Start with visibility
Observe and Shadow modes report what a deterministic policy would do before an enforcing rule can interrupt production.
AI governance gateway
Enforce AI policy before a request reaches the model.
Check identity, approved models, tools, data handling, and spend before the provider receives a request. Test each rule in Observe mode before enforcing it.
Organization and key-scoped policy
Observe, Shadow, and Enforce evaluation modes
Pre-spend tool/MCP declaration checks and pre-release call authorization
Reason-coded request decisions and audit metadata
One rule, one result
Write the rule once. Apply it at the gateway.
Do not make every application reinterpret company policy. AI Gateway HQ checks the same rules for each request, records why it allowed, limited, rerouted, or denied the call, and lets administrators preview the effect before enforcement.
A shared decision recordSecurity, finance, and engineering see the same outcome and reason code. They can resolve exceptions without trading screenshots or reading prompt content.
A controlled rollout
Test the rule before it blocks anyone.
Run the rule in Observe, review the affected traffic, narrow its scope, and turn on Enforce when the result matches the written policy.
What administrators configure
Who and what it covers
Target an organization, workload key, environment, client mode, model, data class, or signed attribute.
How it rolls out
Observe current traffic, Shadow a proposed result, or Enforce a decision the team has already reviewed.
What happens next
Allow, deny, cap, or restrict routes with stable reason codes for triage and reporting.
How to recover
Compare policy and safeguard releases. Restore a known-good configuration as a new version after it passes current checks.
Which tools are available
Restrict function and MCP names, types, hosts, and counts before spend, then stop unoffered or unauthorized calls before release.
What happens to each request
- 01Identify
Bind the request to an organization, workload, environment, user, and declared execution context.
- 02Evaluate
Apply policy and local attack signals before any provider credential is decrypted.
- 03Act
Allow, deny, cap, reroute, or observe the request with a stable reason code.
- 04Evidence
Write authorized metadata for review without persisting prompt or response bodies by default.
See the working control
Troubleshoot from the decision, not from a prompt archive for governance.
For governance, the live ledger shows workload, route, reason code, upstream attempt, outcome, latency, configured cost, and audit-chain integrity.
- This governance view runs in the working customer console
- Exercised with safe OpenAI- and Anthropic-compatible simulators
- The governance capture excludes keys, prompt text, responses, and private email
For governance, the live ledger shows workload, route, reason code, upstream attempt, outcome, latency, configured cost, and audit-chain integrity.
Controls in the product
Set the boundary, rollout mode, and enforcement action.
The console shows each rule's scope and effective mode before an administrator applies it to live traffic.
Higher-level controls stay effective
Organization posture caps the effective policy mode. A route- or key-scoped rule can narrow access, but it cannot silently weaken the organization boundary.
Agent-aware enforcement
Signed context distinguishes planning, interactive execution, CI/CD, and unattended agents. Tool profiles inventory function and MCP metadata, enforce names/types/hosts/counts before spend, and stop unoffered or unauthorized calls before release.
Inside the decision record
Review the rule, request context, and action.
The record shows which control applied and why. Prompt and response bodies stay out of the hosted ledger by default.
Review security boundaries and current status Read the plain-language AI gateway guide Use the 12-test enterprise evaluation Govern without retaining prompt bodies Review the secure gateway boundary- Who and what it covers: Target an organization, workload key, environment, client mode, model, data class, or signed attribute.
- How it rolls out: Observe current traffic, Shadow a proposed result, or Enforce a decision the team has already reviewed.
- What happens next: Allow, deny, cap, or restrict routes with stable reason codes for triage and reporting.
- How to recover: Compare policy and safeguard releases. Restore a known-good configuration as a new version after it passes current checks.
Before you deploy
Questions about applying AI policy.
Confirm how testing, overrides, prompt handling, and tool execution work before a rule reaches production.
Can a team test a rule without blocking users?
Yes. Observe and Shadow modes preserve the proposed decision and reason while allowing traffic to continue. Move to Enforce only after review.
Can business units override a central boundary?
The current model supports organization and workload-key policy. Delegated hierarchy and non-overridable parent controls are not currently available and should not be assumed in a pilot.
Are prompts or tool arguments stored for governance reporting?
Not by default. The hosted ledger retains operational metadata, policy reasons, bounded tool names/types/MCP hosts, counts, cost, and timing rather than prompt/response bodies, tool schemas, arguments, or results.
Does authorizing a tool make its execution safe?
No. The gateway controls what may be offered to a model and what emitted calls may be released. The client or tool host still owns user approval, least-privilege credentials, argument validation, egress policy, sandboxing, execution, and result handling.
Start safely
Start guided setupSee what the policy would do before it can block production.
Start with a provider connection, a limited workload key, and Observe mode; move to enforcement after your team confirms the result.