Agent delegation boundaries
You're building a feature in Python that calls an LLM to classify support tickets, then routes them. You want to use an AI agent to build most of it. Break the task into what you delegate to the agent vs. what you own yourself, and explain the principle behind where you draw that line. The routing rules encode business policy that changes monthly.
Implement
route_ticket(rule_lines: list[str], category: str, priority: int) → strExamples
in
[["billing|3|billing_urgent","billing|0|billing_queue","*|4|escalations"],"billing",5]out"billing_urgent"in
[["billing|3|billing_urgent","billing|0|billing_queue","*|4|escalations"],"shipping",1]out"triage"What a strong answer looks like
Treat the AI’s output as a draft to verify, not an answer to trust. Name the specific flaw and the input that triggers it, say how you’d catch it (tests, edge cases, reading critically), and how you’d re-prompt or decompose to get it right.
0:00 of about 20 min
Vibe & agentic: describe the solution in plain language (or narrate it) and the coach grades your approach.
Which questions mattered is sealed until you submit. Telling you now would just be handing over the edge cases.
Run or narrate your approach, then ask the coach.