On: What Is a Harness?

[0x457]

> . “why app slow” obviously doesn’t work because the task is underspecified.

Not always. In my case LLM goes to grafana mcp, pulls metrics/traces/cpu profiles. Figures out what is slow and proposes a solution.

[rurban → 0x457]

In my cases it always used linux perf to sample the calls, because that's the best tool for my jobs. Never had to tell it to use instrumentation.