Building an AI copilot to make on-call less painful

Getting hit with a critical alert is never fun.
Getting one you don’t understand is even worse.

That’s what led my team to build an AI copilot for on-call engineers during the recent Kraken AI Hackathon. It reads stack traces, explains what’s going on and tailors its response using team-specific context.

In the last two weeks, we’ve had 8 teams across the wider Kraken organisation start using it. So far, we’ve seen positive feedback, but we’re keeping a close eye to see how this evolves.

What we didn’t expect was that non-engineers started using it too! People in product, and client managers began reading the AI’s assessments to get a sense of whether something was serious or not. They didn’t need to ping an engineer to ask, “Is this alert bad?” They could just read the explanation and get a rough idea.

There’s still a lot to improve, and we’re excited to keep experimenting with AI tools.

Here’s a more in-depth write-up on what we built, what failed, and what surprised us.


Would you like to help us build a better, greener and fairer future?

We're hiring smart people who are passionate about our mission.

Posted by Manoj Kurien Lead Software Engineer on Jul 8, 2025