Agentic AI Meetup in San Francisco
ODSC AI x Snowflake Present: The Future of Data-Driven AI
Our premier San Francisco AI Meetup of February 2026!
Skip the usual AI hype and come grab a slice of pizza while we talk shop. We’re bringing together 90+ SF builders to figure out how to actually get AI agents into production without them burning through your compute credits. Come for the networking, stay for the Agent GPA framework, and leave with a better strategy for 2026.
The Session
Topic: Optimize your Agent's GPA with Coding Agents
In this talk, we will share how coding agents help developers build high quality agents faster.
A key insight from building agents in production is that high quality agents operate with their goals, plans and actions aligned. We introduce the Agent Goal-Plan-Action or Agent GPA framework to capture this insight, which achieved state of the art benchmarks on TRAIL/GAIA with 95% error coverage and 86% error localization.
This framework goes beyond examining the agent's final results to assessing the agent's process: Was the goal achieved efficiently? Did the plan make sense? Were the right tools used? Did the agent follow through? Without visibility into these steps, teams risk deploying agents that look reliable but create hidden costs in production. Inaccuracies can waste compute, inflate latency and lead to the wrong business decisions, all of which erode trust at scale.
This approach to agent evaluation enables effective and fast optimization with coding agents. We will also show how to use coding agents to automate the process of measuring and improving an Agent's GPA by using agent optimization skills that take advantage of the GPA evaluation framework.
By the end, attendees will be able to use coding agents and the GPA framework to identify common agent failures, improve their agent and make it ready for production.
Speaker: Anupam Datta, Principal Research Scientist at Snowflake
https://www.linkedin.com/in/anupamdatta/
Anupam is the Snowflake AI Research Lead and former Co-Founder/Chief Scientist of TruEra. A former tenured Professor at Carnegie Mellon, his work centers on Trustworthy AI, spanning explainability, fairness, and the TruLens project. He holds a Ph.D. from Stanford, has published over 100 papers, and currently teaches Trustworthy AI at Stanford University.
Why Attend?
Network with the Best: Connect with 90+ AI practitioners and data leaders in the SF ecosystem.
High-End Experience: Enjoy bites and refreshments in a professional, collaborative environment.
Exclusive Insights.
Agenda
6:00 PM – 6:30 PM: Networking & Bites/Drinks
6:30 PM – 7:15 PM: Presentation: Optimize your Agent's GPA with Coding Agents by Anupam Datta
7:15 PM – 7:30 PM: Interactive Q&A
7:30 PM – 8:00 PM: Networking & Closing
Venue - The House, 103 Montgomery Street, Suite 200, in the historic Presidio of San Francisco, CA 94129.
RSVP now to secure your spot!
Useful Links
Free access to more talks/trainings: Ai+ Training platform
ODSC Blog: https://opendatascience.com/
Join the Community: Slack Channel
Code of Conduct: https://odsc.ai/code-of-conduct/