<!-- mobian-agent-page publisher="dailydev" canonical="https://daily.dev/posts/how-included-health-built-federated-healthcare-agents-with-langgraph-and-deep-agents-4djwmkswk" -->

---
title: How Included Health Built Federated Healthcare Agents...
description: Included Health built Dot, an AI healthcare navigation agent, on a federated LangGraph 'supergraph' architecture using Deep Agents. Different product teams own...
canonical: https://daily.dev/posts/how-included-health-built-federated-healthcare-agents-with-langgraph-and-deep-agents-4djwmkswk
twitter:card: summary_large_image
twitter:site: @dailydotdev
og:type: website
og:site_name: daily.dev
og:title: How Included Health Built Federated Healthcare Agents with LangGraph and Deep Agents | daily.dev
og:description: Included Health built Dot, an AI healthcare navigation agent, on a federated LangGraph 'supergraph' architecture using Deep Agents. Different product teams own...
og:url: https://daily.dev/posts/how-included-health-built-federated-healthcare-agents-with-langgraph-and-deep-agents-4djwmkswk
og:image: https://api.daily.dev/og/posts/4djwMKSwk.png
og:image:alt: How Included Health Built Federated Healthcare Agents with LangGraph and Deep Agents
og:image:width: 1200
og:image:height: 630
og:locale: en
---

> ## Documentation Index
> Fetch the complete documentation index at: https://daily.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# How Included Health Built Federated Healthcare Agents with LangGraph and Deep Agents

**[LangChain](https://daily.dev/sources/langchain)** · 6 min read · 0 upvotes · 0 comments

## Summary

Included Health built Dot, an AI healthcare navigation agent, on a federated LangGraph 'supergraph' architecture using Deep Agents. Different product teams own separate sub-workflows (scheduling, urgent care, behavioral health) that share tone, context, and skills via Deep Agents' filesystem and a platform sub-agent for coverage questions. Skills act as a progressive-disclosure capability registry, human-in-the-loop handoff is a core design feature using LangGraph's durable execution, and LangSmith annotation queues plus multi-turn simulation evals support clinical oversight and safe migrations. After launching in August, the system reported a 75% lift in chat engagement, clinical routing agreement above a 95% target, and over 99% detection of high-risk situations.

## Full article

daily.dev links to this article rather than hosting it. Read it at the original source: <https://www.langchain.com/blog/how-included-health-built-federated-agents-for-healthcare-navigation-with-deep-agents-and-langgraph>

## Questions this post answers

### How does Deep Agents help maintain consistent tone and behavior across multiple sub-agents in a large LangGraph system?

Deep Agents lets teams define a global platform prompt for voice and tone shared across all sub-agents, plus a shared filesystem so an outgoing agent can summarize a conversation and pass a file path to the full history for the receiving agent. This lets a member move between agents owned by different teams without repeating themselves, and lets teams share capabilities like coverage-question handling as an inheritable platform sub-agent instead of duplicating routing logic.

_Teams designing multi-agent handoffs can follow real architecture patterns like this one on daily.dev._

### How can LangSmith multi-turn simulation evals reduce risk when migrating a production agent system to a new architecture?

Running a full eval suite of multi-turn user simulations before rollout let one team confirm mostly improved performance and gain confidence to share results with other affected teams, prior to migrating a multi-team production system from standard agents to Deep Agents. That evaluation safety net helped complete the migration across four product teams in under two weeks with no significant regressions and no team resistance.

_Engineers planning risky agent migrations can find similar eval-driven playbooks on daily.dev._

## Similar posts on daily.dev

- [Building Multi-Agent AI Systems with LangGraph: A Fitness & Nutrition Coach Example](https://daily.dev/posts/building-multi-agent-ai-systems-with-langgraph-a-fitness-nutrition-coach-example-eapbkvklj) · Medium · 1 upvotes · 0 comments
- [Agent Framework vs. Agent Harness, clearly explained\!](https://daily.dev/posts/agent-framework-vs-agent-harness-clearly-explained--wpfu254t5) · Daily Dose of Data Science \| Avi Chawla \| Substack · 110 upvotes · 19 comments
- [From firefighting to building: How AI agents restored our team’s core productivity](https://daily.dev/posts/from-firefighting-to-building-how-ai-agents-restored-our-team-s-core-productivity-zfyvdslnl) · Grab Tech Blog · 2 upvotes · 0 comments

---

Tags: [#ai-agents](https://daily.dev/tags/ai-agents), [#healthcare](https://daily.dev/tags/healthcare), [#langgraph](https://daily.dev/tags/langgraph), [#langsmith](https://daily.dev/tags/langsmith)

[View this post on daily.dev](https://daily.dev/posts/how-included-health-built-federated-healthcare-agents-with-langgraph-and-deep-agents-4djwmkswk)

```json
{"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]}
{"@context":"https://schema.org","@type":"TechArticle","headline":"How Included Health Built Federated Healthcare Agents with LangGraph and Deep Agents","url":"https://daily.dev/posts/how-included-health-built-federated-healthcare-agents-with-langgraph-and-deep-agents-4djwmkswk","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/how-included-health-built-federated-healthcare-agents-with-langgraph-and-deep-agents-4djwmkswk"},"datePublished":"2026-09-17T15:22:59.065Z","dateModified":"2026-09-19T10:07:30.767Z","description":"Included Health built Dot, an AI healthcare navigation agent, on a federated LangGraph 'supergraph' architecture using Deep Agents. Different product teams own...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/6dd16380911e54b525c132113656f80f?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/6dd16380911e54b525c132113656f80f?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"LangChain","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"LangChain","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/0f4f2629e0724a849823f8cd0d913e13","url":"https://daily.dev/sources/langchain"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/how-included-health-built-federated-healthcare-agents-with-langgraph-and-deep-agents-4djwmkswk","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai-agents,healthcare,langgraph,langsmith","timeRequired":"PT6M"}
{"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"LangChain","item":"https://daily.dev/sources/langchain"},{"@type":"ListItem","position":3,"name":"How Included Health Built Federated Healthcare Agents with LangGraph and Deep Agents"}]}
{"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/how-included-health-built-federated-healthcare-agents-with-langgraph-and-deep-agents-4djwmkswk#faq","mainEntity":[{"@type":"Question","name":"How does Deep Agents help maintain consistent tone and behavior across multiple sub-agents in a large LangGraph system?","acceptedAnswer":{"@type":"Answer","text":"Deep Agents lets teams define a global platform prompt for voice and tone shared across all sub-agents, plus a shared filesystem so an outgoing agent can summarize a conversation and pass a file path to the full history for the receiving agent. This lets a member move between agents owned by different teams without repeating themselves, and lets teams share capabilities like coverage-question handling as an inheritable platform sub-agent instead of duplicating routing logic. Teams designing multi-agent handoffs can follow real architecture patterns like this one on daily.dev."}},{"@type":"Question","name":"How can LangSmith multi-turn simulation evals reduce risk when migrating a production agent system to a new architecture?","acceptedAnswer":{"@type":"Answer","text":"Running a full eval suite of multi-turn user simulations before rollout let one team confirm mostly improved performance and gain confidence to share results with other affected teams, prior to migrating a multi-team production system from standard agents to Deep Agents. That evaluation safety net helped complete the migration across four product teams in under two weeks with no significant regressions and no team resistance. Engineers planning risky agent migrations can find similar eval-driven playbooks on daily.dev."}}]}
```

