A deviation-triage agent prompt for regulated labs, with human sign-off
nlarusstone · x · 2026-11-11
Day 23 of an 'an agent a day' series: a Deviation Triage Agent that fires whenever a new deviation is registered. It pulls related notebook entries, samples, equipment and reagent lots, searches past deviations for similar events, summarizes their root causes and CAPAs and whether those CAPAs prevented recurrence, then drafts an investigation outline and proposes a severity with reasoning.
Guardrails: flag cases where 'human error' is proposed as root cause without supporting evidence; assign the draft to the QA owner; never change deviation status or close anything — a person signs off on every decision. The author argues regulated labs are overrun by paperwork and stand to benefit most from agents handling the administrative burden.
More from coding & agent
- Spotify's Claude Code 90% token-saving trick put to a real test — aakashgupta · 2026-11-11
- Bolt: Gemma 4 runs 100% on-device on iPhone to drive a robot dog health companion — DynamicWebPaige · 2026-11-11
- Dev shows off live voice-call AI agent 'Elise' that answers family calls and triages urgency — bigaiguy · 2026-11-11
- agents.md isn't just for AI agents — humans can grok codebases fast with it too — k7agar · 2026-11-11
- Animate real places in 3D with Claude and free map data from AWS and Overture — drbronk · 2026-11-11
- Microsoft Foundry pattern: version and deploy Toolboxes separately from agents behind stable endpoints — WirelessLife · 2026-11-11