Gaten platform
Every agent action, checked before it happens.
When an AI agent wants to refund $500, move money or touch customer data, it asks your policy first. Allowed, denied, or sent for approval — decided in real time and recorded for audit.
1 · agent requests action
support-agent → issue_refund()
amount: $500 · order #A-2210
2 · evaluate policy refunds-policy v2.4
match: $100 < refund.amount ≤ $1,000
- 3 · decisionRouted to finance leadREQUIRES APPROVAL
4 · recorded to audit trail
decision_id dec_8f3a · 14:02:11 UTC
Explore the platform
Five parts. One checkpoint.
- Explore
How it works
Intercept, evaluate, decide, record — what happens between an agent's tool call and the real system.
- Explore
Policies
Readable, versioned rules for any action. Reviewed like code, dry-run before they go live.
- Explore
Human approvals
Held actions reach a named person with full context, timeouts and escalation.
- Explore
Audit trail
Every request and decision in an append-only log, linked to the policy version that made it.
- Explore
Enterprise controls
Low-latency decisions, any agent framework, environment separation and access control.
Any use case
Refunds are one example.
Payments, customer data, outbound messages, infrastructure, account changes — if an agent can do it through a tool, you can put a rule in front of it.
From the blog
Related reading
- Agent policyAI agent policy: how to write rules your agents actually followAn AI agent policy sets what agents may do alone, with approval, or never. How to write one, who owns it, and how to enforce it on every action.
- Agent policyAI agent governance: a practical operating modelAI agent governance turns principles into daily practice — owners, rules, approvals and records for every agent. A lightweight model you can run.
- Agent policyAI agent guardrails: why prompts aren't limitsAI agent guardrails written in a prompt can be talked past. Here's how to enforce real limits on what agents do, checked on every action.


Put your AI agents under policy.
Talk to an expert about enforcing policy on the agents you run — from one support bot to a fleet of autonomous workflows.