From Alert to PR: Building an Autonomous Agent Debugger
What if your observability platform didn't just tell you something was wrong, but told you why, and opened a PR with the fix? We'll walk through how we built Autopilot at Arize: an autonomous investigation agent that triggers on monitor alerts or schedules, pulls traces into a working filesystem, runs root-cause analysis, and produces actionable assets: a PR with prompt or code changes ready for review. We'll cover the architecture decisions (cloud agents vs. sandboxed containers, AI harness + skills), why traces-on-a-filesystem is the key unlock for agent-driven debugging, and how we dogfooded the system on our own agent, Alyx, before shipping it to customers. You'll leave with a concrete picture of what "observability that fixes itself" looks like in practice, and where and why the human stays in the loop.
About the Evals Track
Evals sessions at AI Engineer World's Fair 2026 in San Francisco.
When
Wednesday, July 1, 2026
11:10 AM - 11:30 AM·20m
Where
Track 5 · Room 2005
Capacity: 250 attendees
Sign in to add this talk to your schedule.
Speaker
Jason Lopatecki
Co-Founder & CEO
Arize AI
Jason Lopatecki is Co-Founder and CEO of Arize AI, an AI/ML observability company. He previously co-founded TubeMogul, where he served as Chief Innovation Officer before Adobe acquired the company. His background includes big data architectures, distributed systems, programmatic advertising, and machine learning.