Superpower Daily

Superpower Daily

Your reading space

Sign in
Anthropic Sets Up Bay Area Wet Lab for Physical Biology WorkOpenAI Launches Astra for Law as a Platform for Legal AI Builde...Review Separates Workflow Approval From Tool Enforcement in AI...LangChain Adds Jev Classifier to Agent Workflows for Routing an...Mapbox Adds Live Maps and Route Controls for AI AgentsINTERPOL Uses AI to Identify 126 Suspected Terrorist FightersAnthropic Sets Up Bay Area Wet Lab for Physical Biology WorkOpenAI Launches Astra for Law as a Platform for Legal AI Builde...Review Separates Workflow Approval From Tool Enforcement in AI...LangChain Adds Jev Classifier to Agent Workflows for Routing an...Mapbox Adds Live Maps and Route Controls for AI AgentsINTERPOL Uses AI to Identify 126 Suspected Terrorist Fighters
Swipe

Included Health Launches Dot AI Guide With Human Escalation

The healthcare-navigation guide routes questions across specialized AI workflows, but pauses for a care advocate when the system is uncertain and sends every conversation for clinical review.

By 2 min read
Included Health Launches Dot AI Guide With Human Escalation
Included Health Launches Dot AI Guide With Human Escalation

Listen to this story

The audio brief

About 1:30
0:001:30
Read transcript
Included Health is putting an AI healthcare guide, called Dot, in front of employer and health-plan members—but with a built-in pause button. When Dot is uncertain, it stops and hands the conversation to a human member-care advocate, then resumes with the context intact. Dot is designed to handle more than a single question-and-answer task. Its central workflow, the Dot supergraph, routes conversations into specialized paths for urgent-care intake, appointment scheduling, specialist search, behavioral health, coverage, and other administrative needs. Included Health built that system as a federated group of AI agents using LangGraph and Deep Agents. Instead of rebuilding the same coverage-answering capability inside every path, teams can share it as a platform sub-agent. Deep Agents also carries tone instructions, summaries, and conversation history between workflows owned by different teams. The system loads service details progressively, like skills in a virtual filesystem; Included Health says employer plans could eventually encode roughly twenty to thirty benefits this way. Every conversation goes into a LangSmith queue for clinical review, including care recommendations and emergency-guardrail behavior. Included Health reports a seventy-five percent lift in chat engagement, clinician agreement above ninety-five percent, and detection of more than ninety-nine percent of high-risk situations—but those figures come from its own review process. The key constraint now is whether that human escalation and clinical oversight can remain consistent as Dot handles more journeys.

Story brief

3 key points

Included Health’s Dot is now being used by clients as a healthcare-navigation layer that routes care, coverage, and administrative requests across specialized workflows, then hands uncertain cases to human member-care advocates without losing context. Built as a federated LangGraph and Deep Agents system, it centralizes reusable capabilities such as coverage answers and loads benefit details as needed. Included...

  1. 01

    Dot’s “supergraph” spans urgent-care intake, scheduling, specialist search, behavioral health, and other member journeys.

  2. 02

    Included Health moved four product teams from standard agents to Deep Agents in under two weeks without significant regressions.

  3. 03

    LangSmith queues every conversation for clinical review, including care recommendations and emergency-guardrail behavior.

Included Health launched Dot, an AI-powered healthcare guide, to clients in August. The guide can direct members through care, coverage and administrative questions, but it is designed to pause for a human member care advocate when an agent is uncertain.

A router for healthcare’s branching questions

Dot is part of Included Health’s healthcare-navigation service for employers and health plans. Its main LangGraph workflow, called the Dot supergraph, routes conversations into sub-workflows for urgent-care intake, appointment scheduling, specialist search, behavioral health and other member journeys.

Included Health built the guide as a federated multi-agent system using LangGraph and Deep Agents, with different product teams owning portions of the graph. Rather than duplicate a coverage-answering function inside each journey, the company made it a shared platform sub-agent that multiple workflows can inherit.

Skills supply the service-specific detail

The system represents clinical capabilities and services as skills stored in a virtual filesystem. An agent starts with short descriptions, then progressively loads fuller instructions for the skills it decides fit a member’s needs. Included Health is also working toward encoding third-party employer benefits as skills; it says a plan can contain about 20 to 30 benefits.

The review loop

  • Every conversation enters a LangSmith annotation queue for clinical review of care recommendations and emergency-guardrail behavior.
  • Those clinical labels are exported for Included Health’s operational metrics dashboards.
  • The company used multi-turn simulated-user evaluations while moving four product teams from standard agents to Deep Agents in under two weeks, without significant regressions.

Early performance is based on the company’s own reviews

Included Health reports a 75% lift in chat engagement after launch. It also says clinicians agreed with Dot’s care recommendations above its 95% target in graded conversations, while regular clinical audits found the guide identified more than 99% of high-risk situations.

Those figures come from Included Health’s own review process and are reported in a LangChain case study. The notable design choice is less the number of agents than the attempt to preserve one conversation across automated routing and human intervention—while keeping clinical oversight in the loop.

Sources

  1. langchain.comHow Included Health Built Federated Healthcare Agents with LangGraph and Deep Agents

Loading discussion...

YOUR READING SPACE

Notifications

Included Health Launches Dot AI Guide With Human Escalation | Superpower Daily