Ingesting Agent Traces with dlthub

In this hands-on workshop, we'll show you how to stop flying blind on your AI agents. Using dltHub Pro we'll build a pipeline that ingests agent traces (e.g. tool calls, intermediate steps, token usage, and outcomes) and transforms them into structured, queryable data. From there, we'll turn that data into reports that actually tell you what your agents are doing, where they're failing, and how to make them better. You'll learn how to: Capture and normalize agent traces into a consistent schema Transform and model nested, variable-length trace data with dltHub Pro Deploy your pipeline and build reports that surface real insights about agent performance By the end, you'll have a working reporting layer for your AI agents, so you can debug faster, optimize smarter, and ship with confidence. About the speaker: Alena is a DevRel at dltHub. She builds and optimizes data pipelines, engages with dltHub community, and creates educational content to make data processing more accessible.

This event is sponsored by dltHub DataTalks.Club is the place to talk about data. Join our Slack community!