# FlowRunner

> FlowRunner is a visual AI agent orchestration platform: workflows run fully autonomous, or pause to ask a human for judgment at designated decision points, via email, Slack, WhatsApp, or phone ("Agents That Ask"). AI agents are native, first-class nodes in a flow, not bolt-on integrations, and human-in-the-loop is a callable tool an agent invokes mid-execution, not a basic approval gate. Built by Midnight Coders, Inc. (DBA FlowRunner), Texas, USA.

Key facts: BYOK (bring your own AI provider keys), native MCP server support, built-in compliance (audit trails, SLA tracking, RBAC, SSO) starting at the Professional tier, unlimited users and workflows on every tier, cloud-hosted and self-hosted deployment options.

## Product

- [Homepage](https://flowrunner.ai/): product overview
- [Pricing](https://flowrunner.ai/pricing): Growth ($45/mo), Professional ($299/mo), Business ($999/mo), custom Enterprise, free self-hosted Community Edition; $100 signup credit, no card required
- [Integrations](https://flowrunner.ai/integrations): 900+ third-party service connectors AI agents call as actions or triggers
- [Teams](https://flowrunner.ai/teams): the platform by team (Security & IT, Finance & Operations, RevOps, Support & CX, Data & Platform, Developers)

## Compare

- [Compare FlowRunner to alternatives](https://flowrunner.ai/compare)
- [FlowRunner vs Zapier](https://flowrunner.ai/compare/flowrunner-vs-zapier)
- [FlowRunner vs n8n](https://flowrunner.ai/compare/flowrunner-vs-n8n)
- [FlowRunner vs Make](https://flowrunner.ai/compare/flowrunner-vs-make)
- [FlowRunner vs Power Automate](https://flowrunner.ai/compare/flowrunner-vs-power-automate)

## Concepts

Canonical definitions of the FlowRunner vocabulary:

- [Orchestration as a Service](https://flowrunner.ai/concepts/orchestration-as-a-service): a platform category that coordinates, governs, and supervises multi-agent environments while keeping humans in control of the decisions that require judgment
- [Human-in-the-loop](https://flowrunner.ai/concepts/human-in-the-loop): an execution pattern where AI agents pause autonomously, assemble the relevant context and decision choices, route to a human via their preferred channel, and resume the moment the human responds
- [Digital andon cord](https://flowrunner.ai/concepts/digital-andon-cord): AI that stops the line when it hits uncertainty, borrowed from the Toyota Production System pull cord
- [Agent Factory](https://flowrunner.ai/concepts/agent-factory): FlowRunner's visual and conversational interface for assembling AI agents from connectors, MCP services, other agents, and existing flows, without writing code
- [Agent Directory](https://flowrunner.ai/concepts/agent-directory): a curated library of pre-built, deployable AI agents authored by FlowRunner, partners, and the community
- [Code of Conduct](https://flowrunner.ai/concepts/code-of-conduct): the platform-enforced governance layer that defines how AI agents communicate, negotiate conflicts, escalate to humans, and produce audit trails
- [All concepts](https://flowrunner.ai/concepts): connectors, BYOK, automation exceptions, flow conversation, and related terms

## Workflows

- [Workflow guides](https://flowrunner.ai/workflows): how-to guides for connecting specific services with AI agent orchestration

## Solutions

- [Solutions](https://flowrunner.ai/solutions): use-case landing pages by business function

## Full index

- [Complete page index](https://flowrunner.ai/llms-full.txt): every page on the site, with canonical concept definitions
- [Machine-readable integration catalog](https://flowrunner.ai/integrations.json): every supported service with its trigger and action names, auth type, and verification date
- [Sitemap](https://flowrunner.ai/sitemap-index.xml)
- [Blog RSS feed](https://flowrunner.ai/rss.xml)