AI Dev 26 x SF | Pratik Verma: Observability Agent to Find & Fix Issues in AI Agents

Description

AI agents fail in prod due to brittle workflows, a lack of contextual learning, and an inability to improve over time. At AI Dev 26 x San Francisco, Pratik Verma showed how to use trace-based testing with coding agents as part of agentic engineering to find and fix issues in AI agents. Attendees learned to debug, evaluate and observe AI agents using open source monocle2ai made easy with an observability agent.