Ai+ Training

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.

Local ODSC AI Meetup chapters