Camunda Offers New Capabilities to Build and Maintain Enterprise-Grade AI Agents

Camunda, a leader in enterprise agentic automation, is introducing a range of new agentic capabilities across its platform, including features for simplified deployment, improved security, and greater flexibility to ensure organizations can design and orchestrate AI agents in critical business processes. This announcement was made at its annual CamundaCon event in New York City. 

“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,” said Daniel Meyer, CTO, Camunda. “Agentic orchestration changes that equation, giving enterprises control over how much autonomy to grant an agent, bringing control where needed and flexibility where AI shines. By blending deterministic flows with dynamic agents, organizations achieve productivity gains that were once out of reach.”

According to the company, Camunda’s new capabilities form the foundation for orchestrating trusted agents at scale with the help of BPMN (Business Process Model and Notation): 

• AI agent connector – Enables agents to operate autonomously within end-to-end processes and integrate with a variety of LLM providers such as Azure OpenAI or AWS Bedrock. Organizations can choose the right model for each use case while optimizing for speed and cost, whether deploying focused task agents or dynamic, stateful process agents.

• Model Context Protocol (MCP) connector – With support for multi-agent communication protocols, agents and processes can auto-discover and invoke enterprise systems with full context. This unlocks more advanced coordination patterns while maintaining the governance and transparency enterprises require.

To support this level of agentic automation, agents need the ability to learn, recall, and adapt over time. With Camunda, organizations can turn agent interactions from isolated tasks into continuous, context-aware processes delivering true business value with more features such as:

• AI agent composable short-term-memory – Provides agents with conversational context so they can handle follow-up questions and feedback loops without custom code or performance trade-offs.

• AI agent connector long-term memory (retrieval-augmented generation, or RAG) – Adds built-in retrieval-augmented generation to agents, enabling them to recall past conversations, domain knowledge, or customer data for context-rich reasoning and higher decision accuracy.
• Copilot with FEEL capabilities – Generates, validates, and explains FEEL (Friendly Enough Expression Language) expressions from natural language in Camunda Web Modeler. This makes it easy to integrate AI agent outputs into business rules, ensuring auditable and executable logic. 

The latest Camunda release also supports streamlined deployment with a new Orchestration Cluster consolidating Zeebe, Operate, Tasklist, and Identity into a single application.

This approach simplifies configuration, management and monitoring, while enabling scaling in any direction and guaranteeing high availability and disaster recovery, the company said.

In addition, security and governance are strengthened with a new identity service that delivers enterprise-grade authentication and fine-grained authorization across both self-managed and SaaS environments. 

“Enterprise adoption of agentic orchestration requires a holistic platform. With our latest release we are truly marrying dynamic reasoning with deterministic guardrails, enabling organizations to design AI agents for trust and autonomy,” added Meyer. “With this foundation, the vision of the autonomous enterprise, where humans and AI agents work together, is no longer a pipe dream.”

For more information about this news, visit  https://camunda.com.