BPMN/DMN Deterministic Shell Around Agent
BPMN processes and DMN decision tables form the deterministic spine; LLM-driven agents are invoked only at explicit 'unstructured problem' nodes inside the process.
Problem
Pure-agent replacement of workflow steps loses BPMN observability (which step is running, how long did it take), DMN auditability (which decision rule fired), and existing operator tooling. Hybrid solutions where the agent runs *outside* the workflow lose the integration. Differs from existing hybrid-symbolic-neural-routing by being specifically workflow-engine-grounded — BPMN/DMN as the surrounding shell.
Solution
Model the end-to-end process as BPMN. Decision points use DMN rules where possible. At nodes that need LLM-driven flexibility (free-form input handling, summarization, classification with judgement), invoke an agent as a BPMN service task; the agent runs, returns structured output to the workflow engine, BPMN flow continues. Pair with deterministic-control-flow-not-prompt, hybrid-symbolic-neural-routing, plan-and-execute.
When to use
- Enterprise with mature BPMN/DMN governance.
- Process has both deterministic and unstructured steps.
- Workflow engine supports agent invocation as service task.
Open the full interactive page →
Diagram, neighbourhood map, code examples, related patterns and full provenance.