Refund workflow
Twelve nodes, three human gates. Small refunds go through automatically; mid-size route to a supervisor as tasks; large ones pause for finance. The graph IS the policy.
The protagonist artifact of the cognitive layer. Workflows are what you build; agents run them; apps gate them; knowledge informs them; nodes from the marketplace compose them; Command Center operates them.
A workflow is where your operation actually lives — not in a runbook nobody reads, not in someone’s head, but as a graph that runs every time it is triggered. It is the central artifact of the cognitive layer: every other capability either feeds into a workflow, runs inside one, or makes one easier to operate.
Every workflow is versioned. You can compare v3 to v7. You can roll back. You can fork. You can pause one mid-run and inspect what it has in flight, then resume it tomorrow with the same state. And because the graph is explicit, the auditor doesn’t need a diagram from your engineer — the workflow itself is the diagram.
Every workflow is composed of nodes from the Node Marketplace — pick from 130+ ready-made, or add your own. Each node carries its own lifecycle and audit trail, so the workflow inherits durability and observability by default.
Twelve nodes, three human gates. Small refunds go through automatically; mid-size route to a supervisor as tasks; large ones pause for finance. The graph IS the policy.
The workflow listens to alerts, enriches them with knowledge, classifies severity, then auto-resolves, opens a ticket, or pages someone — depending on the rule.
Kicks off when a contract is signed, pauses for KYC, resumes when documents come in, hands off to provisioning, ends with a welcome email. One graph, many days.