Skip to main content

A policy attaches one built-in plugin to a gateway. It runs at one or more lifecycle stages and can cover the whole gateway or selected consumers.

Rate limits and budgets

Request rate, per-tool rate, and LLM token budgets.

Request size

Cap payload size before the request is forwarded.

Prompt and model controls

Prompt templates and compression.

Tool governance

Allow-lists, injection, and per-tool limits for MCP and function calling.

Guardrails

TrustGuard, provider moderation, and regex replace.

TrustGuard integration

Native collector — no tgk_ key on the TrustGate path.

Policies screen

Open Agent GatewayPolicies.

Create or edit

  1. Catalog → pick a plugin, or New policy.
  2. Set Name (catalog types use a fixed prefix where required).
  3. Scope
    • Mode: Enforce · Observe · Throttle (when the plugin supports it).
    • Coverage: Gateway-wide or Targeted (pick consumers).
  4. Fill Configuration (dedicated form or schema-driven fields).
  5. Save. Use Pause / Resume / Delete from the detail panel without losing history of attachments.

Attach from a consumer

Open a consumerPoliciesAdd Policy, or Clone policies from another consumer. Global policies still apply automatically.

Catalog (UI plugins)

Traffic control

Quota

Prompt management

Tool governance

Guardrails

TrustGuard in the UI. Adding the TrustGuard policy walks you through selecting or creating an Agent Runtime collector. Connection details are injected by the platform; you do not paste base URLs by hand in normal SaaS use.
The live Catalog tab is authoritative for what you can add in your tenant.

Stages

Mode

Ordering

Lower priority runs earlier. Same-priority policies may run in parallel when enabled. Global policies are the baseline; targeted policies refine per consumer.