Workload Maturity Guide

An actionable progression checklist for advancing agent workloads through Mandrel’s four operational maturity tiers.

This guide defines the actionable technical criteria required to advance an agent workload through Mandrel’s four operational maturity tiers.

Maturity Alignment: While Organizational Governance Maturity measures an enterprise’s overall governance readiness across teams, Workload Maturity Tiers govern the specific promotion criteria for individual agent deployments. A mature organization enforces these automated workload gates within its CI/CD and runtime infrastructure.

Tier Summary

Tier	Posture	Identity & Access	Governance Gate	Target Capabilities
Tier 1: Sandbox	Private / Prototype	Anonymous / Dev Token	Static schema check	Read-only MCP resources
Tier 2: Trusted	Verified Workload	SPIFFE SVID + OIDC	`mandrel-cli validate`	Mandatory HITL (`challenge-always`)
Tier 3: Federated	Discoverable Mesh	Signed Realized Spec	Metrology Lab promotion	Intent classification & capability discovery
Tier 4: Autonomous	Hardened Runtime	SPIFFE Federation + DPoP	Continuous Conformance	Dynamic Client Registration & CAE revocation

Tier 1: Sandbox (Private Prototyping)

The entry point for rapid agent prototyping and local development.

Progression Checklist

Author a baseline MandrelSpec declaring metadata name and namespace.
Scope agent tool calls exclusively to read-only MCP resources.
Run locally using Docker Compose behind a Mandrel Collet sidecar.

apiVersion: mandrelproject.ai/v1
kind: MandrelSpec
metadata:
  name: sandbox-agent
  namespace: default
spec:
  governance:
    risk-profile: "balanced"

Tier 2: Trusted (Verified Workload)

Transition from unverified prototype to a monitored workload operating within a strict governance envelope.

Progression Checklist

Pass static validation without errors: mandrel-cli validate agent-spec.yaml.
Provision a workload SPIFFE SVID via SPIRE or the Gantry Operator.
Enforce mandatory Human-in-the-Loop (HITL) gates (action: challenge-always) on all high-risk or state-changing tools.
Define explicit delegation depth limits (spec.runtime.max-hops-allowed).

spec:
  governance:
    risk-profile: "safety-first"
    enforcement-matrices:
      - type: "threshold"
        attribute: "transaction.value"
        tiers:
          - limit: 100.00
            action: "challenge"
  runtime:
    max-hops-allowed: 2

Tier 3: Federated (Discoverable Mesh)

Workloads promoted to the governed agent mesh, enabling capability-based discovery and cross-agent delegation.

Progression Checklist

Submit spec to the Metrology Lab promotion gate (mandrel-cli agents promote).
Obtain an approved, Ed25519-signed Realized Spec with platform policy ceilings baked in.
Configure Layer 0 Isolated Intent Verification (spec.governance.intent-verification).
Register declared capabilities in spec.capabilities.intents for late-binding discovery by orchestrators.

spec:
  governance:
    intent-verification:
      mode: "strict"
      failure-action: "deny"
  orchestrator:
    permitted-intents:
      - name: "Execute_Payout"
        description: "Fund transfer intent routing."

Tier 4: Autonomous (Scalable Production)

The highest assurance posture, enabling autonomous execution bounded by real-time revocation and cryptographic proof of possession.

Progression Checklist

Enforce sender-constrained tokens via DPoP (RFC 9449) (spec.identity.enforce-dpop: true).
Subscribe the Collet sidecar to Continuous Access Evaluation (CAE / RFC 8936) for sub-second token revocation.
Pass Metrology Lab Golden Dataset Benchmarking during automated re-promotion pipelines.
Enable Dynamic Client Registration (DCR) for automated SPIFFE trust domain federation.

Promotion Workflow

graph LR
    T1[Tier 1: Sandbox] -->|mandrel-cli validate| T2[Tier 2: Trusted]
    T2 -->|Metrology Lab Promotion| T3[Tier 3: Federated]
    T3 -->|CAE + DPoP + Benchmarks| T4[Tier 4: Autonomous]