Docs hub
Build production-ready approval flows with role routing, SLA escalation, signed callbacks, policy context, and audit evidence.
Put a person in front of a risky step in any agent, company workflow or internal system, record every step, and get signed evidence. One API call and a callback handler, no MCP server required.
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.
A compact map of the public Contro1 runtime API: request creation, Control Map preview, audit records, and thread timelines.
Know which agent did what: identity from the credential, sub-agents that register themselves, one trace per run with every tool call, hooks and OpenTelemetry that report without relying on the model, and HMAC-signed evidence.
Learn how to create, inspect, and cancel Contro1 requests for approvals, clarifications, and escalations.
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.
Validate signed Contro1 callbacks and safely resume AI workflows after approvals, rejections, expirations, or escalations.
Secure your Contro1 integrations with environment-based API keys, role-aware routing, and clear ownership boundaries.
Choose a Contro1 connection path: five agent setup guides for production agents, Claude Code, Codex, Cursor and personal agents, plus web sign-in for Grok, ChatGPT and Claude.ai. Follow exact steps and verify access.
Connect your own agent (LangGraph, Mastra, OpenAI Agents, CrewAI or plain HTTP) running on Railway, Render, Fly.io, Vercel, AWS or Google Cloud: give it its own identity and an Agent key per place it runs, store the key in the platform's environment variables, give it Actions in Access, and call them.
Connect Claude Code as its own agent with contro1 connect claude-code, which also adds the Contro1 MCP server, and add approvals for risky commands. Exact commands and what you should see.
Connect Codex as its own agent with contro1 connect codex, which adds the Contro1 MCP server for company apps, and stop chosen shell commands for a person with a Codex hook. Exact commands and what you should see.
Connect Cursor as its own agent with contro1 connect cursor, which adds the Contro1 MCP server to ~/.cursor/mcp.json for company apps. Exact commands and what you should see.
Connect OpenClaw and NanoClaw assistants to Contro1: one command per computer, owner approval, approvals for commands, and company apps over MCP.
Connect an agent built on the Claude Agent SDK to the Contro1 MCP with its own Agent key: the Actions it was granted, your skills, approvals when policy requires them, and a trace of every run.
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.
Give Block Buzz agents human approvals, role-based routing, safe retries, and a complete audit trail before high-impact actions run.
Govern AWS Lambda MicroVM launches, endpoint tokens, shell access, and lifecycle controls with Contro1 approvals, audit evidence, and bypass detection.
Run OpenClaw safely at work: an owner-approved identity per assistant, signed human approval before risky actions, no API key on the machine, one audit trail.
Take NanoClaw from one admin DM to a team: credential use, package installs, MCP servers and new agents go to the right reviewer, with an owner and audit trail.
Choose the applications your organization approves, decide who may do what, and connect one MCP. Every person and agent gets exactly their access, and every action is recorded on their name.
Push skills to every agent over MCP, see and scan every skill employees install, and allow only skills from Contro1. With versions, rollback and approvals.
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.
Install and use @contro1/sdk in Node, TypeScript, Express, Fastify, or Next.js backends to create approval requests, verify webhooks, and write audit records.
Use Microsoft Agent Governance Toolkit for policy decisions and Contro1 for human approval routing, signed callbacks, and audit evidence.
Connect Microsoft Teams to Contro1 and receive AI agent approval requests directly inside Teams.
Pause LangGraph execution at deterministic checkpoints, route review through CENTCOM, and resume with signed decisions.
Map OpenAI Agents SDK interruptions to Contro1 requests so humans can approve high-risk actions before execution continues.
Bridge CrewAI review events into Contro1 for routing, approvals, and auditability.
Use HTTP Request and Wait nodes in n8n to pause workflows, route approvals through Contro1, and branch on the result.
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.
Route selected Claude Code actions to a manager or other eligible reviewer before they run, with production deployment as a practical quickstart example.
Route Claude Managed Agents session actions into Contro1 with session correlation, idempotent approval requests, signed callbacks, and audit-ready logs.
Add Contro1 approval gates to Mastra agents and workflows so risky tool calls, workflow steps, and production actions wait for signed human decisions.
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.
Connect Pydantic AI deferred tools and approval-required tool calls to Contro1 decisions, signed callbacks, and audit evidence.
Contro1 helps AI agents request human approval, follow organizational policies, track ownership, maintain agent inventory, and create audit-ready evidence before sensitive actions.
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.
A clear agentic AI definition for enterprise teams, with examples, risk patterns, and the governance controls needed when AI systems can take action.
How enterprise teams can adopt agentic AI safely: use cases by department, governance requirements, approval workflows, observability, and runtime control.
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.
A practical guide to AI agent operations: ownership, policies, approval points, escalation paths, logging, metrics, and operating reviews.
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.
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.
