Minctrl Docs

Introduction

What Minctrl is, and the core concepts behind governed AI workflows.

Minctrl is the AI-native workflow builder for regulated operations. You design a process once; AI agents run it end-to-end; and a governance layer keeps a human on exactly the steps that carry real risk.

The problem it solves: automating a regulated process (prior authorization, KYC, claims, sanctions screening) usually forces a bad trade — either a human touches every step (slow, expensive) or agents run unsupervised (fast, uninsurable). Minctrl splits the difference. Agents do the work; a risk model decides, per step, whether the run can proceed on its own or must park for a human verdict.

Core concepts

How the pieces fit

  1. Processes — a new company starts empty. Build a process on the canvas, import a BPMN or minctrl.process/v1 JSON file (the examples on minctrl.com/flows are such files), or describe it in text and review the draft. Each lands as a versioned process (/process-templates).
  2. Connectors — bind each step's tool-id to your real API (/connectors).
  3. Runs — start a run of one of your processes; it executes until it hits a gate, then parks (/process-runs).
  4. Resume — a person signs the gate; /{id}/resume records the verdict and continues.

Every resource is scoped to your company — you only ever see your own data. See Multi-tenancy for how isolation works.

Ready to run one end-to-end? Head to the Quickstart.

On this page