AARM

Conformance

Conformance Requirements

Two levels: AARM Core (R1–R6, all MUST) for baseline conformance and AARM Extended (R1–R9) for mature implementations.

AARM Core
R1 – R6

All six requirements are MUST. Baseline for AARM conformance.

AARM Extended
R1 – R9

Core + three SHOULD requirements for advanced governance.

Core Requirements — MUST

R1
Pre-execution interceptionMUST

The system MUST intercept every agent-initiated action before it is executed. No action may bypass the control plane.

R2
Context accumulationMUST

The system MUST accumulate and maintain context about the agent's intent, prior actions, and the conversation or task thread.

R3
Policy evaluation with intent alignmentMUST

The system MUST evaluate each action against a policy that considers both the action itself and its alignment with the stated agent intent.

R4
Five authorization decisionsMUST

The policy engine MUST be capable of producing one of five decisions: ALLOW, DENY, MODIFY, STEP_UP, or DEFER.

R5
Tamper-evident receiptsMUST

The system MUST produce a tamper-evident receipt for every evaluated action, including the decision, timestamp, and relevant context.

R6
Identity bindingMUST

Every action receipt MUST be cryptographically bound to an agent identity.

Extended Requirements — SHOULD

R7
Semantic distance trackingSHOULD

The system SHOULD track semantic distance between proposed actions and the original stated intent, flagging drift over long task horizons.

R8
Telemetry exportSHOULD

The system SHOULD export action telemetry in a standard format (e.g. OpenTelemetry) for integration with SIEM and observability platforms.

R9
Least privilege enforcementSHOULD

The system SHOULD enforce least-privilege scoping of agent credentials and tool access at the time of action execution.

Validation Process

Conformance validation is performed through the AARM Conformance MCP server. An agent runs the assessment end-to-end against your implementation — no manual checklists.

01

Request an activation key

Submit the form below with your organization name, product name, and target conformance level (Core or Extended). If your organization is on the allow-list, you will receive an activation key by email. Only listed organizations can run the assessment.

02

Connect to the AARM MCP server

Add the server to Claude Desktop or Claude Code using the instructions below.

https://aarm-conformance-mcp.herman-d10.workers.dev/
03

Run the assessment

Start a conversation with Claude and ask it to run the AARM conformance assessment. The agent will walk through each check, collect evidence, and produce a validation report.

Install on Claude Code

Run this in your terminal:

claude mcp add --transport http aarm-conformance https://aarm-conformance-mcp.herman-d10.workers.dev/

Then launch Claude Code and ask it to start the AARM conformance assessment.

Install on Claude Desktop

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "aarm-conformance": {
      "type": "http",
      "url": "https://aarm-conformance-mcp.herman-d10.workers.dev/"
    }
  }
}

Request access

Submit your organization details to receive an activation key.

Organizational Requirements

In addition to technical requirements, organizations must satisfy the following conditions to publicly describe their system as AARM-conformant.

ConditionExpected Result
Community engagementOrganization has an active representative in the AARM community
Production deploymentSystem is live in production with at least 5 active production customers running for a minimum of 3 months
Security certificationOrganization holds at least one recognized security certification (e.g., SOC 2 Type II, ISO 27001, FedRAMP) relevant to the operating environment
Benchmarking commitmentOrganization agrees to participate in future AARM benchmarking efforts measuring policy detection and enforcement metrics

Technical Testing

Each requirement includes a minimum test to confirm conformance. All MUST tests are required for Core conformance; SHOULD tests are required for Extended.

ReqTestExpected ResultLevel
R1Submit action matching DENY policyAction does not execute; denial receipt generatedMUST
R1Submit action matching DEFER conditionAction suspended; no effects; deferral receipt generatedMUST
R1Make AARM system unavailable, submit actionAction fails (no fail-open bypass)MUST
R2Execute action sequence, inspect context at step NPolicy engine receives all prior actions and data classificationsMUST
R2Tamper with prior context entry (if hash-chained)Tampering detectedSHOULD
R3Submit forbidden actionImmediate DENY regardless of contextMUST
R3Submit allowed action after sensitive data access (context-dependent deny)DENY based on contextMUST
R3Submit denied action with confirming context (context-dependent allow)STEP_UP or ALLOWMUST
R3Submit action with ambiguous/conflicting contextDEFERMUST
R4Trigger each of 5 decision typesALLOW executes, DENY blocks, MODIFY transforms, STEP_UP pauses, DEFER suspendsMUST
R4STEP_UP with no response within timeoutDENY after timeoutMUST
R4DEFER with no resolution within timeoutDENY after timeoutMUST
R5Generate receipts for ALLOW, DENY, MODIFY, STEP_UP, DEFERRequester context, delegation chain, and policy version/hash present per schemaMUST
R5Verify receipt signature offlineSignature validatesMUST
R5Tamper with requester context or policy hash in receiptSignature verification failsMUST
R5Verify deferred action receiptDeferral reason, resolution method, resolution timestamp presentMUST
R6Submit from different principals and sessionsReceipts correctly attribute identity including role/privilege scopeMUST
R6Defer action, then resolveOriginal identity preserved in resolution receiptMUST
R7Execute diverging action sequence exceeding drift thresholdAlert, deferral, or escalation triggeredSHOULD
R8Configure SIEM exportEvents appear with correct schema including DEFER eventsSHOULD
R9Submit read operationIssued credential cannot perform writesSHOULD