talk-data.com

Anyone can build fast. Tools, talent, and tech make shipping easier than ever. But speed alone is a blunt instrument—without precision, it just gets you to the wrong destination faster. This talk is about what truly sets exceptional teams apart: the ability to combine speed with certainty. We’ll explore how we embed rapid validation, lean research, and focused experimentation into your delivery cycles—so you’re not just moving quickly, but confidently. Because the winners in today’s product landscape aren’t the fastest builders. They’re the fastest learners.

Most AI systems today operate in stateless environments, relying on limited prompt windows to infer context. But what happens when context isn’t just a feature, it’s the lifeblood? In this talk, Brian Walters explores the design and implementation of scalable, long-term memory for AI systems using TiDB. Drawing from real-world architectures and use cases, he walks through how TiDB’s hybrid transactional and analytical engine enables persistent memory that is queryable, versioned, and multi-modal.