Seats.aero

Build me a focused trip planning, navigation and travel intelligence workflow for the personal core of Seats.aero. Requirements:

- Use Next.js 15, TypeScript, SQLite, MapLibre GL, and user-supplied map and travel APIs. Model trips, stops, dates, reservations supplied by the user, and itinerary versions; keep stable source IDs and timestamps.
- Paid product context: Save and compare user-entered award availability without crawling airline systems. Build only this DIY scope: Save and compare user-entered award availability, map places and reservations, and keep an offline itinerary without crawling airline systems or claiming live proprietary availability.
- Create trips, days, places, reservations, notes, documents, packing items, and emergency contacts.
- Allow manual updates for delays and reservations and label all external data with source and timestamp.
- Export a complete trip bundle as JSON, calendar file, Markdown, and PDF.
- Use a local web page with input, progress, review, and export views. Required input or access: MapTiler or compatible map key; user-entered reservations.
- Recovery: Deliberately leave out commercial turn-by-turn navigation and global offline maps.
- Acceptance: with one labelled sample, show the input, saved intermediate state, and exported result; verify this invariant: A route API failure must preserve all stops and notes; the exported itinerary must retain stop order and local dates.
- Out of scope: large award-availability dataset, alerts, route tools, and continuous collection; live fare and inventory data. Keep this a personal, inspectable workflow.
- Include a README with setup, a sample input, required keys or permissions, data location, and the supported scope.

# AGENTS.md — Build guide for Seats.aero

## Project scope
Save and compare user-entered award availability, map places and reservations, and keep an offline itinerary without crawling airline systems or claiming live proprietary availability.

Catalogue verdict: no. A consolation build is possible, but the paid product's decisive value sits outside a solo rebuild. For Seats.aero, save and compare user-entered award availability without crawling airline systems. The hard boundary is large award-availability dataset, alerts, route tools, and continuous collection, plus proprietary live data and network coverage.
Use the implementation prompt below to define the deliverable. Complete each phase's acceptance checks before extending the scope.

## Working agreement
- Inspect the repository and its existing instructions before choosing paths, dependencies or commands. Keep one coherent stack and explain changes to the proposed architecture.
- Plan a vertical slice that accepts a real input and produces the useful output described below. Persist only the state the prompt calls for; respect memory-only and upstream-managed workflows. Use fixtures only when they are clearly labelled.
- After scaffolding, document the actual install, development, check and build commands in README and keep them synchronized with the package or project manifest. Do not report commands as successful unless they ran.
- Work in small steps. At handoff, list implemented flows, checks actually performed, remaining blockers, and any credentials or provider setup the owner must supply.
- Do not publish, spend money, contact customers, delete source data or run irreversible migrations without the project owner's authorization.

## Prerequisites
- modern browser
- MapTiler or compatible map key
- user-entered reservations
- optional public transit or weather API

## Stack and architecture
- Use Next.js 15, TypeScript, SQLite, MapLibre GL, and user-supplied map and travel APIs.
- Model trips, stops, dates, reservations supplied by the user, and itinerary versions; keep stable source IDs and timestamps.
- Interface for this trip planning, navigation and travel intelligence workflow: a local web page with input, progress, review, and export views.

## Security and data integrity
- Deliberately leave out commercial turn-by-turn navigation and global offline maps.
- Validate imported records and file paths; keep user data within the storage location named in the prompt.
- State the practical limit: large award-availability dataset, alerts, route tools, and continuous collection.

## Agent implementation rules
- Project rule, data: Model trips, stops, dates, reservations supplied by the user, and itinerary versions; keep stable source IDs and timestamps.
- Project rule, behavior: Create trips, days, places, reservations, notes, documents, packing items, and emergency contacts.
- Project rule, recovery: Deliberately leave out commercial turn-by-turn navigation and global offline maps.

## Optional agent skills and references
No installable skill is listed for this guide; use the project rules and the stack documentation.

Read the linked SKILL.md and its dependencies before adding a skill. Select only the skills matching this project's runtime and task; their documentation does not supply API access, credentials or approval to perform external actions. Pin the reviewed revision where the tool supports it. Follow the chosen agent's documented project-level installation mechanism.

## Distribution ideas
These are optional planning notes. Obtain the owner's approval before publishing or contacting anyone.
- Demonstrate this trip planning, navigation and travel intelligence operation with sample or user-owned data: Create trips, days, places, reservations, notes, documents, packing items, and emergency contacts.
- Show a concrete result or export: Export a complete trip bundle as JSON, calendar file, Markdown, and PDF.
- State the practical limit: large award-availability dataset, alerts, route tools, and continuous collection.

## Engineering roadmap
1. Phase 1, architecture and data: Use Next.js 15, TypeScript, SQLite, MapLibre GL, and user-supplied map and travel APIs. Model trips, stops, dates, reservations supplied by the user, and itinerary versions; keep stable source IDs and timestamps.
2. Phase 2, implement: Create trips, days, places, reservations, notes, documents, packing items, and emergency contacts.
3. Phase 3, implement: Allow manual updates for delays and reservations and label all external data with source and timestamp.
4. Phase 4, review and output: Export a complete trip bundle as JSON, calendar file, Markdown, and PDF.
5. Phase 5, recovery and acceptance: Deliberately leave out commercial turn-by-turn navigation and global offline maps. Verify this invariant with a saved fixture: A route API failure must preserve all stops and notes; the exported itinerary must retain stop order and local dates. State the practical limit: large award-availability dataset, alerts, route tools, and continuous collection.

## Paid-product capabilities outside this build
- large award-availability dataset, alerts, route tools, and continuous collection
- live fare and inventory data
- global routing dataset
- crowdsourced trail intelligence
- booking, disruption support, and offline map fleet

## Implementation prompt
Build me a focused trip planning, navigation and travel intelligence workflow for the personal core of Seats.aero. Requirements:

- Use Next.js 15, TypeScript, SQLite, MapLibre GL, and user-supplied map and travel APIs. Model trips, stops, dates, reservations supplied by the user, and itinerary versions; keep stable source IDs and timestamps.
- Paid product context: Save and compare user-entered award availability without crawling airline systems. Build only this DIY scope: Save and compare user-entered award availability, map places and reservations, and keep an offline itinerary without crawling airline systems or claiming live proprietary availability.
- Create trips, days, places, reservations, notes, documents, packing items, and emergency contacts.
- Allow manual updates for delays and reservations and label all external data with source and timestamp.
- Export a complete trip bundle as JSON, calendar file, Markdown, and PDF.
- Use a local web page with input, progress, review, and export views. Required input or access: MapTiler or compatible map key; user-entered reservations.
- Recovery: Deliberately leave out commercial turn-by-turn navigation and global offline maps.
- Acceptance: with one labelled sample, show the input, saved intermediate state, and exported result; verify this invariant: A route API failure must preserve all stops and notes; the exported itinerary must retain stop order and local dates.
- Out of scope: large award-availability dataset, alerts, route tools, and continuous collection; live fare and inventory data. Keep this a personal, inspectable workflow.
- Include a README with setup, a sample input, required keys or permissions, data location, and the supported scope.

## Completion evidence
Demonstrate the prompt's acceptance scenarios against the scoped workflow. Include setup from a clean checkout and failure recovery. Check persistence across restart and export/restore only for the state the prompt says to store; for memory-only tools, confirm that temporary content is discarded as specified. Record actual results and remaining limitations. A detailed plan alone does not establish a working replacement.