Add approvals and control to AI agents

Quickstart: add approvals to an AI agent in minutes

Create your first Contro1 request, route it to the right operator, and return a signed callback to your agent.

A Complete Guide to the API

A practical walkthrough of the Contro1 runtime API: which endpoint an agent calls, when to call it, what to send, and how approvals, audit records, traces, and evidence fit together.

API endpoint index

A compact map of the public Contro1 runtime API: request creation, Control Map preview, audit records, and thread timelines.

Agent identity, traceability & signed evidence

Give every agent a verified identity, scope its authority (least agency), reconstruct any run end-to-end (tools, sub-agents, retrieved context), and export HMAC-signed evidence.

Requests API reference for AI agent approvals

Learn how to create, inspect, and cancel Contro1 requests for approvals, clarifications, and escalations.

Audit records and cases for autonomous agent actions

Use Contro1 audit records to log actions that agents are authorized to run autonomously, and correlation_id to connect requests and logs into one case timeline.

Webhook callbacks for signed operator decisions

Validate signed Contro1 callbacks and safely resume AI workflows after approvals, rejections, expirations, or escalations.

Authentication and API key handling for Contro1

Secure your Contro1 integrations with environment-based API keys, role-aware routing, and clear ownership boundaries.

Contro1 CLI

Install and use the contro1 CLI to register AI agents, create approval requests, push AI inventory, retrieve evidence and traces, and test workflows before using the SDK or API.

Connect Block Buzz to Contro1

Give Block Buzz agents human approvals, role-based routing, safe retries, and a complete audit trail before high-impact actions run.

Lambda MicroVMs connector

Govern AWS Lambda MicroVM launches, endpoint tokens, shell access, and lifecycle controls with Contro1 approvals, audit evidence, and bypass detection.

OpenClaw human approval and audit connector

Give your OpenClaw personal AI assistant a real, unbypassable guardrail: signed human approval for sensitive actions, a durable audit of everything it does autonomously, and one review queue across many assistants.

Contro1 Python SDK

Install and use the framework-agnostic Contro1 Python SDK to request human approvals or input, verify signed webhooks, log autonomous actions, and fetch audit evidence.

Contro1 JavaScript and TypeScript SDK

Install and use @contro1/sdk in Node, TypeScript, Express, Fastify, or Next.js backends to create approval requests, verify webhooks, and write audit records.

Microsoft Agent Governance Toolkit integration

Use Microsoft Agent Governance Toolkit for policy decisions and Contro1 for human approval routing, signed callbacks, and audit evidence.

Microsoft Teams Connector for Contro1: Approval Requests in Teams

Connect Microsoft Teams to Contro1 and receive AI agent approval requests directly inside Teams.

How to add human approvals to LangGraph

Pause LangGraph execution at deterministic checkpoints, route review through CENTCOM, and resume with signed decisions.

How to add human approvals to OpenAI Agents SDK

Map OpenAI Agents SDK interruptions to Contro1 requests so humans can approve high-risk actions before execution continues.

How to add human approvals to CrewAI

Bridge CrewAI review events into Contro1 for routing, approvals, and auditability.

How to add human approvals to n8n

Use HTTP Request and Wait nodes in n8n to pause workflows, route approvals through Contro1, and branch on the result.

Add human approval to Codex with Contro1

Route selected Codex shell actions to an accountable reviewer before they run, and use the same Contro1 workflow when Codex needs input from a person.

Add human approval to Claude Code with Contro1

Route selected Claude Code actions to a manager or other eligible reviewer before they run, with production deployment as a practical quickstart example.

How to add human approvals to Claude Managed Agents

Route Claude Managed Agents session actions into Contro1 with session correlation, idempotent approval requests, signed callbacks, and audit-ready logs.

How to add human approvals to Mastra agents and workflows

Add Contro1 approval gates to Mastra agents and workflows so risky tool calls, workflow steps, and production actions wait for signed human decisions.

How to add human approvals to Strands Agents

Add Contro1 approval gates, Control Map routing previews, signed callbacks, and full autonomous tool-call logging to Strands Agents running on Bedrock, AgentCore, or custom infrastructure.

How to add human approvals to Pydantic AI

Connect Pydantic AI deferred tools and approval-required tool calls to Contro1 decisions, signed callbacks, and audit evidence.

Human Approval, Agent Ownership, and Audit Trails for AI Agents

Contro1 helps AI agents request human approval, follow organizational policies, track ownership, maintain agent inventory, and create audit-ready evidence before sensitive actions.

Free AI Inventory for Organizations

Map every AI tool, model, copilot, and agent in your organization. Assign owners, track risks, manage tasks, and keep a live AI inventory with Contro1.

What Is Agentic AI? Enterprise Definition, Examples, and Risks

A clear agentic AI definition for enterprise teams, with examples, risk patterns, and the governance controls needed when AI systems can take action.

Agentic AI in the Enterprise: Use Cases, Risks, and Governance

How enterprise teams can adopt agentic AI safely: use cases by department, governance requirements, approval workflows, observability, and runtime control.

Agent Operations Platform: The Missing Layer for Enterprise AI Agents

What an agent operations platform is, why enterprises need one, and how approvals, routing, escalation, audit, and signed callbacks turn AI agents into accountable operations.

AI Agent Operations: How to Run Agents in Production Without Losing Control

A practical guide to AI agent operations: ownership, policies, approval points, escalation paths, logging, metrics, and operating reviews.

AI Agent Control Tower: How Enterprises Control Autonomous Agents in Production

What an AI agent control tower is, what it must include, and how teams use it to control autonomous agents with an AI control plane: granular approval workflows, agent inventory, traces, escalation, and audit evidence.

Human-in-the-Loop AI Platform: What Enterprises Actually Need

A human-in-the-loop AI platform is more than an approve button. Learn the workflows, routing, escalation, audit, and callback patterns production agents need.