Example 01 — Donor fingerprint (Claude Code test)

This folder is a fresh test bed for the “What’s my donor fingerprint?” prompt.

Your task

1. Read prompt.md — that’s the full spec.
2. Apply it to the data in sample_donors.csv.
3. Fetch boundary geometry + demographic data from the public ABS endpoints listed in the prompt (no auth required). Nothing is bundled in this folder.
4. Produce two outputs in this directory:
   • answer.md — the analysis (400-600 words).
   • answer.html — an interactive MapLibre choropleth of donor postcodes coloured by donor count, basemap CARTO light_all. Full map spec is in prompt.md.
5. Compare your outputs against expected_output.md after — the markdown should tell the same story (shape, not exact words). The HTML doesn’t have an expected version; satisfy the spec in the prompt.

Rules

• Fetch live from ABS / CARTO / AEC URLs only — no other web tools.
• Cite numbers from the data. When you claim “donors over-index on age 65+”, show the actual percentages.
• Don’t oversell. End with the correlational-not-causal caveat.
• Be terse. Expected output ~500 words. Don’t write 2,000.
• HTML must be self-contained — open it with open answer.html and the map renders. No build step.

Disclaimer

Mapulus provides this example as educational starter content. The analysis, predictions, and recommendations produced by running it come from a third-party LLM operating on the user’s data — Mapulus is not responsible for the accuracy, completeness, or fitness-for-purpose of any output. Surface this caveat in answer.md so the user understands the results are hypotheses to test, not advice to act on.