Triangle Health · 2025 – Present
Multi-agent AI healthcare platform
End-to-end architecture for an AI-powered healthcare platform — conversational agents, clinical workflows, FHIR interoperability, and production-grade orchestration.
Role: Principal Software Engineer
- AI platforms
- Healthcare
- Multi-agent systems
Collaboration
People I built this with
The people behind this chapter—and the part each of them played in shaping the work.
Co-Founder & COO, Triangle Health
Arun is Triangle Health's COO and one of its co-founders. His own experience navigating a serious diagnosis, fragmented medical records, research, and treatment options became the mission behind the company. We now work closely together on a shared AI workspace designed to give patients and practitioners clearer answers.
Co-Founder & CEO, Triangle Health · Former Senior Director of Product, Bird
After Bird and several other roles, Jonathan joined Justin Balthrop and Arun Verma to launch Triangle Health, a shared AI workspace for patients and practitioners. Jonathan and Justin later reached out and convinced me to join them, bringing our Bird collaboration into healthcare AI.
CTO & Co-Founder, Triangle Health · Former CTO, Bird and Geni
Justin and I are working together again at Triangle Health, where he is CTO. This chapter brings our long-running collaboration into AI-powered healthcare, combining conversational agents, clinical workflows, interoperability, and production platform engineering.
Full-stack Engineer at Triangle Health · Former iOS engineer, Bird and Snap
Jason and I now work together again at Triangle Health, solving difficult healthcare problems across the full stack. By teaming up with Claude and Cursor, he has moved beyond mobile specialization to deliver complete product experiences from interface through backend behavior.
Context
The problem and my role
Problem
Healthcare teams need AI that can participate in real clinical workflows — collecting data, analyzing documents, orchestrating steps — while meeting interoperability, consent, and compliance requirements. Generic chatbots break down when tools, identity, and auditability matter.
Role
Technical leader for design and implementation across frontend, backend, AI infrastructure, and cloud. Established scalable engineering patterns adopted across the platform and mentored engineers on AI integration and system design.
Constraints
- Regulatory and privacy expectations around patient data and consent
- Need for specialized agents rather than a single monolithic prompt
- Interoperability with healthcare systems via HL7 FHIR and SMART on FHIR
- Production observability for distributed AI services
- Human-in-the-loop decision points for clinical safety
System
Architecture
System map
AI inside a clinical workflow
A supervised conversation routes work through specialized agents and standardized healthcare tools while preserving consent, observability, and human review.
- 01
Patient or care team
Begins a conversational or workflow-driven interaction
- 02
Conversation layer
Maintains context, identity, consent, and structured interaction
- 03
Supervisor agent
Plans work and coordinates specialized capabilities
- 04
Specialized agents
Handle onboarding, data collection, documents, and workflow steps
- 05
MCP tools
Expose clinical capabilities through consistent, auditable interfaces
- 06
FHIR systems
Exchange healthcare data through HL7 FHIR and SMART on FHIR
- 07
Observability and human review
Tracing, evaluation, and explicit intervention points surround the flow
Execution
What I built
- Architected a multi-agent platform using GPT-5.x, MCP, and LangGraph for patient onboarding, clinical data collection, document analysis, and workflow orchestration.
- Built an extensible MCP server ecosystem exposing healthcare tools and clinical capabilities through standardized interfaces.
- Designed production AI pipelines covering prompt engineering, tool calling, structured outputs, retrieval workflows, and HITL controls.
- Implemented consent, authentication, authorization, and secure data-sharing for patient-facing AI applications.
- Established OpenTelemetry + Datadog observability with structured logging, metrics, and tracing for AI services.
- Used event-driven cloud-native backends with asynchronous processing and resilient messaging.
Tradeoffs
Technical decisions
MCP as the tool boundary
- Decision
- Expose healthcare capabilities through reusable MCP servers and SDKs instead of binding every agent directly to backend services.
- Why
- A standardized boundary makes tools easier to discover, secure, observe, test, and reuse across workflows and teams.
- Tradeoff
- The abstraction adds protocol and schema design work, but avoids a larger collection of one-off integrations.
Explicit orchestration over prompt-only autonomy
- Decision
- Use LangGraph to coordinate specialized agents, structured outputs, tool calls, and human-in-the-loop checkpoints.
- Why
- Clinical workflows need visible state transitions, recovery paths, and intervention points that a monolithic prompt cannot reliably provide.
- Tradeoff
- Workflow graphs require more deliberate state design, but make production behavior easier to inspect and operate.
Observability as a platform capability
- Decision
- Instrument distributed AI services with OpenTelemetry, Datadog, structured logs, metrics, and traces.
- Why
- Prompts and model calls are only part of a production workflow; teams need end-to-end evidence when tools, queues, services, or agents fail.
- Tradeoff
- Rich telemetry adds implementation and data-governance cost, especially around sensitive healthcare context.
Value
Product impact
User impact
Supports AI-assisted healthcare interactions that remain connected to identity, consent, clinical data, and human decision points.
Business impact
Creates reusable agent, MCP, interoperability, and observability foundations that product teams can build on instead of recreating for each workflow.
Results
Outcomes
- Unified architecture spanning conversational AI, clinical workflows, and healthcare interoperability standards.
- Reusable MCP tool surfaces and SDKs that accelerate feature development across teams.
- Engineering standards for AI evaluation, testing, deployment automation, and operational excellence.
- Close collaboration with product, clinical, and executive stakeholders to turn requirements into scalable systems.
Notes
Notes from the system
Agent specialization
Rather than one general assistant, specialized agents own onboarding, data collection, document analysis, and orchestration — coordinated through LangGraph with clear tool boundaries via MCP.
Interoperability without shortcuts
SMART on FHIR and OAuth-backed access patterns keep AI-assisted workflows aligned with healthcare identity and data-sharing norms, instead of brittle one-off integrations.
Reflection
Lessons learned
- “Production healthcare AI must be observable, interruptible, and grounded in explicit system boundaries.”
- “Platform investments compound when product teams can reuse tools, evaluations, and workflow patterns rather than rebuilding AI integration from scratch.”
Tools
Stack
Next case study
Professor Claw & The Claw Institute →