Python is an interpreted high-level programming language for general-purpose programming. Created by Guido van Rossum and first released in 1991, Python has a design philosophy that emphasizes code readability, notably using significant whitespace
Every clinic visit starts the same way: a patient sits in a waiting room holding a clipboard, answering the same questions they'll be asked again ten minutes later — while the clinician walks in cold, with no idea whether the next case is a sore throat or a heart attack in progress.
That gap: between what the patient knows and what the clinician sees — is what Triage Park closes. It's our entry for the InterSystems Programming Contest: AI Agents for FHIR.
In my first article, I described the baseline version of the FHIR Patient Snapshot Agent: a Streamlit and Python application that retrieves FHIR resources from InterSystems IRIS for Health and uses an LLM to generate a concise patient summary.
This follow-up article explains how I extended the project with two additional InterSystems-focused features:
The goal was to make the project more useful as a clinical summarisation prototype while keeping the design small enough to understand and reproduce.
FHIR Patient Snapshot Agent is a small open-source application built for the InterSystems AI Agents and FHIR Programming Contest.
The project implements the suggested Smart Patient Summary Generator idea: it retrieves structured FHIR resources for a selected patient and generates a concise, role-specific patient summary.
The goal is not to diagnose or recommend treatment.
On save the ClassMethod:
ClassMethod create() [ Language = python ] {
print("python")
}
it has received the error :
Compilation started on 06/03/2026 02:15:21 with qualifiers 'cuk /multicompile=0'
ERROR #7802: Worker job/s '1078:17' unexpectedly shut down in group '#Default:(9119826733444):0'.
ERROR #7802: Worker job/s '1078:17' unexpectedly shut down in group '#Default:(9119826733444):0'.
with the compileFlags "cuk" the return is:
ERROR #7802: Worker job/s '1160:34' unexpectedly shut down in group '#Default:(6933525859080):0'.
At 4:57 PM on a Friday, a routine laboratory order failed.
The patient's sample was already in transit. The external reference laboratory rejected the request — it could not uniquely identify the patient. The insurance operator rejected authorization for a different reason. Neither system spoke the same language, neither exposed compatible error messages, and the only integration layer in the middle simply forwarded requests.
A laboratory technician spent the next 25 minutes navigating portals, copying identifiers, and manually reconciling data between systems.
Smart Patient Summary Generator is an AI-powered FHIR demo application built for InterSystems IRIS for Health. It reads FHIR R4 patient data, extracts key clinical information, and generates concise summaries for four different roles:
By consolidating fragmented FHIR records into role-specific summaries, the application helps clinicians quickly understand a patient’s current condition, recent changes, and follow-up risks. For patients and family caregivers, it presents the same clinical context in a more accessible format.
Hi Community,
In this article, I will introduce my application iris-fhir-agents A multi-agent clinical AI platform powered by InterSystems IRIS for Health. Features agents for triage, specialist consultation, pharmacy safety, and FHIR server exploration — all grounded by IRIS Vector Search RAG. Includes a no-code Agent Builder that lets you design and deploy custom clinical agents without writing a single line of code.
Hi!
I'm trying to compiling a class with an Embedded Python and got this error:
Compilation started on 06/12/2026 11:44:17 with qualifiers 'cuk'
Compiling class User.VectorSearch
ERROR #7802: Worker job/s '749:33' unexpectedly shut down in group '#Default:(446070926892):0'.
ERROR #7812: Work queue unexpectedly removed, shutting down.
ERROR #5002: ObjectScript error: <THROW>WaitForComplete+215^%SYS.WorkQueueMgr *%Exception.StatusException ERROR #7802: Worker job/s '749:33' unexpectedly shut down in group '#Default:(446070926892):0'.
ERROR #7812: Work queue unexpectedly removed, shutting down.
Detected 3 errors during compilation in 1.020s.
Most "AI agent + FHIR" projects end up with the same shape: a FHIR server over here, a vector database over there, and a Python service in the middle whose job is to call an embedding API, marshal float arrays back and forth, and keep two datastores in sync. Three moving parts, two network hops, and an embedding client you now own forever.
Triage Park: our entry for the InterSystems Programming Contest: AI Agents for FHIR, doesn't have any of that. The agent never computes an embedding. It never imports an OpenAI embeddings client. There is no vector database.
Hi everyone,
I created a short demo and reference repository showing how to configure Auth0 as an OAuth provider for an InterSystems IRIS FHIR server, and how to call protected FHIR resources from a Python Flask application.
The links below include a video walkthrough and a github repo with the sample application used in the video
Links
Video walkthrough:
GitHub repository: https://github.com/MarshyKid/iris-fhir-oauth-demo
Hospital readmissions cost the US healthcare system $17 billion annually. A significant portion of those readmissions are preventable — but only if the right information reaches the right clinician at the right moment: at discharge.
That's the problem I set out to solve with Smart Discharge Navigator, my entry for the InterSystems Programming Contest: AI Agents for FHIR 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.
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.
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
Before a patient walks into a consultation room, a critical failure has already occurred: nobody read their medical history. The physician has 15 minutes.
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")
]
In the previous IoP article, I showed how IoP can expose Python messages to DTL by generating JSON schemas. That is useful when the message is primarily a Python object and we want the IRIS tooling to understand its structure.
This time, the direction is a little different.
Starting with IoP 3.7.1, a PersistentMessage can now be a native IRIS message body class. The Python class is still the source code you write, but the generated IRIS class extends Ens.MessageBody
Vector search is a retrieval method that converts text, images, audio, and other data into numeric vectors using an AI model, and then searches for items that are semantically close. It enables “semantic similarity search” from free text, which is difficult with keyword search alone.
However, in real use, I encountered cases where results that are “close in meaning” but logically the opposite appeared near the top of the search results.
This is a serious issue in situations where affirmation vs. negation matters. If the system returns the wrong answer, the impact can be significant, so we cannot ignore this problem.
This article does not propose a new algorithm. I wrote it to share a practical way I found useful when semantic search fails due to negation.
TL;DR: This article demonstrates how to run GraphRAG-style hybrid retrieval—combining vector similarity, graph traversal, and full-text search—entirely within InterSystems IRIS using the
iris-vector-graphpackage. We use a fraud detection scenario to show how graph patterns reveal what vector search alone would miss.
Every year, businesses and consumers lose billions to fraud. In 2024 alone, consumers reported $12.5 billion lost—a 25% increase year over year. What makes modern fraud so difficult to detect is that fraudsters rarely work alone.
With Embedded Python and the Native API, it is becoming increasingly natural to write part of IRIS application logic in Python. But one question quickly comes up: how can you manipulate IRIS persistent objects from Python without losing the connection to the native object model, class dictionary, indexes, storage, and SQL projections?
iris-persistence explores that question. The project provides a Python object persistence layer for InterSystems IRIS, inspired by %Persistent
I am trying to connect to hive database and IRIS Intersystems Databases using jaydebeapi in python. I am able to connect to one database at a time. While trying to connect to other database, I am getting the below error
"Class org.apache.hive.jdbc.HiveDriver is not found"
or
"Class com.intersystems.jdbc.IRISDriver is not found"
lin1 -
hive_con = jd.connect(java_driver_class, jdbc_conn_url, [hive_user, hive_pass],jarfile)
lin2 -
iris_con = jd.connect(iris_driver_class, iris_conn_url, [iris_user, iris_pass],jarfile)
Hello everyone.
After trying to run Python methods in the intersystemsdc/irishealth-community Docker container, which no longer allows any Python methods to be executed, I decided to abandon this version and start working with containers.intersystems.com/intersystems/iris-community.
In this environment, the Python methods work, which was a significant improvement.
I'm trying to import my libraries with pip install -r requirements.txt
When developing Python applications with InterSystems IRIS, you can quickly end up with several execution contexts:
python3 process that loads the Embedded Python libraries from a local IRIS installation;These three cases are useful, but they do not behave exactly the same way for imports, system configuration, object APIs, and SQL access.