Meetup: Knowledge Graphs & Agents
Agentic AI only works as well as the context you can reliably retrieve.
We're kicking off our first meetup of 2026 with a practical deep dive into knowledge graphs + agents. The focus will be on clean graph retrieval patterns: querying a knowledge graph without unnecessary abstraction, keeping type-safety, and getting end-to-end observability (not just LLM calls).
We'll explore:
Where knowledge graph retrieval fits into modern agent architectures
A SurrealDB + Pydantic AI pattern for tool-based graph querying
How to build with type safety + observability baked in
Talks
SurrealDB knowledge graph retrieval tool for a Pydantic AI agent
Martin Schaer (SurrealDB)
Once you have a knowledge graph in SurrealDB, Pydantic AI agents provide one of the most straightforward ways of querying it, without adding unnecessary layers of abstraction that limit your options, and providing production ready type-safety and full-stack observability (not only for the LLM calls).
Building Agents with Pydantic AI, Logfire and SurrealDB
Chris Samiulluh (Pydantic)
This session explores how to build AI agents by combining three powerful tools: Pydantic AI for agent development, Pydantic Logfire for observability, and SurrealDB as a multi-model database backend. A practical approach to agent development, demonstrating how these tools work together to create applications that are both powerful and maintainable.
Agenda
18:00 Doors + drinks
18:30 Welcome
18:35 Talk 1 + Q&A
19:15 Talk 2 + Q&A
20:00 Networking
20:30 Close
Who should attend?
Software engineers and builders working on agents, RAG, semantic search, knowledge graphs, and anyone who cares about reliable context retrieval and systems you can reason about.
About the speakers
Chris Samiulluh
Chris is VP of Partnerships at Pydantic, the company behind the popular Python validation library with +500 million downloads per month. He focuses on the intersection of AI engineering, observability, and enterprise sales strategy. With over a decade of experience writing code, Chris has deep expertise in scaling machine learning applications and AI engineering. He ran the Beijing Python meetup for two years, mentors junior developers, and continues to create software development tutorials and guides. He is the co-author of the popular Udemy course "Deployment of Machine Learning Models."
Martin Schaer
Martin is a computer science engineer working at SurrealDB and his GenAI startup. He recently worked in lab automation, where he designed and developed a declarative framework for instrument drivers and a 3D visualiser for testing robotic transport solutions. His background also includes founding a successful advertising agency in Costa Rica and extensive work in web development, UX, branding, and digital marketing.