Webinar: Vector RAG that actually understands context

​Please note - to reserve a spot for this webinar you must register at: https://surrealdb.com/events/webinar/2026-01-21-vector-rag-that-actually-understands-context

​--

​Webinar: Vector RAG that actually understands context

​Basic vector RAG breaks down as systems scale. Semantic similarity alone cannot enforce hierarchy, causality, or typed relationships - leading to degraded accuracy and opaque results over time.

​In this live webinar, Matthew Penaroza (Head of Solutions Architecture, SurrealDB) shows how to design retrieval systems that maintain context as data and usage grow. You’ll learn how vectors and graphs work together to enforce structure, reduce search space, and explain why evidence was retrieved - not just that it was.

​This session focuses on retrieval quality and interpretability, not database internals.

​

​What we’ll cover

• ​Why vector-only RAG fails at scale (and why common fixes don’t solve it)

• ​What “context” actually means in retrieval systems

• ​How graph-based retrieval complements vectors

• ​Implementing hybrid vector + graph retrieval in a single query

• ​Producing retrieval traces that explain evidence selection

• ​What to measure to avoid semantic collapse in production

​

​Speaker

Matthew Penaroza
Head of Solution Architecture, SurrealDB

​Matthew Penaroza is Head of Solution Architecture at SurrealDB, where he helps design and scale distributed AI systems for global enterprises. As the solutions architect behind the core database systems at companies such as Plaid, Uber, and Atlassian, he brings firsthand insight into how the world’s largest organizations design data infrastructure and how those same architectural principles can be applied to AI systems that demand context precision and intelligent data management.

​

​Who's this event for?

​Applied AI + platform engineers building RAG/agents at AI-native companies, and leaders responsible for retrieval quality, complexity, and long-term system health.