Example 03 — Score next campaign (Claude Code test)

This folder is a fresh test bed for the “Score my next campaign” prompt — ranking a list of postcodes you’re considering for your next push before you commit budget.

Your task

1. Read prompt.md — that’s the full spec.
2. Apply it to sample_donors.csv (current donor profile) and sample_campaign_targets.csv (the list of postcodes to score).
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 — ranked target list with top-10 + bottom-5 + a justified cut-line + channel suggestions (500-700 words).
   • answer.html — MapLibre choropleth of the target postcodes coloured by similarity score, with the cut-line ring + legend baked in. Basemap CARTO light_all. Full spec in prompt.md.

Rules

• Fetch live from ABS / CARTO URLs only — no other web tools.
• Honest framing. The ranking is similarity to existing donors, not predicted giving. State your scoring method at the top of answer.md.
• Cut-line must be justified. Tie it to the Lorenz-curve logic (28% of postcodes → 80% of dollars).
• Channel suggestions must match each postcode’s demographic profile, not be generic.
• HTML must be self-contained.
• Be terse. 500-700 words in answer.md.

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.