👤 Checkpoint

Human-in-the-Loop for AI Agents

Pause any AI agent at a critical step. Wait for human approval. Resume with one API call. No message brokers. No infrastructure. Just one HTTP request.

How it works

1️⃣

Agent pauses

Your agent calls POST /api/checkpoint with the task description and current state. It gets a checkpoint ID back.

2️⃣

Human reviews

A human gets notified (email, Slack, dashboard). They review what the agent wants to do and approve or reject it.

3️⃣

Agent resumes

On approval, the agent's webhook fires with the original state. It picks up exactly where it left off. Rejection includes a reason.

3 lines to add human approval

// In your agent's critical step:
const checkpoint = await fetch("https://www.agent-utils.com/api/checkpoint", {
  method: "POST",
  headers: { "x-api-key": "au_...", "Content-Type": "application/json" },
  body: JSON.stringify({
    agentName: "deploy-bot",
    taskDescription: "Deploy v2.3.1 to production",
    state: { version: "2.3.1", target: "prod" },
    webhookUrl: "https://your-agent.com/resume"
  })
});

// Agent sleeps. Human approves via dashboard.
// Webhook fires → agent resumes with original state.

Why human-in-the-loop?

🇪🇺 EU AI Act compliance

The EU AI Act mandates human oversight for high-risk AI systems. Checkpoint gives you auditable approval logs out of the box.

🛡️ Prevent costly mistakes

Agents making production deployments, financial transactions, or data deletions? Add a human gate before the irreversible action.

⚡ Zero infrastructure

No Redis. No message queues. No state machines. One API call pauses your agent, one webhook resumes it. We handle the rest.

📊 Audit trail

Every approval/rejection is logged with timestamps, reasons, and the full agent state. Export for compliance audits.

Add human oversight to your agents

Free tier: 100 checkpoints/month. No credit card required.

Get your API key →