Weaviate Podcast Weaviate's Query Agent with Charles Pierse - Weaviate Podcast #128!
7 snips
Sep 22, 2025 Charles Pierse, Director of Weaviate Labs, shares insights on the GA release of the Weaviate Query Agent. He discusses the journey from beta to GA, highlighting unexpected lessons and team collaborations. The conversation dives into technical aspects, including response models, citations, and how Search Mode enhances retrieval. Charles explains how the Query Agent integrates with the Cloud Console, making it intuitive for users. He also presents a compelling case study featuring MetaBuddy's innovative use of the agent for nutrition data.
AI Snips
Chapters
Transcript
Episode notes
Ship With Cross-Team Collaboration
- Collaborate across product, core, and console teams to make agent features feel seamless.
- Interview users early to discover unexpected behaviors and requirements.
Agent As Domain Expert
- Treat the Query Agent as a domain expert that knows how to use Weaviate APIs.
- It acts as a next-generation database interface you can talk to in natural language.
Provide Multiple Interaction Modes
- Support both single-query and conversational chat modes because users will embed the agent into chat flows.
- Provide a pure retrieval "search mode" for users who only need sources, not generated answers.