Templates / AI agent patterns / ai-parallelization
AI Parallel Guardrails
Runs three independent model checks on a drafted customer reply at the same time — personal data, policy and tone — and joins them before a FEEL script combines the votes. A reply every check passes is sent; one that any check flags waits for a human reviewer. Sectioning the checks keeps each prompt small and the latency that of the slowest call.
Scenarios · 2
- All three checks pass and the reply is sent fan-out → fan-in → combine-votes → send-reply → reply-sent
- A flagged reply waits for a human combine-votes → human-review → send-reply → reply-sent
Job types · 2
-
email-sendSend reply -
io.camunda.agenticai:aiagent:1Check for personal data, Check refund policy, Rate tone
Files · 2
- ai-parallelization.bpmn Process model
- ai-parallelization.bpmn.tests.json Test scenarios (runScenario format)
Every scenario passes on @bpmnkit/engine's runScenario in the
package's tests. casen template use ai-parallelization [dir] writes the files above
into your project — see the templates guide for running
the scenarios and deploying.