What we screen for

How a bill gets classified

1. 1. Ingest. Every bill from all 50 states and D.C. is pulled from Open States and refreshed as it moves.
2. 2. Pre-screen. A curated circular-economy lexicon — 440+ terms across 16 signal categories, tiered and weighted — narrows the full legislative universe to plausible candidates, so deeper analysis is spent only on bills that might be relevant.
3. 3. Classify. Each candidate is evaluated against the fixed criteria above and either flagged relevant — with a confidence score, policy instrument, and material tags — or set aside.
4. 4. Extract. Relevant bills have their compliance specifics pulled from the bill text: deadlines, covered products, producer obligations, fees, and preemption signals.
5. 5. Review. A growing subset is spot-checked by a human, which flips the bill's reviewed marker.
6. 6. Re-screen. As a bill advances or its text changes, it's re-evaluated so the record stays current.

Auto-classified vs. reviewed

Each bill is first auto-classified: a language model reads the title, summary, and text and decides whether it touches one of the tracked instruments, with a confidence score and the material streams it affects. Compliance details (deadlines, covered products, producer obligations) are then extracted from the bill text.

A bill marked reviewed has additionally been spot-checked by a human. Anything not yet reviewed carries only the automated call — shown on each bill so you always know which is which.

Classifications are automated and can contain errors; always verify against the primary source before acting. We continuously expand the reviewed set.