How we merged two overlapping court order trackers, enriched missing fields with Claude Haiku for a few cents, replaced 200 paywalled links with free CourtListener alternatives, and shipped a searchable explorer — all through conversational prompting with Claude Code.
Public PPP data can produce enforcement-relevant anomaly maps. An open-source fraud-scoring system, run against the SBA PPP dataset, surfaced lender and geographic concentrations that overlap with known enforcement patterns — while also showing why public data cannot prove fraud by itself.
The PPP fraud pipeline worked because the SBA released unusually inspectable data. Medicare's public data is fragmented, de-identified, and missing the features detection needs. Here's what exists on GitHub, where it falls short, and what CMS would need to release to make outside healthcare-fraud analysis more practical.