Chatgpt prompts for cheap flights

Setup & Context: Trip Snapshot Brief

Provide: [TRIP TYPE], [ORIGINS (IATA codes or cities)], [DESTINATIONS], [EARLIEST DEPART DATE], [LATEST RETURN DATE], [FIXED DATES YES/NO], [TIME FLEX (+/− HOURS PER LEG)], [TRAVELLERS (COUNT + ADULT/CHILD INFANT)], [ROUTING PREFERENCES (nonstop only, max 1 stop, avoid X, prefer Y)], [BAGGAGE NEEDS (carry‑on only / 1 checked / sports gear etc.)], [SEAT/COMFORT (min legroom, aisle, avoid middle, basic ok?)], [LOYALTY (programmes, status)], [AVOID AIRLINES/AIRPORTS], [PASSPORT/VISA/ENTRY CONSTRAINTS], [PAYMENT CARDS AVAILABLE], [POINTS/MILES BALANCES (by programme)], [ANY HARD COMMITMENTS (events/meetings times/locations)], [NOTES].
Act as a senior airfare workflow lead and turn this into a crisp, constraint‑driven Trip Snapshot Brief we can reuse downstream.
Work through it like this:
1) Normalise dates and time windows: resolve fixed vs flexible, compute usable outbound/return windows and time‑of‑day preferences per leg.
2) Separate MUST‑HAVES vs NICE‑TO‑HAVES; mark hard constraints that will kill a deal.
3) Record routing allowances (stops, airport switches, red‑eye tolerance) and blacklist items (airlines, aircraft, airports) with reasons.
4) Capture baggage and seating expectations to drive fare family choices later.
5) Log loyalty, status, cards, and points that could change value‑for‑money or fees.
6) Define success criteria: target outcomes (price band, duration, risk posture) and evidence needed to say “good enough”.
Give me the output as:
- Sections: Summary; Windows & Flex; Constraints Table (MUST vs NICE); Routing Rules; Baggage & Seating; Loyalty & Payments; Success Criteria.
- Include a simple Leg Window table with columns: Leg, Earliest, Latest, Time Flex (+/−h), Fixed? (Y/N).
Quality bar: Clear enough that a different analyst can start searching without asking a single clarifying question.
If any field is missing or unclear, ask a concise question; if I don’t answer, mark it MISSING and proceed without inventing details.