Biography
Bernard Kavanagh is Principal Solutions Architect (EMEA) at TiDB, a distributed database company focused on real-time analytics and AI infrastructure. He specialises in high-performance data systems and helps organisations move from fragmented data stacks to unified platforms that can support modern AI and agentic workflows.
At TiDB, he works on “Agent-First” memory stores that combine vector search, hybrid SQL, and real-time analytics in a single platform, aiming to reduce the complexity and cost of multi-service AI stacks. His production experience includes building a real-time multi-agent platform for 200,000+ IoT devices that significantly cut infrastructure costs and LLM token usage while improving diagnostic accuracy.
His profile is especially relevant for sessions on AI infrastructure, real-time data systems, agentic AI architectures, vector databases, and the practical challenges of scaling AI applications in production.
Session
- AI FoundationsSpeaker
Keynote 51 - Memory in AI systems - Why state is the missing keystone
Wednesday 23 September, 13:40 – 14:00Auditorium StageWhen your agent decides something is worth remembering past its current session, where does that write go today, and how is it retrieved? We will discuss how data layers and agent state memory are critical to scalable, productionised agentic workflows.