Build Agentic Applications Faster with InterSystems IRIS
InterSystems IRIS AI Hub provides a comprehensive set of capabilities for building, deploying, and governing AI agents and agentic workflows. Embedded within InterSystems IRIS® and InterSystems IRIS for Health®, it provides a unified environment for developing agentic AI applications that are tightly integrated with your enterprise data, business logic, and operational workflows. Teams can build native AI agents, publish business logic as governed tools using the Model Context Protocol (MCP), and apply consistent security, governance, and human oversight throughout the AI lifecycle, whether your data already sits in InterSystems IRIS or across your solution ecosystem.
Closing the Gap Between an AI Pilot and Its Production Implementation
Calling a language model is easy. Putting one into production is not. The moment an agent needs live enterprise data, permission to act, and an accountable record of what it did, most teams discover their AI stack sits outside every control their business runs on. Credentials are spread across cloud runtimes. Data is copied to wherever the AI lives. Each new agent becomes a fresh security review and risk.
AI Hub closes that gap by making the data platform itself the place where AI is built and governed, instead of bolting on another stack alongside it.
Core Capabilities of InterSystems IRIS AI Hub
Build Agents Faster and More Safely on InterSystems IRIS
AI Hub offers familiar patterns to build agents and agentic workflows quickly on InterSystems IRIS. With convenient abstractions for language models, prompts, tools, and skills, you can create native agents quickly, with direct, governed access to existing data assets and business logic.
The resulting agents fit perfectly in your existing software development lifecycle and can ship and run with your mission-critical applications without requiring additional installations, separate configurations, or DevOps workflows.
Connect Agents to Data and Business Tools, Wherever They Are
Through native support for Model Context Protocol, AI Hub enables you to expose any existing data, functionality, or business processes already on InterSystems IRIS to virtually any modern AI framework, purely declaratively, without writing a single line of code.
The MCP support is bidirectional, so any native agents developed using AI Hub can access MCP servers exposing third-party product functionality in your enterprise software portfolio, such as Workday, Jira, Salesforce, and many others.
Governance from Build Time to Chat Time
AI Hub was built from the ground up to be deeply integrated within the InterSystems IRIS platform. Having no outside dependencies means a more secure software supply chain, and the ability to express security policies for agents just like for your existing business users.
Furthermore, your agentic workflows can easily include human workflow sections as well, thanks to InterSystems IRIS Interoperability. This means it is easy to include advanced approval policies, well beyond the standard “elicitations” you get from common AI apps.
What sets AI Hub apart is the deep integration with InterSystems IRIS features and ease of development, meaning customers can easily augment existing applications with powerful agents at exceptionally low implementation cost and retaining consistent governance. For new projects and customers, AI Hub is differentiated through its integration with the rich InterSystems IRIS interoperability feature set and by its native support for MCP, providing boundless opportunities to build agentic workflows that interact with your existing data, systems, and services ecosystem.
InterSystems IRIS AI Hub was built to ensure our customers can build AI apps, agents, and agentic workflows quickly and safely, by offering them the enterprise context they need to be effective, the security context they need to be safe, and the workflow context they need to integrate with human-in-the-loop business processes.