Reusable controls

Apply ready-made controls to common agent actions.

AI Control Packs are APort's enterprise-facing policy bundles for finance, data, repository, messaging, web, system, MCP, and deliverable workflows.

Browse policy catalog Read the OAP spec

Buyer

Who this is for

Teams that need a control library instead of writing every agent policy from scratch.

Outcomes

Use enterprise language with buyers while preserving OAP Policy Pack terminology in implementation.
Map passport capabilities and action context to specific allow/deny decisions.
Start from standard controls, then customize paid hosted policies for customer environments.

Controls

Finance and payment controls
File and data export controls
Repository and release controls
Messaging and web controls
MCP and deliverable controls

Proof

Policy IDs
Required context fields
Capability requirements
Decision reason codes

Setup

Set up Control Packs the way your team works.

Start agent-first when the agent has repo context, switch to human review when a security owner wants the path, or use the CLI when the integration is already clear.

Recommended

Let my agent prepare Control Packs.

Use this when an agent needs to map a concrete action to a governed policy.

agent instruction

choose the right APort AI Control Pack for this workflow — https://aport.io/skill

Copy this into the agent that already has access to your repo or runtime environment. Require a diff before enforcement or secrets are enabled.

Implementation

Policy Packs in API and docs

The implementation name remains Policy Packs because that is the OAP/API term. Do not duplicate pack inventories here; the live catalog is the source of truth.

Open policy catalog

Build the control path in layers.

Pre-action authorization