Triage Like an Engineer
In a production incident, structure your prompt like an incident report: describe the symptom, provide the evidence (logs, traces, diffs), state your hypothesis, and ask for both the immediate fix and the root cause fix. Don't just say 'it's broken: fix it.'
Where you'll practice this
One Promptles scenario teaches this principle directly.
The Production Incident
It's 2 AM and your on-call pager fires. The checkout endpoint `/api/checkout` is returning 500 errors for all users. You have: server logs showing "Cannot read properties of null (reading 'id')", an error trace pointing to `services/checkout.ts:47`, and a git diff from the last…