Alex Hancock

When home-brewing pioneer Pinter scaled rapidly from $2.3M to $65M ARR across the UK and US, its small team faced a massive influx of first-party data from hundreds of thousands of customers. Instead of scaling headcounts to build a traditional tech stack, Pinter restructured its entire operations agentically—launching ""Ceres,"" an AI foundation powered by Snowflake. Built on a unified architecture combining Snowflake, GitHub governance, and an OntoLedgy ontology context, Ceres bridges transactional and analytical data in one location. This foundation enabled a non-ML developer to build an enterprise-grade fraud detection model in just five days, alongside launching agentic experiments that automate customer retention, referral viral loops, and ecommerce storefront management. Pinter will share critical lessons from building beneath the AI ""waterline""—from managing tokens and governance guardrails to using a Build-Measure-Learn framework to scale AI operations efficiently.

Goose serves as a real-world proving ground for new MCP capabilities before they're widely adopted. In this talk, you'll learn how to use advanced and early versions of MCP features that go beyond basic tool calling—with practical examples from production. You'll see: * Code mode MCP: handling...