Abstract

Common Table Expressions (CTEs) provide a structured framework for defining reusable intermediate result sets within SQL statements. InterSystems IRIS implements CTEs via the WITH clause, enabling clearer query composition and modular analytical processing while remaining fully integrated with the IRIS cost-based optimizer.

This article explores the semantics of CTEs in InterSystems IRIS, explains their interaction with query optimization, discusses appropriate deployment scenarios, and presents executable examples illustrating practical patterns for production environments.

An engineering walkthrough of the IRIS-CardioFlow project architecture with real code for its AI, FHIR, and connectivity layers and the role of iris-agentic-dev in a modern ObjectScript workflow.

Introduction

Monitoring cardiovascular surgical flow in real time is a classic healthcare integration problem: data arrives from heterogeneous sources, must be persisted with clinical semantics, exposed through an API, and presented in a way the care team can act on. The CardioIris repository (internally named IRIS-CardioFlow) is a lean demonstration of that scenario, built on InterSystems IRIS 2026.

Hi Community,

Have you ever wished your EHR could think? Not just display data. Not just fire alerts. But actually read a patient record, reason over clinical guidelines, and write a structured referral order back to the system — in response to a single message from a clinician

In this article, I am going to show you how to create your own custom clinical AI agent.

🏥 About iris-fhir-agents App

iris-fhir-agents is a multi-agent clinical AI platform built entirely on InterSystems IRIS for Health.

When I started building Smart Discharge Navigator, I faced a common challenge: FHIR data is stored as JSON bundles, but the analysis I needed required joining multiple resources together, the kind of thing SQL was built for.

InterSystems FHIR SQL Builder solved this completely. Instead of parsing JSON bundles in application code, I was able to write plain SQL directly against FHIR resource projections inside IRIS for Health. This article shows exactly how I used it to build the population-level readmission risk scoring engine at the heart of the application.

Back when I was a Developer Support Engineer in the InterSystems Worldwide Response Center (WRC), I would occasionally receive cases involving large message backlogs in a production. The customer would discover that a subset of queued messages were no longer useful and would ask a question similar to the following:

Is there an established best practice for mass-aborting messages in a specific component's queue that match a particular set of criteria?

This article introduces SHAP explainability methods as an approach to understand the reasons behind predictions in machine learning black-box models. It also includes a simple Jupyter notebook that you can use and modify to gain hands-on experience with these concepts:

https://www.kaggle.com/code/jorgeivnjh/explainability-in-ml-models

https://github.com/JorgeIvanJH/Explainability-in-ML-models

We will leverage these concepts for a future implementation in our Continuous Training Pipeline: https://community.intersystems.com/post/complementing-iris-mlflow-continuous-training-ct-pipeline

I’m pleased to share a demo of FHIR Agent Studio, now available on YouTube.

FHIR Agent Studio Demo

https://www.youtube.com/watch?v=vktfq_kvNnk

FHIR Agent Studio brings AI agents together with FHIR, InterSystems IRIS, Vector Search, and large language models to demonstrate how developers can explore, build, and test agent-driven healthcare workflows.

You can also find more information here:

Introduction article: https://community.intersystems.com/post/introducing-fhir-agent-studio-ai-agents-fhir-intersystems-iris

GitHub repository: https://github.com/SeanConnelly/ai-studio-for-fhir

Hey! June Article Bounty is live on Global Masters! ☀️🚀

Submit a brand-new article on one of the announced topics and earn a bounty of 🏆 5,000 Global Masters points once it’s approved! 🎉

Here’s the list of June topics:

An AI agent reads the FHIR patient record before the consultation, asks the right questions based on what it already knows, detects critical red flags, and writes its findings back — so the physician arrives prepared.

This project was inspired in the suggested task #10 (Conversational FHIR Triage Assistant) for the InterSystems Programming Contest: AI Agents for FHIR

Healthcare Pain Points Addressed

Before a patient walks into a consultation room, a critical failure has already occurred: nobody read their medical history. The physician has 15 minutes.

I've seen that %JSON.Adaptor makes it easy to serialize and deserialize objects to JSON, but I've also seen people building custom serialization logic. Are there scenarios where %JSON.Adaptor falls short, such as handling nested objects, null values or custom field naming conventions? What has been your experience?

Sara is my entry for the InterSystems AI Agents for FHIR contest. Feel free to try out Sara and vote for Sara on the contest page.

https://youtu.be/UAjI9O848wU?si=BWTVk9gsV4xTOlUj

• Sara-1.5-4B on Hugging Face
• MedToolCalling on Hugging Face
• Sara on GitHub

Physicians spend only 47% of their work time on direct patient care [1]. The rest goes to EHR administrative tasks: order entry, documentation, prior authorizations, with 43% of their time spent on a clinical computer [2]

Healthcare billing isn’t a pipeline. It’s a conversation about trust. 

Every day, millions of clinical transactions flow from doctors’ keyboards to insurance ledgers. Standard health IT systems are built to count these transactions. They store them. They organize them. 

They route them. But standard systems don't notice them. 

We’ve built faster and faster databases to process claims, but we forgot to ask: Does this claim make sense? 

Because we don’t ask in real-time, we’ve accepted a compromise. We pay first, wait six months, and then hire forensic auditors to find the mistakes.

In .NET projects I usually rely on appsettings per environment. In IRIS Productions, settings are stored per component and seem tied to the namespace. What strategies do you use to manage different configurations across environments without manually changing settings every time you promote a Production?

Hi Community,

We're excited to invite you to the upcoming webinar: 

👉 Can FHIR also serve as input for operational management? 👈

🗓️ Date & Time: Wednesday, June 10th, 10 am CEST

In the previous article, we used pyprod to create production components while relying on the UI for production configuration. That same production can now be defined entirely in Python:

from intersystems_pyprod import Production, ServiceItem, ProcessItem, OperationItem

iris_package_name = "HelloWorld"

class MyProduction(Production):
    services = [
        ServiceItem(
            "MyServiceName",
            "HelloWorld.MyService",
            host_settings={"target": "MyProcessName"},
        )
    ]
    processes = [
        ProcessItem(
            "MyProcessName",
            "HelloWorld.MyProcess",
            host_settings={"target": "MyOperationName"},
        )
    ]
    operations = [
        OperationItem("MyOperationName", "HelloWorld.MyOperation")
    ]

The problem

How many times have we migrated an IRIS Instance to another machine, maybe even another version, and after a few days realized we forgot that one SSL Configuration critical for a Business Operations to work? Or maybe a credential, or a lonely class in a package by itself?

The solution

The simple solution is to make a checklist¹. A checklist of the entities we have to move. But simple checklists on Word documents are often forgotten, or just ignored.

Hello everyone,

The InterSystems Learning Services Certification Team is pleased to announce the release of the HealthShare Unified Care Record Deployment Specialist Certification exam. The exam is now available for purchase and scheduling in the InterSystems exam catalog.

Welcome to the monthly recap of updates and releases to VS Code and InterSystems-related extensions relevant to IRIS developers. 

Don’t forget, if you’re migrating from InterSystems Studio to VS Code, or want to deepen your knowledge, check out the VS Code training courses from George James Software: georgejames.com/vscode-training. 

This recap covers the four VS Code releases in May: v1.119, v1.120, v1.121, and v1.122.

Editor and navigation

• Quieter inline suggestions (v1.