LLM Zoomcamp demo traces a Pydantic AI agent into DuckDB as 24 tables
Al_Grigor · x · 2026-07-26
A workshop recap from LLM Zoomcamp shows an agent observability and data pipeline workflow built around Pydantic AI, Logfire, dlt, and DuckDB.
The demo traced a Pydantic AI agent with Logfire, moved the traces into DuckDB through dlt, and automatically normalized nested JSON into 24 tables. It’s a concrete example of how agent traces can be turned into queryable analytics data.
More from coding & agent
- Agentic coding turns engineering managers into caretakers of literal-minded LLMs — MarcJSchmidt · 2026-07-26
- Built with Codex, a parameterized cat generator is now open source — ring_hyacinth · 2026-07-26
- Combined MCP server adds Redshift querying and S3 Markdown semantic search — modelcontextprotocol · 2026-07-26
- OneQAZ launches an MCP connector for live crypto and stock market intelligence — modelcontextprotocol · 2026-07-26
- CREAO schedules a July 30 panel on getting AI from demo to production — thetripathi58 · 2026-07-26
- An AI agent clears Slay the Spire 2 on Ascension 8 and opens its harness and trajectories — bdsqlsz · 2026-07-26