of terabytes with ~27 months of history and a Spark + homegrown ML stack and reports lower TCO after consolidating onto SingleStore. Built three production features: AI insights — 30/60/90-day account summaries that load in seconds by pulling six months of events from SingleStore; email writer — generates personalized outreach from account signals; Sherlock — ingests docs as vectors, uses OpenAI to compose answers, rolled out internally and moving to customers.
AI-written summary · about
chapters (7)
- 0:00Introduction and company overview
- 3:16How Sixense collects and uses data
- 8:22Database consolidation with SingleStore
- 9:06AI insights for sales teams
- 10:51AI-powered email writer
- 12:22Sherlock AI support bot
- 15:13Performance and future AI enhancements
related talks
56mAI War Stories: Real world learnings delivering enterprise AI solutions
33mEngineering AI Applications: A Conversation with AI Leaders
50mTake AI/ML from theory to practice with Intel technologies
40mInsights and Key Learnings on Our AI Journey
01h 44mHow to build world-class AI products
49mHow to be an AI First company
58mAI in Reality Fireside Chat: Enterprise AI & Open‑Source Innovation
36mBeyond the Hype