Most AI incident tools still leave a key decision to humans
An AI SRE agent can help troubleshoot an incident. But can you trust it to decide on its own when something needs attention?
Most teams treat agent autonomy as a yes or no question. For incident response, it is a progression with three phases, and many agents in production sit earlier on it than the teams running them realize. Most AI SRE tools still stop short of the final phase.
On Thursday, October 22, The New Stack hosts a live webinar with Raaz Dwivedi, co-founder and CTO of Traversal and an assistant professor at Cornell Tech. His team applies causal AI and agentic reasoning to production incidents. He will walk through where the industry sits on that progression and what it takes to move up.
You have successfully registered for the webinar.
The three phases of agent autonomy
Invoked: copilots, chat interfaces, and CLIs that wait for an on-call engineer to open them and ask a question mid-incident.
Background: scheduled jobs, alert rules, and triggers that fire on conditions someone predicted in advance.
Proactive: agents that decide for themselves when an incident needs attention, without waiting to be invoked or scheduled.
The first two phases share a limit. Each depends on a person noticing that something is wrong, or on someone predicting the right condition ahead of time. Proactive agents remove that dependency.
What it takes to trust an AI SRE agent
Moving to the third phase raises a trust question. An agent that waits to be asked can be wrong without much consequence, because an engineer reviews the answer. An agent that decides when to engage also has to judge when to stay quiet. Dwivedi will cover what separates an agent that responds from one that acts on its own, why many AI SRE tools stall in the first two phases, and what has to be true before a team lets an agent make that call.
What changes once agents act on their own
Dwivedi will also discuss where the shift is already happening, drawing on Traversal Workers, agents that already operate at the proactive end of the progression. He will explore what changes for engineering teams once the agent in their stack stops waiting to be asked.
The session closes with live Q&A, so you can ask him your questions directly.
Join us on Thursday, October 22, 2026 at 1 p.m. Eastern / 10 a.m. Pacific, to learn where your team stands in the progression and what it would take to move up. Register today.
