We use AI at work, Claude specifically, and it’s faster than avg SRE for trivial tasks like cross signals correlation. But it requires a lot of effort to build a harness from your company contexts for it to work like an SRE. And it’s just a tool so if you have to build your knowledge to make it useful, otherwise it’s just a blunt. Or in other word, incompetent people are incompetent no matter of tools

▲

menaerus 5 hours ago | parent | next [-]

What contexts would the AI model need for analyzing, let's say, cluster-wide incident other than the observability data that such systems anyway collect already?

▲

ragall 4 hours ago | parent [-]

The entire company code base, design docs, realtime threat intelligence feeds, all the vendors' status pages, etc...

▲

menaerus 3 hours ago | parent [-]

Not sure how that relates to incident debugging?

	▲	ragall 3 hours ago \| parent [-]
		Very often the causes of an incident aren't visible in metrics because the relevant metrics aren't collected. Sometimes an incident is caused by external actors, etc...

▲

hedgehog 5 hours ago | parent | prev [-]

Is it really that complicated to set up? A basic version is make everything work from a CLI in terminal coding agent of choice (probably already mostly there), hook it up to alerts, and let it run in a corner?

	▲	llama052 4 hours ago \| parent [-]
		Not OP, for me the issue is nuance of all of your infrastructure, application and outside layers. There's a lot of documentation and such, but often times things don't work as expected to a degree and it requires filling in the blanks correctly. The amount of times I've had an AI Agent misinterpret an alert and assume it was XYZ when it was some random layer it had no idea about is often. It can certainly get closer but unless your tech stack is a webserver and an application it can get complicated.