Meet withLove: The AI‑Native Platform for InterSystems IRIS
You’ve seen how tools like Lovable are shaking up web development. People are spinning up entire apps just by talking to an AI, almost like pair‑programming on steroids.
Now imagine bringing that same “vibe coding” experience into healthcare. know, it sounds crazy. Healthcare is complex, full of regulations, and usually gives us a headache just thinking about the interoperability rules.
That’s exactly the space where withLove lives: an AI‑Native, Low‑Code platform built entirely on InterSystems IRIS for Health.
And no, this is not “one more chatbot” that spits out half‑broken code for you to babysit. The idea is different. Think of a full studio where autonomous agents plan, code, compile, and deploy solutions while you stay focused on architecture and intent.
The Concept: “Self‑Driving” IRIS Health Studio
The world already has plenty of AI helpers for React, Supabase, and friends. What’s missing is something that speaks the stack that actually runs hospitals. withLove is specialized in that universe: FHIR R4, HL7 v2, ObjectScript, and SQL are its native language.
Your role is simple to describe, but powerful: you are the Architect. withLove acts as your full‑stack team, on call 24/7. You say what you need — “I want an API to manage Dengue cases with FHIR validation baked in” — and the platform delivers a running solution instead of just a code snippet.
Multi‑Agent Architecture: Your Silent Team
At the core, there’s an orchestrator called GenAi.AgentRun(). It analyzes what you want and distributes tasks to software “factories.” The generated code follows the strict best practices we are used to.
Meet the squad:
- 🎨 UI Agent (AppFactory): Builds responsive UIs using TailwindCSS and Alpine.js. Finally, screens that don’t look like they came from a Windows XP kiosk.
- 💾 Backend Agent (ClassFactory): Designs and compiles
%Persistentclasses for you. It takes care of types, indexes, and relationships without ceremony. - 🔌 API Agent (ApiFactory): Publishes solid REST services (
%CSP.REST) with routes, error handling, and basic documentation wired in from the start. - ⚙️ Interop Agent (InteropFactory): If integration is your world, this is the fun part. It generates DTL and Production components to connect HL7 v2, SOAP, and FHIR flows.
- ⚕️ FHIR Agent & Handler: Produces synthetic JSON Bundles for testing and the logic to import them into SQL tables, so you can prototype without waiting for real data.
Differentials That Actually Matter
1. Brownfield Scanner: Upgrade Without Rewriting Everything
Most serious healthcare projects don’t start from a blank page. There’s always a big legacy system behind the scenes. The Scanner Agent tackles exactly that: it scans your existing classes, reverse‑engineers the data model, and builds modern REST APIs on top. You expose old data with new patterns, without tearing down the core system.
2. RAG Knowledge Base: An AI That Knows Your Rules
withLove ships with a RAG (Retrieval‑Augmented Generation) engine embedded in the workflow. You can load it with clinical protocols, PDFs, and technical manuals from your institution. The agents will use this specific knowledge to answer questions or write code that respects your institution's rules.
3. Human-in-the-Loop
The AI does the heavy lifting, but you are the boss. We are not handing the keys to Skynet (yet). The workflow forces a Review & Approve step. You see the ObjectScript code, review it, and only then it gets compiled. Safe and controlled.
Curious to try it out? Clone the repo, start the container, and ship your first FHIR API in a couple of minutes, preferably before your coffee gets cold.☕
If you share our vision for an AI-native healthcare stack, please vote for withLove in the InterSystems Full Stack Contest. Your support means the world to us! 🤍