Example 04 — Donor cluster locator (Claude Code test)

This folder is a fresh test bed for the “Where do my donors cluster?” prompt.

Your task

1. Read prompt.md — that’s the full spec.
2. Apply it to sample_donors.csv.
3. Fetch boundary geometry + adult-population per POA 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 — state breakdown, capital-vs-regional, top-10 by count, top-10 by rate, donor-belt + donor-desert descriptions, one chart recommendation, and a “what to do with this” section with one concrete play per bucket (both-lists / count-only / rate-only) (600-800 words).
   • answer.html — two side-by-side MapLibre maps in a CSS Grid: left panel coloured by donor count, right panel coloured by donor rate per 1,000 adults. Postcodes that appear on both lists get a dashed purple outline. Pan/zoom is synced between the panels. The page also carries a small dismissible “What to do” actions card with one short play per bucket. Full spec in prompt.md. Basemap CARTO light_all.

Rules

• Fetch live from ABS / CARTO URLs only — no other web tools.
• The story is the delta between count and rate. If they’re identical, say so explicitly.
• Geography in words. “Eastern Sydney waterfront” beats “2026, 2030, 2027”.
• HTML must be self-contained.
• Both maps must stay in sync when the user pans/zooms one of them.
• Be terse. 600-800 words in answer.md.
• Actions must be concrete — name the postcodes and the moves, not generic advice.

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.