Tech Gathering: Moving Beyond the AI Agent Hype
ODSC x Snowflake: Moving Beyond the AI Agent Hype
The D.C. meetup for anyone actually trying to ship production-ready AI (March 2026).
Building an AI agent is a "weekend project." Scaling one for production is a full-time job. Most agents look great in a demo but fail the "real world" test because we only look at the final answer—not the process.
Join us for an evening in D.C. where we move past "vibes-based" engineering and into a formal framework for agent success.
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.
Meet Your Speaker
Matt Harris | Principal AI Strategy Architect (FSI) at Snowflake
Matt is a veteran in the data space, serving as a Principal Solutions Engineer at Snowflake. He specializes in helping complex organizations transform their data architecture into a competitive advantage. With deep expertise in the Snowflake Data Cloud, Matt focuses on making advanced data science and AI accessible, governed, and ready for production environments.
Logistics
6:00 PM – Networking & Bites: Fuel up and meet the D.C. AI community.
6:30 PM – Technical Presentation: The GPA Framework with Matt Harris.
7:15 PM – Interactive Q&A: Dig into the tech.
7:30 PM – Closing Connections: Make one last contact before heading out.
Why Attend?
Network with the Best: Connect with AI practitioners and data leaders in the D.C. tech and public sector ecosystem.
High-End Experience: Enjoy bites and refreshments in a professional, collaborative environment.
Exclusive Insights: Get a direct line to Snowflake’s technical leadership on where enterprise AI is headed next.
Venue: Mindspace, 1301 K Street Northwest, Washington, DC 20005
Limited spots available!