# APort

Authorization for enterprise AI workflows.

Set what agents may do with money, data and code. APort checks proposed actions against policy and provides decision evidence for review. Connect it to the applications and agent runtimes your team already uses.

## When To Use APort

- [Authorize payments and refunds](https://aport.io/blog/ai-payment-agent-security-policy-pre-action-authorization/) (API integration): Check an agent's payment capability, amount, currency and configured limits before your service moves money. Keep payment execution and reconciliation in your existing system.
- [Govern access to customer data](https://aport.io/enterprise/ai-agent-governance/) (API integration): Evaluate protected reads and exports against configured data policies. Supply trusted customer and resource context, then enforce the decision at the service boundary.
- [Delegate software delivery](https://aport.io/task-delivery/) (Restricted preview): Prepare a repository task, approve implementation, review checks and inspect completion evidence through the task workspace or MCP. Merge authority remains separate.

## Authority and evidence

Agent passports define ownership, capabilities, limits and status. Hosted policy
verification evaluates actions at `/api/verify/policy/{policy_id}`. Local hooks,
GitHub Repository Guard and custom service integrations enforce decisions at
their respective boundaries. Hosted decision signing depends on configuration;
local unsigned evidence has a different trust scope.

Your integration must enforce the decision before execution. A signed authorization is not proof that the action executed. Keep customer identity, resource permissions and execution evidence in the application.

Managed task delivery is in restricted preview; its production qualification is pending. Task execution depends on account eligibility, repository authorization, configured providers and available allowance. Preparation can use paid inference. An allowance is not a provider billing cap.

## Key Resources

- [Plan your workflow pilot](https://aport.io/pilots/)
- [Enterprise AI governance](https://aport.io/enterprise/ai-agent-governance/)
- [Products](https://aport.io/products/)
- [About APort](https://aport.io/about.md)
- [GitHub Repository Guard](https://aport.io/products/github-repository-guard/)
- [Quickstart](https://aport.io/quickstart/)
- [Frameworks](https://aport.io/frameworks/)
- [AI Control Packs](https://aport.io/products/control-packs/)
- [Policy catalog](https://aport.io/policy-packs/)
- [Compare authorization approaches](https://aport.io/compare/)
- [Research](https://aport.io/research/)
- [Pricing](https://aport.io/pricing.md)
- [Auth guide](https://aport.io/auth.md)
- [API guide](https://aport.io/api.md)
- [API documentation](https://aport.io/api/documentation)
- [OpenAPI](https://aport.io/api/openapi-json)
- [Platform skill](https://aport.io/skill)
- [Skills library](https://aport.io/skills/)
- [ARD catalog](https://aport.io/.well-known/ard.json)
- [Agent Skills index](https://aport.io/.well-known/agent-skills/index.json)
