Agent
Reason, explore, inspect, code, delegate, and decide while the path is uncertain.
Flows
Turn repeatable agent work into durable visual flows.
Let agents explore and design. Move dependable execution into an explicit engine with queues, retries, checkpoints, backpressure, and recovery.
The division of labor
Reason with agents. Run with flows.
Flow Editor
Turn the discovered procedure into tasks, connections, queues, conditions, schedules, and subflows.
Runtime Viewer
Observe execution, queue pressure, task state, checkpoints, and recovery as the Flow runs.
Deterministic core
Make reliability visible.
Schedule and routeCRON triggers, explicit DAGs, conditions, and subflows define when and where work moves.
Persist and recoverFlowFiles and checkpoints keep durable progress across interruptions.
Control pressureQueues and backpressure stop fast producers from overwhelming slower consumers.
Retry deliberatelyModel error handling and delivery instead of hiding it inside a prompt loop.
AI inside a Flow
Use models as tasks, not as the scheduler.
A Flow can call an agent or LLM exactly where judgment is useful while deterministic tasks own collection, transformation, persistence, retries, and delivery.
Agent-generated flowsAsk an agent to draft or maintain the workflow, then inspect the resulting structure.
Human-visible executionStart and stop tasks, inspect queues, and understand the current state without reading an opaque transcript.
Repeatable operationsRun digests, routing, media pipelines, monitoring, and multi-step delivery on schedules.
Apache NiFi meets Claude Code
Build with reasoning. Operate with structure.
Start with an agent task, then promote the dependable path into a Flow.