SAP Adds Governed Joule Agents and Tabular AI Models at TechEd

The centerpiece is Joule Work, where new capabilities are designed to help AI agents work more efficiently and interoperate with open protocols. SAP said the Model Context Protocol and Agent 2 Agent allow Joule, its agentic AI assistant, to gather context, make decisions and execute multistep business workflows across the enterprise while bringing in third-party data or services.

SAP is also placing governance at the center of that openness. “Open protocols need governed doors,” Ted Way, vice president and chief product officer of SAP business AI product engineering, told SiliconANGLE in an interview. Way said SAP wants customers’ own agents to collaborate with its business agents across company systems, but opening those interconnections requires a controlled entry point where organizations can enforce and oversee activity. A new orchestration layer will enable assistants and agents to invoke Joule Agents through a governed gateway.

SAP said a recent update will allow agents to trigger n8n workflows through Joule Studio. N8n is a node-based workflow automation platform that connects different apps and uses deterministic automation. AI agents can trigger it, but unlike generative AI, n8n uses event-based and trigger-based logic for decision-making. It cannot hallucinate and follows exact rules from start to finish, making it suitable for highly regulated or sensitive work that depends on precise steps. “It needs to do these five steps in this order exactly like this every single time,” Way said. SAP’s approach combines flexible natural-language agentic triggers with prescribed workflows, so an agent may help determine when action is needed while compliance-sensitive procedures still require an exact sequence.

On the data side, SAP announced the expansion of SAP Business Data Cloud Ontology Manager in SAP Data Cloud, or BDC, to provide an AI-native authoring experience by giving agents an understanding of how applications relate to one another. The product defines relationships between company facts, allowing agents to reason more accurately and make decisions across enterprises. SAP’s acquisition of Reltio, recently announced at SAP Connect, brings multidomain data management to BDC, helping unify customer, supplier and product records across SAP and third-party systems into trusted data products for applications and agents. SAP said the new product is designed to complement its existing Knowledge Graph, which provides business context from SAP data.

SAP is also expanding its lakehouse capabilities with Dremio, another acquisition, by adding native support for Apache Iceberg and Apache Polaris and a high-performance federated query engine that enables unified data access without moving or copying data.

For structured data, SAP announced SAP-RPT-2.0, a tabular AI model that expands beyond classification and regression to support anomaly and outlier detection and provides AI-powered analysis through embeddings. Way said not every enterprise problem is a language problem, noting that much business data is stored in tables. SAP said the model will add multitable capabilities to reduce manual engineering and deliver faster, deeper insights from structured data.

SAP also launched SAP-RPT-TS, a model that helps customers predict values across time-indexed metrics for key forecasting. Because it uses SAP Business Planning without custom business machine learning, less technical users can deploy the model on their systems, SAP said.

In a partnership with Hewlett Packard Enterprise Co., SAP said it is deploying SAP-RPT on the International Space Station. The aim is to help predict issues before failures escalate, reconstruct missing sensor values from historical data and generate explainable mission health reports for astronauts and ground teams without sending data back to Earth before analysis.