It's about the hardest agentic problem that has measurable results and will be adopted (because it's an engineering culture) that I can think of. RunWare have some good insights on this - much of the problem is context layer improvisation and repetition, and the only way out is an awful lot of diagnostic development.
And anything less than 90% accuracy on causal analysis is more work than doing everything by hand.
Yeah the context is the key to make the LLM really useful for oncall. But honestly the SRE agent companies today are trying to keep users in their platforms, not focusing on solving the context problem. That's what I saw.
I am a middle aged man who lives on a sailing boat. A decade in early stage / founding without an exit that's closer to a car crash. Still trying, I don't have the temperament for consulting or corporate.
There's gotta be a ton of people in their 20s working remotely and living on a boat right now. They don't have to bust their ass like an entrepreneur either. They're just normal employees.
I would really like to see more people down my prompt engineering rabbit hole of trying to use ontology / compilation tricks to produce prompts from models rather than curating text. I have this working pretty well for complex tool interaction, without a JSON schema or template in sight.
Believe it or not, agents can run things like this:
e3{p13=e4(p14), p38=$} returns [e3] · Incremental collaboration signal (what changed and when). Poll to stay current; acknowledge so the server can advance your cursor · optional params: p38
And anything less than 90% accuracy on causal analysis is more work than doing everything by hand.