The Stack Overflow Podcast Your runbooks are obsolete in the age of agents
Oct 24, 2025
Spiros Xanthos, CEO of Resolve AI, dives into the transformative role of AI agents in incident management. He discusses how traditional runbooks are becoming outdated and how AI agents can autonomously troubleshoot complex systems, potentially saving up to 70% of engineers' time. Spiros elaborates on agents acting as on-call responders, gathering evidence across various tools, and assisting with the increasing complexity of software systems. He also touches on the evolving role of developers in an AI-driven landscape and offers insights into the future of engineering.
AI Snips
Chapters
Transcript
Episode notes
Observability Alone Doesn't Solve Toil
- Modern observability centralizes data but human toil still dominates running systems at scale.
- Complexity grows superlinearly so no single person understands entire production systems.
Founding Resolve To Tackle Operational Work
- Spiros left Splunk to build agents that handle the 70% of work around running systems instead of new development.
- Resolve AI focuses on agents that troubleshoot alerts, manage incidents, and operate production systems.
Incident Troubleshooting Is The Hardest Problem
- Incident troubleshooting is high-pressure, low-latency, and often the most painful human task in production.
- Agents can target this hardest subset to deliver immediate operational value.