AMSTERDAM: Building Autonomous Systems - KubeCon AfterParty (LangChain, SurrealDB, Qodo)
Agentic AI only works as well as the context you can reliably retrieve.
This event brings together AI engineers and platform engineers to talk about what happens after the demo: reliability, guardrails, and the runtime + data foundations you need to ship agentic systems in production.
With speakers from LangChain, AWS, Qodo, plus a keynote from SurrealDB, we’ll dig into practical architectures for building and operating AI apps at scale - from execution environments to platform controls and durable memory.
We’ll explore:
What “production-ready” means for agents: safety, observability, and failure modes
How platforms should support agent workflows (not just model calls)
Patterns for separating experimentation from execution (and keeping both fast)
Building durable agent memory with knowledge graphs - and making retrieval predictable
Talks & technical sessions
Sandboxed Deep Agents — Daniel Kneipp (LangChain)
Hidden Failure Modes for AI Agents — Nupur Sharma (Qodo)
Building Agent Memory with Knowledge Graphs — (SurrealDB)
LangChain Authorized AI Apps — Sohan (LangChain)
Panel / open discussion
Building and operating AI systems in real-world environments
Networking & drinks
Agenda (subject to change)
Welcome & opening remarks
Talks & technical sessions
Panel / open discussion
Networking & drinks