Architecture

The technical and philosophical framework for engineering amorphous AI.

The Mandrel Project provides a deterministic governance layer for stochastic AI agents. It is designed to “clamp” amorphous agent behaviors to a rigid, machine-readable contract.

Design Philosophy: Engineering the Amorphous

In high-precision manufacturing, a Mandrel provides internal support and defines the shape of a workpiece. Similarly, the Mandrel Project provides the deterministic axis for risk mitigation in agentic systems:

  • The Mandrel Spec: A declarative contract defining an agent’s structural boundaries and risk envelope.
  • The Collet (Sidecar): A high-performance proxy that “clamps” the agent to the spec, ensuring it never slips from security, financial, or data-sovereignty constraints.
  • The Gantry: An automated capability for Agent Lifecycle Management, including sidecar injection and SPIFFE identity provisioning.
  • The Metrology Lab: The Promotion Authority where agents are certified and signed against platform policies and “Golden Datasets” to quantify performance risk. The role it fills is defined as a portable contract, so a deployment can satisfy it with the managed service, a self-hosted lab, or a CI pipeline holding a signing key — see the metrology contract.

Core Architectural Pillars

1. Runtime Mesh (Orchestrator-Specialist)

Mandrel utilizes a decoupled pattern enforced by the Collet sidecar:

  • Orchestrator: Handles intent classification and task delegation.
  • Specialist: An ephemeral, domain-specific worker bound to scoped infrastructure and governed by a specific Mandrel Spec.
  • Model Context Protocol (MCP): The standardized interface used by specialists to interact with enterprise systems (Resources, Prompts, and Tools).

For late-binding topologies where orchestrators dynamically discover and bind specialists over the network at runtime, see the white paper on governing late-binding agent harnesses.

2. Compound Identity (The “Double Badge”)

To prevent privilege escalation and “Identity Wash,” Mandrel mandates a two-factor context:

  • Machine Identity: SPIFFE SVIDs managed by the Gantry.
  • Human Context: User authorization propagated via OIDC and Nested JWTs (RFC 8693).

3. High-Assurance Governance

The architecture ensures a Fail-Closed posture. If the governance layer (Collet, Registry, or IdP) is unreachable or a constraint is ambiguous, the system terminates the action rather than failing-open. This assurance is maintained throughout the agent lifecycle via Continuous Conformance Checks, which periodically re-evaluate promoted agents against “Golden Datasets” to mitigate model and threat drift.

Layered Workload Maturity Model

Individual agent workloads progress through four operational maturity tiers as they advance toward production. While Organizational Governance Maturity measures overall enterprise adoption, a highly mature organization enforces automated workload maturity gates to promote agents through these specific tiers:

  1. Tier 1: Sandbox (Private): Rapid prototyping using read-only MCP resources.
  2. Tier 2: Trusted (Verified): Agent passes mandrel-cli validate static checks; receives a SPIFFE ID; HITL is mandated for high-variance actions.
  3. Tier 3: Federated (Discoverable): Realized Spec is signed and published to the Metrology Lab for dynamic capability discovery by orchestrators.
  4. Tier 4: Autonomous (Scalable): Fully hardened runtime controls enabled, including Dynamic Client Registration (DCR) and Continuous Access Evaluation (CAE) real-time revocation.

Logical Flow

graph TD
    subgraph "User Layer"
        U[Human Operator] -->|Auth| IDP[Identity Provider]
        U -->|Task| ORCH[Orchestrator Agent]
    end

    subgraph "The Mandrel Mesh"
        ORCH -->|Discovery| LAB[(Metrology Lab)]
        ORCH -.->|A2A gRPC| COL[Collet / Specialist]
    end

    subgraph "Governance Control"
        COL -.->|Evaluate| OPA{Open Policy Agent}
        COL -.->|Audit| OTEL[OpenTelemetry]
    end