SymphonyAI launched IRIS Foundry 2.0, an industrial AI platform that uses a connected cortex, AI agents, and copilots to enable predictive maintenance, supply chain traceability, and intelligent decision-making across manufacturing operations without requiring companies to replace existing systems.
- Connected Cortex Technology: Built from a company's Unified Data Model, connecting assets, time-series data, orders, documents, and labor records in one integrated view.
- AI Agents and Copilots: Answer questions in plain language, show evidence through knowledge graphs, and perform complex analysis using secure code execution.
- Data-Level Security: Plant-level permissions control what each user sees, with enforcement through the Foundry API layer.
- Practical Applications: Teams use the platform for order tracking, supplier traceability, workforce scheduling, defect analysis, and predictive maintenance.
- No Replacement Required: Connects to existing historians and ERP systems without requiring platform migration or data re-platforming.
SymphonyAI launched IRIS Foundry 2.0, an industrial AI platform that features a connected cortex at its center, agents and copilots that answer questions and show evidence, new predictive models, data-level access control, and a faster path from idea to working app.
Each piece solves a specific problem from operations and data teams.
“The industry has spent years proving that AI can work in a plant. The harder job now is making it understand the plant, and then making that understanding the standard across every site you operate. A context layer is how that happens. It does not ask you to replace your historian or re-platform your ERP. It connects what you already have and keeps the relationships current as your operation changes,” according to SymphonyAI.
Key takeaways:
· Cortex is built directly from a company‘s Unified Data Model (UDM). Assets, time-series channels, orders, documents, labor records, shifts and the relationships between them sit in one connected view. As tabular data is ingested for a UDM type, the matching graph nodes are created, and edges follow the relationships you defined.
· Every object connects back to the data pipeline that produced it, so you can see where information comes from and decide how far to trust it.
· The Cortex Agent lets people ask questions in plain language. Behind the scenes, the language model plans the work and uses a knowledge graph agent to follow the connections, find related assets and information, and assemble an answer. Copilot then shows the nodes and relationships behind the response, and the graph keeps the same query context when you open it, so follow-up questions stay consistent.
· When an answer needs real analysis, the agent retrieves the relevant data from the graph, writes and runs code in a secure sandbox, and brings the result back into the conversation.
· Teams are using this pattern for order and delivery questions, supplier and material traceability, workforce and scheduling, defect root cause and predictive maintenance.
· IRIS Foundry 2.0 adds data-level permissions that can be set at the plant level for datasets, including time series and tabular data, and assigned to users. The Foundry API layer enforces them, so every role sees what it is entitled to and nothing more.
· IRIS Forge offers AI-assisted application creation, versioning, deployment and access control, with an enhanced UI and a VS Code extension for teams that prefer to build in code. Personalized workflows let you describe what you want in plain language, for example “check this channel every hour, and if it crosses the threshold, plot the trend and email me,” and Copilot creates and schedules the workflow. No API knowledge required.
