Numan Builds Eval‑First AI Health Coach Nu with LangGraph and LangSmith
Current overview (not historical)
Numan has developed an AI health coach called Nu, leveraging LangGraph and LangSmith to prioritize evaluation over direct medical advice. Nu is positioned as a wellness product, explicitly avoiding diagnosis, prescription, or clinical decision‑making. The team introduced a classification‑assessment rubric and a simulated dialogue layer to stay within regulatory boundaries, and implemented safety probes and guards to review each response before release, ensuring compliance with MHRA regulations. While Nu is not a medical device, the design choices reflect a cautious approach to regulatory risk, balancing user engagement with safety oversight. The project demonstrates how AI frameworks can be used to build health‑related tools that respect legal limits while still providing personalized guidance.
Written with AI from the reporting · updated 10/19/2026
Expand the detailed fact route and sources
Story route
A station-by-station route from the first public evidence onward; every station carries its own evidence and uncertainty.
- 1Unclassified fact stationOct 19, 23:06single sourcereport-time onlyrevised
Numan 使用 LangGraph 和 LangSmith 构建评估优先的 AI 健康教练
Read original source ↗ LangChain BlogReplay this moment in the explorerEvidence & revisions · 1 source records
- Subject：
- Numan
- Action：
- 使用 LangGraph 和 LangSmith 构建评估优先的 AI 健康教练
- Object：
- AI 健康教练 Nu
- Occurred (fact side)：
- not recorded
- Published (valid side)：
- Oct 19, 23:00
- First seen (known side)：
- Oct 19, 23:06
Fact stationSingle source · one-sided claimRevisedReport-time onlyCopy may have been revised later; time replay is bounded. Layer labels group reading only, not causation between layers.
Uncertainty marks flag where to check the sources; they are not proven causation.
Report timeline
Explore every side through dated source reports.
- LangChain BlogRelated fact: single sourceFact occurrence time unverifiedSource report revisedNuman builds eval-first AI health coach with LangGraph to avoid medical regulation pitfalls
Report first recorded Oct 19, 23:06
Numan, a UK digital health company, developed Nu, an AI health coach for patients managing long-term conditions. To avoid crossing into medical diagnosis or prescriptions, the team abandoned static single-turn evaluations and scripted multi-turn tests, which failed to capture conversation context and safety boundaries. Instead, they built a custom eval framework using LangGraph and LangSmith, implementing a supervisor model that orchestrates handoffs to domain-specialist sub-agents with categorized rubrics to evaluate safety and coaching quality across full conversation histories.
Read original source ↗
Event discussion
Reader opinions are hosted on GitHub Discussions; posting requires a GitHub account. Comments are not verified facts.