Recurring meeting timezone spec
You're directing an AI agent to build a Python scheduling feature: a user creates a recurring weekly meeting at "9:00 AM in their local timezone," and the system must compute the correct UTC instant for each future occurrence and store reminders. Write the prompt/spec that makes the agent handle this correctly across DST transitions and policy changes. What constraints and edge cases do you put in writing, and what library behavior do you mandate? Then describe the subtly wrong thing a naive prompt produces.
weekly_meeting_utc(first_date: str, local_hour: int, occurrences: int, standard_offset_hours: int, dst_start: str, dst_end: str) → list[str]["2026-03-04",9,3,-5,"2026-03-08","2026-11-01"]out["2026-03-04T14:00Z","2026-03-11T13:00Z","2026-03-18T13:00Z"]["2026-10-28",9,2,-5,"2026-03-08","2026-11-01"]out["2026-10-28T13:00Z","2026-11-04T14:00Z"]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.
Vibe & agentic: describe the solution in plain language (or narrate it) and the coach grades your approach.