🔐 Pre-Approval API for AI Agents

TEACH YOUR AGENT TO ASK PERMISSION

Should your agent send that email? Post that tweet? Spend that money?Let users decide with simple rules.

# Check before you act

curl -X POST https://consent.agentz.fyi/api/v1/check-action \

-H "Authorization: Bearer cg_xxx" \

-H "Content-Type: application/json" \

-d '{"action": "send_email", "category": "email", "metadata": {"recipient": "boss@company.com"}}'

# The verdict

{
  "allowed": true,
  "decision": "allow",
  "reason": "Rule: Allow work emails",
  "rule_id": "rule_abc123"
}

How It Works

Three decisions. Total control.

Agent proceeds autonomously. No friction, full trust for approved actions.

Action blocked. Agent knows not to proceed. Clear boundaries.

Agent requests human approval. Webhook notifies you for decision.

Define rules by category, conditions, and priority. No code required.

Sub-50ms response times. Your agent won't even notice.

API keys encrypted at rest. Full audit log of every check.

See every decision your agent makes in real-time.

Get notified when 'ask' decisions need human input.

One-click rule templates: Allow All, Deny All, Work Hours Only, and more.

Start free, upgrade when you need more.

For getting started

$0/mo

Popular

For production agents

$5/mo

Stop guessing what your agent should do. Let users define the rules.