Hey Community!

We're happy to share the next video in the "Code to Care" series on our InterSystems Developers YouTube:

⏯  When AIs Debate: Agentic AI in Action with Math Problems

#InterSystems Demo Games entry

⏯️ Copilot for InterSystems Embedded BI

The Co-Pilot enables you to leverage InterSystems BI without deep knowledge in InterSystems BI. You can create new cube, modify existing cubes or leverage existing cubes to plot charts and pivots just by speaking to the copilot.

Presenters:
🗣 @Michael Braam, Sales Engineer Manager, InterSystems
🗣 @Andreas Schuetz, Sales Engineer, InterSystems
🗣 @Shubham Sumalya, Sales Engineer, InterSystems

#InterSystems Demo Games entry

⏯️ AI Smart Data Fabric

Shows how IRIS for Health can supercharge AI development with a Smart Data Fabric to train and feed their AI Models.

Presenters:
🗣 @Kevin Kindschuh, Senior Sales Engineer, InterSystems
🗣 @Jeff Semmens, Sales Engineer, InterSystems

#InterSystems Demo Games entry

⏯️ Autonomous Business Intelligent Clerk (ABiC) - Combining InterSystems BI and Generative AI

Our Autonomous Business Intelligent Clerk, or ABiC for short, is a prototype revolutionizing how companies process data and make decisions. Normally, to get insights from data, you’d need IT knowledge or expertise in statistics. But with ABiC, that’s no longer necessary. All you have to do is ask your question in plain language. ABiC understands your interests and intentions, then shows a clear dashboard to guide your decisions. With ABiC, complex data is autonomously analyzed and turned into answers that support users, helping to accelerate business processes. This demo sends the metadata of InterSystems BI cubes to LLM. How does it work? Check out the video for more details!

Presenters:
🗣 @Tomo Okuyama, Sales Engineer, InterSystems
🗣 @Nobuyuki Hata, Sales Engineer, InterSystems
🗣 @Tomoko Furuzono, Sales Engineer, InterSystems
🗣 @Mihoko Iijima, Training Sales Engineer, InterSystems

#InterSystems Demo Games entry

⏯️  Closing the Scientific Knowledge Gap with AI

For venture capitalists (VCs), evaluating research can be challenging. While researchers typically possess years of training and deep expertise in their field, the VCs tasked with assessing their work often lack domain-specific knowledge. This can lead to incomplete understanding of scientific data and an inability to direct organizational initiatives. To solve this problem, we have designed a solution that empowers VCs with AI-driven due diligence: ResearchExplorer. ResearchExplorer is powered by InterSystems IRIS and GPT-4o to help analyze private biomedical research alongside public sources like PubMed using Retrieval-Augmented Generation (RAG). Users submit natural language queries, and the system returns structured insights, head-to-head research comparisons, and AI-generated summaries. This allows users to bridge expertise gaps while securely protecting proprietary data.

Presenters:
🗣 @Jesse Reffsin, Senior Sales Engineer, InterSystems
🗣 @Lynn Wu, Sales Engineer, InterSystems

Hi Community,

Enjoy the new video on InterSystems Developers YouTube:

⏯ HealthShares Nav App as a Service Orchestrator with Single SignOn for 3rd Party Apps @ Global Summit 2024

#InterSystems Demo Games entry

⏯️ AI Clinical Trial Platform

The Trial AI platform leverages InterSystems cloud services including the FHIR Transformation Service and IRIS Cloud SQL to assist with clinical trial recruitment, an expensive and prevalent problem. It does this by ingesting structured and unstructured healthcare data, then uses AI to help identify eligible patients.

Presenters:
🗣 @Vic Sun, Sales Engineer, InterSystems
🗣 @Mohamed Oukani, Senior Sales Engineer, InterSystems
🗣 @Bhavya Kandimalla, Sales Engineer, InterSystems

I am brand new to using AI. I downloaded some medical visit progress notes from my Patient Portal. I extracted text from PDF files. I found a YouTube video that showed how to extract metadata using an OpenAI query / prompt such as this one:

ollama-ai-iris/data/prompts/medical_progress_notes_prompt.txt at main · oliverwilms/ollama-ai-iris
 

I combined @Rodolfo Pscheidt Jr https://github.com/RodolfoPscheidtJr/ollama-ai-iris with some files from @Guillaume Rongier https://openexchange.intersystems.com/package/iris-rag-demo.

I attempted to run

python3 query_data.

Hey Community!

We're happy to share the next video in the "Code to Care" series on our InterSystems Developers YouTube:

⏯  Can AI fix bugs? The setup

Audience

Those curious in exploring new GenerativeAI usecases.

Shares thoughts and rationale when training generative AI for pattern matching.

Challenge 1 - Simple but no simpler

A developer aspires to conceive an elegant solution to requirements.
Pattern matches ( like regular expressions ) can be solved for in many ways. Which one is the better code solution?
Can an AI postulate an elegant pattern match solution for a range of simple-to-complex data samples?

#InterSystems Demo Games entry

⏯️ Healthcare AI Agent Platform

An AI Agent Platform specifically built for the healthcare industry that requires no technical background to utilize. By simply defining a goal or initiative, a swarm of AI agents will conduct operations to achieve the stated end goal and measure their own efficacy along the way to continuously improve. Healthcare organizations today are facing a myriad of challenges that impact financial and clinical performance. These problems are well known, and there is a general consensus on how many of them can be alleviated with AI. However, healthcare organizations face unique challenges in implementing AI:

• HIPAA/Regulatory compliance - Data quality & accessibility - Embedding AI into current clinical workflows, i.e. integrating AI in such a way that it does not require clinicians to re-orient their processes. It should complement existing workflows, not disrupt them.
• Implementation cost/high technical barrier of entry – staff needed to build and maintain AI processes can become expensive
• Ambiguous ROI calculation – careful considerations must be made to properly measure and understand the efficacy of AI integrations. InterSystems is uniquely positioned to address these challenges, enabling healthcare organizations to implement AI with minimal burden.

Presenters:
🗣 @Daniel Cole, Sales Engineer, InterSystems
🗣 @Jeff Morgan, Sales Engineer, InterSystems
🗣 @Raef Youssef, Sales Engineer, InterSystems
🗣 @Jose Ruperez, Senior Sales Engineer, InterSystems
🗣 @Harry Tong, Principal Solutions Architect, InterSystems
🗣 @Nicholai Mitchko, Sales Engineering Manager, InterSystems

Hey Community,

Watch this video to learn about AI Co-Pilot, which simplifies DTL coding and offers personalized assistance which makes it accessible to users with varying levels of technical expertise:

⏯ Accelerate DTL Coding with AI Cloud Service @ Global Summit 2024

#InterSystems Demo Games entry

⏯️ Care Compass – InterSystems IRIS powered RAG AI assistant for Care Managers

Care Compass is a prototype AI assistant that helps caseworkers prioritize clients by analyzing clinical and social data. Using Retrieval Augmented Generation (RAG) and large language models, it generates narrative risk summaries, calculates dynamic risk scores, and recommends next steps. The goal is to reduce preventable ER visits and support early, informed interventions.

Presenters:
🗣 @Brad Nissenbaum, Sales Engineer, InterSystems
🗣 @Andrew Wardly, Sales Engineer, InterSystems
🗣 @Fan Ji, Solution Developer, InterSystems
🗣 @Lynn Wu, Sales Engineer, InterSystems

☤ Care 🩺 Compass 🧭 - Proof-of-Concept - Demo Games Contest Entry

Introducing Care Compass: AI-Powered Case Prioritization for Human Services

In today’s healthcare and social services landscape, caseworkers face overwhelming challenges. High caseloads, fragmented systems, and disconnected data often lead to missed opportunities to intervene early and effectively. This results in worker burnout and preventable emergency room visits, which are both costly and avoidable.

Care Compass was created to change that.

#InterSystems Demo Games entry

⏯️ FHIR-Powered AI Healthcare Assistant

Leverage InterSystems's FHIR SQL Builder to project FHIR data to a dataset for vector embedding, and feed the vector store to a RAG chain with LLM and Chatbot.

🗣 Presenter: @Simon Sha, Sales Architect, InterSystems

Thank you community for translating an earlier article into Portuguese.
Am returning the favor with a new release of Pattern Match Workbench demo app.

Added support for Portuguese.

The labels, buttons, feedback messages and help-text for user interface are updated.

Pattern Descriptions can be requested for the new language.

The single AI Model for transforming user prompt into Pattern match code was fully retrained.

Values to Pattern Code Model also retrained

The separate AI model for generating Pattern match code from a sample list of values has been retrained.

INTRO

Barricade is a tool developed by ICCA Ops to streamline and scale support for FHIR-to-OMOP transformations for InterSystems OMOP. Our clients will be using InterSystems OMOP to transform FHIR data to this OMOP structure. As a managed service, our job is to troubleshoot any issues that come with the transformation process. Barricade is the ideal tool to aid us in this process for a variety of reasons. First, effective support demands knowledge across FHIR standards, the OHDSI OMOP model, and InterSystems-specific operational workflows—all highly specialized areas.

Hey Community!

We're happy to share the next video in the "Code to Care" series on our InterSystems Developers YouTube:

⏯  Chaining LLMs for Better Results using Agentic AI

Hey Community!

We're happy to share the next video in the "Code to Care" series on our InterSystems Developers YouTube:

⏯  Role of Data and Interoperability in Effective AI in Healthcare

Audience

Those curious in exploring new GenerativeAI usecases.

Developers and analysts looking for a quick way to tame the Pattern Match operator.

In both ObjectScript and SQL this has a quite visually dense format.

 if2"CARD"

Challenge

Use generative AI to assist create and modify pattern match code from different natural language input.

Hi Community!

We’re excited to announce that several winners of the InterSystems AI Programming Contest have been invited to showcase their projects at the Tech Exchange during InterSystems Ready 2025!

Join us on Wednesday, June 25, to explore innovative, real-world solutions built with InterSystems IRIS, AI, LLMs, and intelligent agent technologies — directly from the developers who created them:

Introducing Smart Clinical Sidechick — the intelligent, no-drama partner your EHR wishes it could be. She reads FHIR data in real time, interprets lab results without ghosting, and explains clinical alerts like she actually cares. Built with GPT-4 brains and YAML sass, she’s not here to replace your main EHR—just to make it look bad. Tired of irrelevant alerts and cryptic warnings? Sidechick serves up real, explainable insights, not vague “elevated risk” vibes. And when your backend crashes, she doesn’t panic—she self-heals.

Artificial Intelligence (AI) is getting a lot of attention lately because it can change many areas of our lives. Better computer power and more data have helped AI do amazing things, like improving medical tests and making self-driving cars. AI can also help businesses make better decisions and work more efficiently, which is why it's becoming more popular and widely used. How can one integrate the OpenAI API calls into an existing IRIS Interoperability application?

Hi developers!

This will be a very short article as in April 2025 with Lovable and other Prompt-to-UI tools it becomes possible to build the frontend with prompting. Even to the folks like me who is not familiar with modern UI techics at all.

Well, I know at least the words javascript, typescript and ReactJS, so in this very short article we will be building the ReactJS UI to InterSystems FHIR server with Lovable.ai.

Let's go!

I combined @Rodolfo Pscheidt https://github.com/RodolfoPscheidtJr/ollama-ai-iris with some files from @Guillaume Rongier https://openexchange.intersystems.com/package/iris-rag-demo.

My own project is https://github.com/oliverwilms/ollama-ai-iris

I can run load_data.py and it connects to IRIS (same container).

When I try to run query_data.py https://github.com/oliverwilms/ollama-ai-iris/blob/main/query_data.py , it cannot connect to ollama:

ConnectionError: Failed to connect to Ollama. Please check that Ollama is downloaded, running and accessible.

I wonder if I need to add in query_data.

Hi Community,

We’re excited to introduce the AskMe assistant—try it out for yourself!

I read the article by @Rodolfo Pscheidt:

https://community.intersystems.com/post/ollama-ai-iris

I forked his app and copied selected files from @Guillaume Rongier iris-rag-demo to make it containerized:

oliverwilms/ollama-ai-iris
 

I ran load_data.py and I got this output:

irisowner@e10968e4da42:/irisdev/app$ python3 load_data.py
Document ID: cbfa2f20-6627-407b-bbad-31722d18ca13
modules.json: 100%|█████████████████████████████████████████████████████████████| 349/349 [00:00<00:00, 778kB/s]
config_sentence_transformers.

Hi, colleagues!

As you can see the new topic of the programming contest - AI Agents. 

The topic was over-hyped recently on the Internet and has different meanings. You might get curious about what we mean by AI agents in regard to the InterSystems programming contest.

Hi Developers!

We are happy to present the bonuses page for the applications submitted to the InterSystems AI Programming Contest!

See the results below.

Hi Community,
Traditional keyword-based search struggles with nuanced, domain-specific queries. Vector search, however, leverages semantic understanding, enabling AI agents to retrieve and generate responses based on context—not just keywords.
This article provides a step-by-step guide to creating an Agentic AI RAG (Retrieval-Augmented Generation) application.

Implementation Steps:

1. Create Agent Tools
   • Add Ingest functionality: Automatically ingests and index documents (e.g., InterSystems IRIS 2025.1 Release Notes).
   • Implement Vector Search Functionality
2. Create Vector Search Agent
3. Handoff to Triage (Main Agent)
4. Run The Agent