How the ledger was read
This app reads a single cloud database of 4,183 published Australian public-sector accountability reports (2006–2026) from 50 oversight bodies across all nine jurisdictions — auditors-general, ombudsmen, anti-corruption and integrity commissions, royal commissions, the Productivity Commission, inspectors-general and independent reviews.
Each document was chunked and embedded (478,543 passages), mined for key points and 111,196 verbatim quotations, and independently graded by a language model on two 1–5 rubrics — finding severity and systemic extent — then tagged for theme and recommendation acceptance. A separate pass clustered the corpus bottom-up into 276 topics, rolled into 59 superclusters and 11 families, each re-graded across four eras and seven body types.
Everything on every page is a live query against Cloudflare D1 (the ~1 GB relational residual) and Vectorize (the embeddings), through fully-typed Drizzle. The same data is exposed to agents over an MCP server at /mcp.
What the numbers are — and are not
Severity, reach and the per-era/body-type “positions” are model judgements, not official ratings, and inherit the model’s calibration. Cross-body divergence reflects both genuine differences of mandate and differences in what each body was examining. Averages combine very different report genres and are descriptive, not evaluative. Recommendation-acceptance rates cover only reports that recorded a response — many genres (royal commissions, PC inquiries) structurally do not, and are excluded rather than read as evasion. The family tier is a clean is_primary partition; the topic↔supercluster tier is genuine multi-membership. Partial-year 2026 is included as-is.