Medplum AI Concierge: build intelligent patient portals with Generative UI

Patient portals give users access to health data, but they do not always make that data easy to explore or understand. In most cases, patients still have to navigate static screens, interpret raw results, and figure out what matters on their own.

To make this experience more useful, healthcare applications need better ways to help patients explore and interpret their data. Aligned with these goals, Vinta has launched the Medplum AI Concierge, an open-source demonstration of an AI-powered healthcare dashboard that leverages Generative UI to transform how patients interact with their medical data.

Before we get into the architecture, here’s a quick look at the Medplum AI Concierge in action.

‍

‍

The core technology: Generative UI, CopilotKit, and LangGraph

At the heart of the Medplum AI Concierge is the Agent–User Interaction (AG-UI) Protocol, powered by CopilotKit and orchestrated by LangGraph. This combination allows the application to move beyond simple conversational-based chatbot. Instead of just replying with text, the AI agent can render dynamic React components—widgets—directly into the chat interface or dashboard. For example, when a patient asks about their blood pressure, the agent fetches the structured FHIR data from Medplum’s backend and generates an interactive chart on the fly.

Simplifying health data interpretation

Here’s how a typical workflow looks when Generative UI replaces static portal navigation:

1. The patient simply types, "Show my glucose levels over the past year."
2. The AI interprets the request, queries the Medplum FHIR backend for the relevant Observation resources, and instantly renders a dynamic "Lab Results - Glucose" widget on the dashboard, complete with trend charts and status badges (Normal/High).
3. But it doesn't stop at visualization. Patients can click the "Interpret Data" button. The AI analyzes all visible widget data and presents a contextualized, easy-to-understand interpretation in the chat sidebar.
4. The result: an empowered patient, fewer confused messages to the clinic, and a highly personalized flow of information that spans vitals, lab results, medications, and care plans. This creates immediate value for patients, while also enabling digital health platforms to deliver an AI-native user experience.

Our solution: the Medplum AI Concierge open-source demo

The Medplum AI Concierge is a free, open-source project that gives development teams a blueprint for building intelligent healthcare applications. It provides a robust architecture for:

• Connecting conversational AI with a strict, secure, FHIR-compliant EHR backend (Medplum).

• Dynamically generating UI widgets for vitals (Blood Pressure, BMI, Weight, etc.) and lab results (HbA1c, Cholesterol, eGFR, Fasting Insulin, etc.).

• Enabling complex FHIR searches through natural language.

• Integrating Care Plans and Medications into the conversational context, allowing patients to ask questions about their ongoing treatments.

Check out the Medplum AI Concierge on GitHub and explore the open-source architecture that brings Generative UI into your healthcare apps.

Turning complex health data into actionable insights

Medplum AI Concierge is a practical example of how Generative UI can make patient-facing healthcare applications more useful. Instead of relying only on static dashboards and fixed navigation, it shows how AI can help patients ask better questions, surface the right data, and interact with that data in a more contextual way.

The patterns demonstrated in the project are relevant across a few different audiences:

For patients -  it creates a more navigable experience around health data, making it easier to ask questions, follow trends, and understand what they are seeing.

For providers and care teams - it can reduce part of the back-and-forth that happens when patients are left alone to interpret raw results or static records.

For healthtech product teams - it offers a concrete reference for combining conversational AI, structured FHIR data, and dynamic UI in a patient-facing workflow.

For teams already building on top of Medplum or other FHIR-based systems, the demo can also serve as a technical reference for implementing similar patterns in production.

Working on patient-facing AI in healthcare?
Vinta can turn patterns like this into production-ready experiences.