Vague requirements unsuitable for delegation
Product hands you a vague request: 'make the billing system fairer when customers downgrade mid-cycle.' A teammate wants to drop this straight into an AI agent and let it implement proration logic. Decide whether this task, as stated, is suitable for AI delegation right now, and explain what about the task — independent of difficulty — determines the answer.
Implement
blocking_spec_gaps(requirement_lines: list[str]) → list[str]Examples
in
[["refund_vs_credit|TBD|1","annual_vs_monthly|fairer|1","button_label|TBD|0","tax_handling|credit net of tax, no refund|1"]]out["annual_vs_monthly","refund_vs_credit"]in
[["refund_vs_credit|credit to next invoice|1","already_issued_invoices|leave untouched|1"]]out[]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.