# About

Who builds the Agentic Control Plane, how it's built, and the working method behind the numbers we publish.

# About

Agentic Control Plane (ACP) is the control layer for AI agents: every tool call an agent makes is checked against your policy before it runs (allow / flag / deny / ask), priced at API rates — including subscription traffic — and written to an audit log. It works regardless of framework, model, or client: one command wires up Claude Code, Codex, or Cursor; SDKs cover CrewAI, LangGraph, OpenAI Agents SDK, Pydantic AI, and a dozen other frameworks.

## Who builds it

ACP is built by [David Crowe](https://www.linkedin.com/in/mrdavidcrowe). The open-source core is [GatewayStack](https://github.com/agentic-control-plane) — six composable npm modules, MIT-licensed — and the delegation-chain primitive is published as an open specification ([ADCS](/spec/delegation-chain)). The managed service, [ACP Cloud](https://cloud.agenticcontrolplane.com), is free up to 5 initiating agents.

## How we work

- **Measured, not estimated.** Every number we publish comes from something we ran, metered, or scanned ourselves — the canonical index with method and capture date for each is [The Data](/data).
- **Dogfooded.** ACP governs the agents that build ACP. Features ship to our own workspace before they ship to anyone else, and the audit rows in our screenshots are real.
- **Built in the open.** The modules, the spec, the benchmark ([AgentGovBench](https://github.com/agentic-control-plane/agentgovbench)), and this site are all public repositories.

## Contact

Email [hello@agenticcontrolplane.com](mailto:hello@agenticcontrolplane.com), open an issue on [GitHub](https://github.com/agentic-control-plane), or see the [contact page](/contact) for everything else.