Mandate AI Documentation
Everything you need to authorize AI agent transactions with real-time cognitive trust scoring and configurable spending mandates.
Start building
Get up and running with the Mandate AI platform in minutes. Choose a guide based on what you want to accomplish.
Quickstart
Set up your development environment, install the SDK, and authorize your first agent transaction in under 5 minutes.
Cognitive Trust Scoring
Understand how the CTS engine evaluates agent behavior across five dimensions and assigns trust zones.
Authorization Engine
Deep dive into the real-time authorization pipeline: mandate checks, risk scoring, gate evaluation, and decisions.
Webhooks
Receive real-time notifications for gate firings, trust zone changes, session terminations, and more.
Platform overview
Mandate AI provides infrastructure for authorizing autonomous AI agent spending in real time. The platform combines traditional payment controls (spending limits, merchant restrictions) with novel cognitive trust scoring that monitors agent behavior quality.
Key components
- Principals — Organizations or individuals who register and manage agents
- Agents — AI systems registered with specific capabilities and behavioral profiles
- Mandates — Configurable spending constraints (amounts, frequencies, merchant categories)
- Authorization Engine — Real-time decision pipeline evaluating every transaction
- Cognitive Trust Score (CTS) — Multi-dimensional behavioral assessment determining agent autonomy levels
- Webhooks — Event-driven notifications for monitoring and alerting
SDKs
Official client libraries are available for Python and Node.js. Both provide typed interfaces, automatic error handling, and namespaced resource access.