Included Health built federated healthcare agents on LangGraph, lifting chat engagement 75%
LangChain · x · 2026-09-18
LangChain published a case study on how healthcare platform Included Health built Dot, an AI healthcare navigation guide using a federated multi-agent architecture on LangGraph and Deep Agents, with LangSmith for clinical oversight.
- Why: rigid decision-tree navigation couldn't handle cases where what members ask differs from what they need, nor flag emergencies like chest pain in the first turn.
- Evaluation: multi-turn simulation evals got 4 teams onto Deep Agents in under 2 weeks with no significant regressions.
- Results: 75% more chat engagement and 99%+ high-risk detection accuracy.
More from coding & agent
- Jev Plays Minecraft: an AI agent livestreams 24/7 to beat the Ender Dragon — jarrodwatts · 2026-09-18
- Making agents 10x faster and cheaper with jev: routing, review, and a $0.0039 browser demo — gabriel1 · 2026-09-18
- Honeycomb CTO Charity Majors: 'Production is a stage of development' — mipsytipsy · 2026-09-18
- Faros AI report: PRs merged with zero review up 31.3% as AI speeds coding — mipsytipsy · 2026-09-18
- Runware Ships Deep-Dive Prompt Guides for Pruna AI's P-Video-2 Pro Video Model — aziz4ai · 2026-09-18
- What do you re-check in the last moment before an AI agent acts? — Portotify · 2026-09-18