Building the Data Layer for AI Agents

AI has transitioned from demonstrations to production, with agents that remember, reason, and act over time. This shift transfers the challenging problem from the model to the data layer. Durable memory, real-time context, retrieval, and per-tenant isolation now need to function at scale, within a single system.Spend an evening with AWS and TiDB exploring this shift together. AWS provides the platform and market perspective, while TiDB offers the data layer designed for this challenge: distributed SQL that scales without sharding, HTAP on live data, and native vector search with durable state for agent memory, operating on AWS alongside Bedrock and AgentCore. One foundation supports the transactional scale you require today and the agentic scale you will need tomorrow, so you won’t have to re-platform to transition between the two.Moonshot AI’s Kimi demonstrates this in production, managing tens of millions of isolated agent tenants on TiDB, with each tenant provisioned in under a second. What the frontier accomplishes first, the market follows next.You will depart with a market map indicating where AI value is tangible, an architecture you can apply to your own workload, and insights into the demand curve heading your way.Programme17:00 — Arrival, drinks, and networking17:30 — Welcome and framing17:35 — Topic and Speaker to be announced, AWS17:55 — The Agentic Data Layer on AWS: TiDB and AWS, Architecturally. Bernard Kavanagh, TiDB18:15 — Lessons from the Frontier: Inside the Kimi Build, and What APAC Signals Next. Siddon Tang, TiDB18:35 — Fireside Q&A with all three speakers18:50 — Beer and finger foodSpeakers:Speaker to be announced AWSBernard Kavannagh, Principal Solutions Architect, Applied AI, TiDBBernard is a Principal Solutions Architect focused on Applied AI, crafting production architectures for agentic and AI-native workloads. He translates the joint value of TiDB + AWS into reference patterns that engineering teams can implement, merging the transactional database, vector store, cache, and analytics stack into a single engine on AWS, and demonstrating its application for payments, multi-tenant SaaS, real-time risk, and agentic features.Siddon Tang, Chief AI Officer & GM, APAC, TiDBSiddon is one of the foundational engineers behind TiDB and the creator and long-time lead of TiKV, its distributed storage engine and a CNCF-graduated project. Over a decade of building TiDB has established him as one of the most recognised voices in distributed databases and the Rust systems community. As Chief AI Officer and GM of APAC, he now directs TiDB’s AI initiatives and its collaborations with frontier AI companies — including Moonshot AI’s Kimi agent-hosting platform, one of the largest agentic workloads globally.