Safety on OpenAdapt Bloghttps://blog.openadapt.ai/tags/safety/Recent content in Safety on OpenAdapt BlogHugo -- 0.164.0en-usFri, 17 Jul 2026 00:00:00 +0000The silent wrong write: your automation should halt instead of guessinghttps://blog.openadapt.ai/posts/silent-wrong-action/Fri, 17 Jul 2026 00:00:00 +0000https://blog.openadapt.ai/posts/silent-wrong-action/Screen-only verification silently passed 5 of 7 transactional fault classes — a green banner over a wrong database. We found the failure class in our own engine first, fixed five silent wrong-write modes, and built effect verification against the system of record: 55.6% silent wrong-action rate driven to 0%.We ran it on a real EMR. The compiler won.https://blog.openadapt.ai/posts/openemr-benchmark/Wed, 08 Jul 2026 00:00:00 +0000https://blog.openadapt.ai/posts/openemr-benchmark/Compiled workflows vs. a frontier computer-use agent on real OpenEMR: 20/20 vs 10/10 task success, 1.8x faster, $0 vs $0.55 per run in model spend — and with agent fallback, $0.029 vs $0.238 per successful run. Deterministic compilation wins on cost and latency, and never silently writes the wrong thing.