Skip to main content
AI Automation & Agents

AI assistant for a national diagnostics network

An AI agent layer for a diagnostics network whose patient app has 1M+ downloads: plain-language lab-report explanations, test guidance, lab lookup and voice, orchestrated across MCP tool servers.

  • Sector Healthcare, Diagnostics
  • Client National diagnostics lab network
Downloads of the client's patient app on Google Play
1M+
Specialised MCP servers: tests, general, radiology, locations, reports
5
Patients can speak to the assistant as well as type
Voice
The starting point

The challenge

Patients struggle to understand their lab reports, which test to take next and where to go, while the lab's support staff answer the same questions all day.

The solution

What we built

  • Architected an orchestrator agent in PydanticAI that routes each request to specialised MCP tool servers for tests, reports, radiology documents, locations and general information.

  • The assistant explains lab reports in plain language, suggests relevant tests and answers questions about the lab's services.

  • Location tools find the nearest collection centres.

  • Added voice through VAPI, so patients can speak to the assistant as well as type.

  • Routed models through OpenRouter, including GLM.

Architecture

How the system works

MCP architecture: a PydanticAI orchestrator routes requests to five MCP servers for tests, general information, radiology documents, locations and reports, over the underlying knowledge bases and clinical data services
The orchestrator and its five MCP servers, each wrapping several tools and workflows.
Engineering

How it was engineered

  • Built evaluation sets from sample reports and patient-style questions, and ran them after every iteration and in production.

  • Traced every agent run and tool call in Logfire.

  • Kept each capability in its own MCP server, so tools can be tested, updated and deployed independently.

Scope

What was delivered

01

Orchestrator agent

02

Specialised MCP tool servers

03

Lab-report explanation and test guidance

04

Location lookup

05

Voice interface

06

Logfire observability

Technology

Stack

PydanticAIMCPOpenRouterGLMFastAPIVAPILogfire

Need something similar?

We can scope and build a system with comparable capabilities, shaped around your own workflows, data and integrations.