Camunda is launching a suite of tools designed to help enterprises deploy artificial intelligence (AI) agents in business-critical operations, addressing what the company calls a major roadblock preventing AI projects from moving beyond the pilot stage.
The new features, announced Tuesday, aim to provide the governance and control mechanisms that organizations need to integrate autonomous AI agents into their workflows without compromising security or compliance.
“Most agentic AI projects stall at pilot, not because the models aren’t capable, but because there is not yet an architecture available that provides the guardrails to deploy agents to business-critical processes without risk,” Camunda Chief Technology Officer Daniel Meyer said.
The platform’s cornerstone is what Camunda calls “agentic orchestration,” which allows companies to determine how much autonomy individual AI agents receive while maintaining oversight of complex, multi-step business processes.
Key capabilities include a new AI agent connector that enables autonomous operation across various large language model providers, including Azure OpenAI and AWS Bedrock. The system also supports the Model Context Protocol (MCP), letting different agents and enterprise systems communicate and coordinate with full contextual awareness.
To make AI agents more effective over time, Camunda has built-in memory capabilities. Short-term memory gives agents conversational context for handling follow-up interactions, while long-term memory through retrieval-augmented generation allows agents to access past conversations and domain knowledge for more informed decision-making.
The platform also features a copilot tool that translates natural language into FEEL (Friendly Enough Expression Language) expressions, making it easier to integrate AI outputs into auditable business rules.
Agentic orchestration could raise IT confidence. Just 8% admit they are scaling AI at an enterprise level, according to Accenture. Indeed, only 27% believe in AI agents, compared with 43% a year ago — before an avalanche of agentic AI releases from nearly every major software company, cites Capgemini.
George Kutnerian, CEO of Wellpointe Inc., a healthcare services provider, said his company has already leveraged Camunda’s orchestration capabilities to build a medication order management system.
“It’s that same orchestration strength — now coupled with agentic capabilities within the governance we require — that has us excited to unlock even greater efficiency and innovation as we develop transformative care delivery models,” Kutnerian said.
The release also includes technical improvements for deployment, consolidating multiple components into a single Orchestration Cluster application to simplify configuration and management while ensuring high availability.
Meyer framed the launch as a step toward what he calls the “autonomous enterprise,” where humans and AI agents collaborate seamlessly.
“With this foundation, the vision of the autonomous enterprise, where humans and AI agents work together, is no longer a pipe dream,” Meyer said in an interview. “We are offering both a deterministic and dynamic solution in one offering; it’s not either or.”
