What’s your agent’s GPA?
In this hands-on workshop we will prototype, evaluate and improve a health research agent armed with MCP tools for search over biomedical data.
We’ll cover the following steps:
Connecting and loading AI-ready data from the Snowflake Marketplace
Creating an MCP server
Using LangGraph to set up our agent and allowed the LLM to call different tools
Using evaluations to systematically measure the agent's performance and improve the agent.
By the end of this workshop, you’ll be able to understand how to measure and improve agent performance.
Workshop Instructions: https://www.snowflake.com/en/developers/guides/build-agent-powered-workflows/
About the speaker:
Josh is a developer advocate for AI and Open Source at Snowflake, previously at TruEra (acquired by Snowflake). He is also a maintainer of TruLens, an open-source library to systematically track and evaluate LLM based applications.
Josh regularly delivers tech talks and workshops at events including PyData, Devoxx, AI_Dev, AI DevWorld, AI Camp meetups and more. He also developed courses and taught students on a variety of platforms including Coursera, DeepLearning.ai, Udemy and DataCamp, and served as an advisor for Trustworthy Machine Learning at Stanford.
DataTalks.Club is the place to talk about data. Join our Slack community!
This post is sponsored by Snowflake.