How we build this

We believe you should see exactly how the information here is made — that’s what being independent means. No black box.

From a real decision to a plain-English summary

1. 1. We fetch the actual decision

   Every entry comes from a public Board of Veterans’ Appeals decision, published by the Board itself.

2. 2. AI reads and summarizes it

   A language model extracts the structured facts (what was claimed, the outcome, the deciding factor) and writes a plain-English summary. It reports only what the decision says.

3. 3. A trust gate hides anything uncertain

   A decision only becomes visible if the model’s confidence clears a bar and the outcome is clearly determinable. Low-confidence or ambiguous extractions stay hidden rather than risk misinforming you.

4. 4. We verify the summaries

   We spot-check extractions against a stronger reference model and track where the summaries are reliable and where they’re weaker — so we know which fields to trust and which to keep improving.

What’s in the library right now

1,114,510 vetted decisions visible. Outcomes: 306 denied · 74 dismissed · 325 remanded · 290 granted · 5 mixed. This grows continuously as more decisions are processed.