#Artificial Intelligence (AI)

Hi Community,

Enjoy the new video on InterSystems Developers YouTube:

⏯ Your AI Survival Guide & Lessons Learned @ Ready 2025

What is Unstructured Data?
Unstructured data refers to information lacking a predefined data model or organization. In contrast to structured data found in databases with clear structures (e.g., tables and fields), unstructured data lacks a fixed schema. This type of data includes text, images, videos, audio files, social media posts, emails, and more.

Why Are Insights from Unstructured Data Important?
According to an IDC (International Data Corporation) report, 80% of worldwide data is projected to be unstructured by 2025, posing a significant concern for 95% of businesses.

In the previous article, we saw in detail about Connectors, that let user upload their file and get it converted into embeddings and store it to IRIS DB. In this article, we'll explore different retrieval options that IRIS AI Studio offers - Semantic Search, Chat, Recommender and Similarity. 

New Updates  ⛴️ 

• Added installation through Docker. Run `./build.sh` after cloning to get the application & IRIS instance running in your local
• Connect via InterSystems Extension in vsCode - Thanks to @Evgeny.

Keywords:  Vibe coding, Windsurf, IRIS, TIE

Why not?   "Vibe coding" is never about the vibe!

Has anyone not been trying "vibe coding" so far?

Even merely 3 years ago, if anyone asked

• "Could I do IRIS implementation for NHS TIE in English or Spanish or just Chinese ?", or
• "Can I just instruct TIE in English to build itself an e2e route, to pick up a PDF report then turn into ORU/MDM message and submit into the PAS ?", or
• "Could we query IRIS database in English only, and build up dashboard or ad hoc report of my own by English instructions?

Keywords:  IRIS, Agents, Agentic AI, Smart Apps

Motive?

Transformer based LLMs appear to be a pretty good "universal logical–symbolic abstractor".  They started to bridge up the previous abyss among human languages and machine languages, which in essence are all logic symbols that could be mapped into the same vector space. 

Objective?

Wondering for 3 years we might be able to just use English (etc human natural languages) to do IRIS implementations as well, one day.

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.

Hi developers!

I'm testing vibecoding with ObjectScript and my silicon friend created a code-block that got me thinking "what's wrong"?

Here is the piece of code:

for i=0:1:(json.%Size()-1) {

set p = json.%Get(i)

if (p="value1")!(p="value2") {

quit 1
}

AI wanted to quit from a method with a return value. Good intention, but bad use of the command.

And ObjectScript compiler compiles this code with no error(?) (syntax linter in VSCode says it's a syntax, kudos @Brett Saviano ).

But in action, it produces <COMMAND>, of course.

Welcome to the finale of our journey in building MAIS.

• In Part 1, we constructed the agnostic "Brain" using LiteLLM and IRIS.
• In Part 2, we designed the "Persona", mastering Dynamic Prompt Engineering and the ReAct theory.

Now, the stage is set. Our agents are ready, defined, and eager to work. However, they remain frozen in time. They require a mechanism to drive the conversation, execute their requested tools, and pass the baton to one another.

Today, we will assemble the Nervous System

Ever since I started using IRIS, I have wondered if we could create agents on IRIS. It seemed obvious: we have an Interoperability GUI that can trace messages, we have an underlying object database that can store SQL, Vectors and even Base64 images. We currently have a Python SDK that allows us to interface with the platform using Python, but not particularly optimized for developing agentic workflows. This was my attempt to create a Python SDK that can leverage several parts of IRIS to support development of agentic systems.

10:47 AM — Jose Garcia's creatinine test results arrive at the hospital FHIR server. 2.1 mg/dL — a 35% increase from last month.

What happens next?

• Most systems: ❌ The result sits in a queue until a clinician reviews it manually — hours or days later.
• This system: 👍 An AI agent evaluates the trend, consults clinical guidelines, and generates evidence-based recommendations — in seconds, automatically.

No chatbot. No manual prompts. No black-box reasoning.

This is event-driven clinical decision support with full explainability:

✅ Triggered automatically by FHIR events ✅ Multi-agent reasoning (context, guidelines, recommendations) ✅ Complete audit trail in SQL (every decision, every evidence source) ✅ FHIR-native outputs (DiagnosticReport published to server)

Built with:

• InterSystems IRIS for Health — Orchestration, FHIR, persistence, vector search
• CrewAI — Multi-agent framework for structured reasoning

You'll learn: 🖋️ How to orchestrate agentic AI workflows within production-grade interoperability systems — and why explainability matters more than accuracy alone.

In Part 1, we laid the technical foundation of MAIS (Multi-Agent Interoperability Systems). We have successfully wired up the 'Brain', built a robust Adapter using LiteLLM, locked down our API keys with IRIS Credentials, and finally cracked the trick code on the Python interoperability puzzle.

However, right now our system is merely a raw pipe to an LLM. It processes text, but it lacks identity.

Today, in Part 2, we will define the Anatomy of an Agent We will move from simple API calls to structured Personas.

Some concepts make perfect sense on paper, whereas others require you to get your hands dirty. Take driving, for example. You can memorize every component of the engine mechanics, but that does not mean you can actually drive.

You cannot truly grasp it until you are in the driver's seat, physically feeling the friction point of the clutch and the vibration of the road beneath. While some computing concepts are intuitive, Intelligent Agents are different. To understand them, you have to get in the driver's seat.

Hey Community!

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

⏯  How Big Research Bets Are Made Without a Crystal Ball

I'm a huge sci-fi fan, but while I'm fully onboard the Star Wars train (apologies to my fellow Trekkies!), but I've always appreciated the classic episodes of Star Trek from my childhood. The diverse crew of the USS Enterprise, each masterminding their unique roles, is a perfect metaphor for understanding AI agents and their power in projects like Facilis. So, let's embark on an intergalactic mission, leveraging AI as our ship's crew and  boldly go where no man has gone before

Hi everyone.

I'm going to give you a quick tip on how to implement an AI agent to search the Intersystems documentation integrated into Teams.

Yes, I know the documentation page has its own AI search engine and it's quite effective, but this way we'd have faster access, especially if Teams is your company's corporate tool.

You can also create another AI agent to search articles published in the developer community (which also has its own integrated AI search engine).

Hi,

We're working on new capabilities to help you build Agents and AI applications faster with InterSystems IRIS. In order to better understand which entry points and development methodologies would help you most, we've created this brief survey: Building AI solutions with InterSystems IRIS. 

Filling it in should not take much more than 5 minutes, and your feedback on this exciting topic will help us fine tune our designs and prioritize the right features.

Thanks in advance!
benjamin
 

Hey Community!

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

⏯  Using GenAI in Real Life: Daily Use Cases That Work

In this article I will be discussing the use of an alternative LLM for generative IA. OpenIA is commonly used, in this article I will show you how to use it and the advantages of using Ollama

In the generative AI usage model that we are used to, we have the following flow:

• we take texts from a data source (a file, for example) and embedding that text into vectors
• we store the vectors in an IRIS database.
• we call an LLM (Large Language Model) that accesses these vectors as context to generate responses in human language.

Hey Developers,

Enjoy the new video on InterSystems Developers YouTube

⏯ Integrating AI Agents into InterSystems IRIS - Patterns and Techniques @ READY 2025

Hey Developers,

Enjoy the new video on InterSystems Developers YouTube

⏯ Generative AI in InterSystems Data Studio @ READY 2025

Hey Community,

Enjoy the new video on InterSystems Developers YouTube:

⏯ Analytics and AI with InterSystems IRIS - From Zero to Hero @ Ready 2025

Yes, yes! Welcome! You haven't made a mistake, you are in your beloved InterSystems Developer Community in Spanish.

You may be wondering what the title of this article is about, well it's very simple, today we are gathered here to honor the Inquisitor and praise the great work he performed. 

So, who or what is the Inquisitor?

Perfect, now that I have your attention, it's time to explain what the Inquisitor is. The Inquisitor is a solution developed with InterSystems technology to subject public contracts published daily on the platform  https://contrataciondelestado.es/ to scrutiny.

Hey Community,

Enjoy the new video on InterSystems Developers YouTube:

⏯ The Road to AI in Healthcare @ Ready 2025

This anthropic article made me think of several InterSystems presentations and articles on the topic of data quality for AI applications. InterSystems is right that data quality is crucial for AI, but I imagined there would be room for small errors, but this study suggests otherwise. That small errors can lead to big hallucinations. What do you think of this? And how can InterSystems technology help?

https://www.anthropic.com/research/small-samples-poison

Introduction

In my previous article, I introduced the FHIR Data Explorer, a proof-of-concept application that connects InterSystems IRIS, Python, and Ollama to enable semantic search and visualization over healthcare data in FHIR format, a project currently participating in the InterSystems External Language Contest.

In this follow-up, we’ll see how I integrated Ollama for generating patient history summaries directly from structured FHIR data stored in IRIS, using lightweight local language models (LLMs) such as Llama 3.2:1B or Gemma 2:2B.

The goal was to build a completely local AI pipeline that can extract, format, and narrate patient histories while keeping data private and under full control.

All patient data used in this demo comes from FHIR bundles, which were parsed and loaded into IRIS via the IRIStool module. This approach makes it straightforward to query, transform, and vectorize healthcare data using familiar pandas operations in Python. If you’re curious about how I built this integration, check out my previous article Building a FHIR Vector Repository with InterSystems IRIS and Python through the IRIStool module.

Both IRIStool and FHIR Data Explorer are available on the InterSystems Open Exchange — and part of my contest submissions. If you find them useful, please consider voting for them!

• IRIStool and Data Manager
• FHIR Data Explorer