LangChain details Nu's architecture: supervisor agent routes to specialist subagents, evals run the real graph
LangChain · x · 2026-10-20
LangChain shared more architecture details of Numan's AI health coach Nu:
- LangGraph is the agent itself: a supervisor model orchestrates handoffs to domain-specialist subagents.
- Each subagent owns one coaching area with its own prompt and tools.
- The composable design makes adding new specialists cheap and keeps safety evals uniform across all of them.
Every eval — from single-reply fixtures to simulated multi-turn conversations with LLM patient personas — runs against the real agent graph, so scores reflect exactly what a patient would encounter.
Related event: Numan Builds Regulated AI Health Coach on LangGraph with Evaluation Loop(4 posts)→
More from coding & agent
- Ethan Mollick's new book charts 30 months of AI progress, from cyborg to conjurer work — rseroter · 2026-10-23
- OpenJet claims Qwen3.8-27B coding runs 1.9x faster than llama.cpp on one RTX 3090 — JeremyCMorgan · 2026-10-23
- Jensen Huang details Vera Rubin agentic stack: NVL72, MGX, CMX and RTX — rohanpaul_ai · 2026-10-23
- Building an autonomous SEO agent in Hermes with three skills: programmatic pages, Keywords Everywhere, DataForSEO — EXM7777 · 2026-10-23
- Building a sports betting AI agent with onchain execution and human approval by default: architecture and lessons — Dry-Comfortable-2678 · 2026-10-23
- Capy 0.5.0 lets Claude Pro/Max subscribers reuse their plan quota, adds OIDC cloud access — garrytan · 2026-10-23