Enterprise content management firm Hyland Software Inc. today launched two new components of its Content Innovation Cloud, which the company says present a unified, continuously updated view of an organization’s content, processes, people and applications to fuel a network of task-specific artificial intelligence agents.

The Enterprise Context Engine pulls from systems such as enterprise resource planning, customer relationship management and human resources and maps relationships that create what the company describes as a “living record of enterprise activity.”

The Enterprise Agent Mesh is a network of task-specific agents tuned for specific industries, including healthcare, banking, insurance, government and higher education. Hyland said the mesh uses the context layer to make decisions and take actions inside complex workflows, while preserving institutional knowledge and incorporating human feedback.

The company has launched six new cloud services this year and plans four more next year. The new context and agent layers are designed to unify these capabilities and apply them to enterprise-scale automation.

Chief Executive Jitesh Ghai, who joined the company last year from data integration giant Informatica Inc., framed the announcement as the next step in applying AI to enterprise operations. “We’re entering this era of AI-fueled, AI-powered intelligence and automation,” he said in an interview.

Shared services layer

Ghai characterized the Enterprise Context Engine as “a shared services platform layer” that sits beneath Hyland products and agentic solutions. It leverages graph analytics technologies to connect artifacts in a way that informs workflows and supports new applications, he said.

Hyland said most of the required information is already present in customer environments or Hyland’s repositories. Existing workflows and decisions are captured through Hyland’s engines and related to the context model for each organization.

The company will provide prebuilt meshes for its core verticals and a no-code platform customers can use to adapt or assemble their own. “The Agent Mesh architecture enables organizations to leverage the Enterprise Context Engine to replace business processes with agent meshes,” Ghai said.

He contrasted that approach to generic agent builders that require significant process reengineering. “Our point of view is very simple: We have the data. We understand the business processes,” he said. That enables Hyland’s approach to “replace the human decision with an agentic decision [with] minimal change.”

Hyland said the platform is designed to work in conjunction with customers’ existing repositories and workflow engines. The architecture uses the Model Context Protocol to connect to systems of record and other vendors’ agents. Customers can audit “each decision made by each agent” to understand why a particular action was taken, Ghai said.

He didn’t disclose specifics of pricing or availability.

Image: Alex/Adobe Stock