Build on
PayReality
You're integrating the authority-continuity layer for delegated enterprise actions: it evaluates every signed action your AI agents send against your organization's delegated authority before it executes, and hands back a decision and its evidence.
An agent can now reason about a situation and decide, on its own, to request a real-world action. Nothing has independently confirmed that it's actually authorized to take that action until PayReality evaluates it.
Where PayReality sits
Your agent submits a signed intent to PayReality and receives an Allow, Deny, or Human Review decision. PayReality doesn't call your enterprise system itself: a trusted enforcement point you operate verifies and respects that decision before the downstream operation proceeds. Where that same enforcement point or a trusted execution adapter can report back what actually happened, PayReality also reconciles it against what it authorized. See the full Architecture for how each component in between fits together.
There are four surfaces you actually connect: the SDK or Runtime API to identify your Agent and submit signed intents; a Trusted Adapter where the real attempted operation needs an independent, trusted observation path; connected Trusted Enterprise Facts where your authority rules depend on external context; and Capability issuance and verification at your own enforcement boundary for actions that need stronger execution control. Most integrations start with the first and add the others only as the use case demands.
Getting Started
Create an organization, register an agent, and get your first Authorization Receipt back.
Architecture
The full path from an agent's signed intent to a decision and its evidence, component by component.
Runtime API
The Intent API: POST /v1/intents, its three possible outcomes, and the request/response lifecycle.
Authentication
The Operator Key, per-user roles and permissions, per-developer API keys, and agent certificates.
Authority Graph
Delegated authority, roles, resources, and approval limits, and how governance becomes machine-readable.
Runtime Policies
How a policy is compiled, versioned, and deployed, and why that differs from the governance document it came from.
Authorization Receipts
Why logs aren't enough, the receipt lifecycle, and the planned architecture for independent verification.
Evidence Verification
Signature verification, evidence export, and audit workflows against the Evidence Portal today.
SDKs
The Python SDK, and the language roadmap for Node.js, Go, Java, .NET, and Rust.
Webhooks
Enterprise events (IntentReceived, DecisionCompleted, ReceiptIssued, and more) with real payloads.
Integration Examples
Rotating keys, sending a heartbeat, and retiring an agent, with real SDK code for each.
Integration Guides
Connecting Runtime Authority to agent frameworks, model providers, and enterprise systems.
Agent Registration
The full agent lifecycle: registered, active, suspended, retired, or revoked.
API Reference
Endpoints, schemas, headers, status codes, errors, and versioning.
Interactive API Reference
Generated directly from the running platform, not a static mirror that can drift out of date.