Files
geointel/docs/CODEX_MASTER_PROMPT.md
Jens faeb58ef6d
GeoIntel release gates / Compile, test, contracts and builds (push) Successful in 1m49s
GeoIntel release gates / Python and npm vulnerability policy (push) Successful in 21s
GeoIntel release gates / Production AI image, SBOM and container scan (push) Successful in 5m39s
GeoIntel release gates / Deploy exact gated revision to Unraid (push) Failing after 58m43s
Initial public release
2026-08-31 21:56:53 +02:00

1.8 KiB

Codex Master Prompt — GeoIntel Kempen

You are working inside the GeoIntel Kempen repository.

GeoIntel Kempen is a GeoAI Workbench for the Belgian Kempen. It is not a generic GIS viewer and not a policy dashboard. The core value is turning raster data, vector data and AI outputs into geospatially correct layers, metrics, QA findings and exports.

Mandatory reading before coding

Read these documents first:

  • README.md
  • docs/SPECIFICATION_FREEZE_M0.md
  • docs/V1_SCOPE_FREEZE.md
  • docs/DATASET_STRATEGY.md
  • docs/SERVICE_ARCHITECTURE.md
  • docs/REPOSITORY_CONVENTIONS.md
  • docs/CODEX_EXECUTION_PLAN.md
  • docs/ACCEPTANCE_CRITERIA.md
  • docs/FIXTURE_STRATEGY.md

Main build target

Build toward Demo 1: Building detection on imagery, conversion to geospatial detection outputs, QA/QC against GRB or a local reference building fixture, and GeoJSON export.

Development rules

  • Backend-first.
  • Service boundaries must be respected.
  • No placeholder-only pages.
  • No fake success responses without persisted data.
  • No unrelated features.
  • No auth/multi-user/payment.
  • No heavy LiDAR/MLOps/training studio in V1.
  • Never calculate metric area/length directly in EPSG:4326.
  • Always preserve CRS and source metadata.
  • Mock/development providers are allowed only if isolated and clearly named.

Implementation order

Follow docs/CODEX_EXECUTION_PLAN.md pass by pass. Do not skip ahead to UI polish.

Handoff requirements after each pass

Update docs/CODEX_EXECUTION_LOG.md with:

  • completed items;
  • files changed;
  • tests run;
  • known limitations;
  • next recommended pass.

Also update docs/TODO.md where relevant.

Final response format after a build pass

Return:

  1. Summary of completed work.
  2. Tests/build checks run.
  3. Known limitations.
  4. Next recommended pass.
  5. Whether the build meets the acceptance criteria for the current milestone.