Invarail
A code repository containing 151 decision entries, used to test the handover mechanism of Decision Brain.
Timeline (last 90 days)
When an agent believes item A supersedes item B, another agent must each quote a passage from the original text to confirm before the handoff counts; on Invarail's 151 items, the team initiated 15 handoffs, confirmed 9, and the rest were rejected.
In a controlled experiment on 24 frozen questions (covering the three repositories Invarail, GOV.UK content-publisher, and log4brains), Decision Brain found the required evidence 20/20, versus 15/20 for the same model plus keyword search.
All Facts (2)
When an agent believes item A supersedes item B, another agent must each quote a passage from the original text to confirm before the handoff counts; on Invarail's 151 items, the team initiated 15 handoffs, confirmed 9, and the rest were rejected.
50%UnverifiedIn a controlled experiment on 24 frozen questions (covering the three repositories Invarail, GOV.UK content-publisher, and log4brains), Decision Brain found the required evidence 20/20, versus 15/20 for the same model plus keyword search.
50%