Skip to main content

​
Policy Evaluation

Policy evaluation is the core function of Parmana. Parmana evaluates verified facts against policy and determines whether an action is authorized. 
Verified Signals
        ↓
Policy Evaluation
        ↓
Decision
        ↓
Attestation
Policy evaluation occurs before execution. No action should execute until policy evaluation has completed.

​
Purpose

Parmana answers a single question:
Do the verified facts satisfy the policy requirements for this action?
If the answer is yes: 
Authorize
If the answer is no: 
Reject
If additional authority is required: 
Require Override

​
Core Principle

Parmana does not trust AI outputs. Parmana evaluates verified facts. 
AI Request
      ↓
Verified Signals
      ↓
Parmana Evaluation
AI may initiate a request. AI does not determine authorization. Policy determines authorization.

​
Inputs

Policy evaluation requires: 
Policy
Policy Version
Verified Signals
Example: 
{
  "policyId": "claims-approval",
  "policyVersion": "1.0.0",
  "verifiedSignals": {
    "insurance_active": true,
    "risk_score": 10,
    "vip_customer": false,
    "claim_amount": 100
  }
}
The policy defines the requirements. The verified signals provide the facts.

​
Verified Signals

Verified signals are facts that have already been validated by external systems. Examples: 
Customer Authenticated
Insurance Active
Account Verified
Balance Available
Destination Verified
Fraud Check Completed
Example: 
{
  "insurance_active": true,
  "risk_score": 10,
  "claim_amount": 100
}
Important: 
Parmana does not verify signals.
External systems verify signals. Parmana evaluates them.

​
Rule Evaluation

The policy engine evaluates verified signals against policy rules. Example: 
Policy
      ↓
Rule 1
Rule 2
Rule 3
      ↓
Decision
Example policy: 
IF insurance_active = true
AND risk_score < 50
AND claim_amount <= 1000

THEN approve
The evaluation process is deterministic. The same policy and signals always produce the same result.

​
Decision Outcomes

Policy evaluation produces a decision. Possible outcomes: 
Approve
Reject
Require Override
Example approval: 
{
  "action": "approve",
  "requires_override": false,
  "reason": "standard_approval"
}
Example rejection: 
{
  "action": "reject",
  "requires_override": false,
  "reason": "policy_requirements_not_satisfied"
}
Example override requirement: 
{
  "action": "reject",
  "requires_override": true,
  "reason": "manual_authority_required"
}

​
Rule Trace

Parmana records how a decision was reached. Example: 
{
  "ruleTrace": [
    {
      "ruleId": "high-risk-reject",
      "matched": false
    },
    {
      "ruleId": "standard-approval",
      "matched": true
    }
  ]
}
This provides transparency into policy evaluation.

​
Override Requirements

Some policies require escalation. Example: 
{
  "requires_override": true
}
Evaluation produces: 
Pending Override
The workflow becomes: 
Evaluation
      ↓
Pending Override
      ↓
Human Review
      ↓
Approval or Rejection
Overrides are separate from policy evaluation. The original decision remains unchanged.

​
Attestation Creation

After evaluation, Parmana creates a signed attestation. 
Decision
    ↓
Attestation
The attestation records:
  • Policy
  • Policy Version
  • Decision
  • Evidence Fingerprint
  • Provenance
  • Signature
Example: 
{
  "executionId": "claim-001",
  "policyId": "claims-approval",
  "policyVersion": "1.0.0",
  "decision": {
    "action": "approve"
  },
  "signature": "..."
}
The attestation becomes the authorization record.

​
Determinism

Policy evaluation is deterministic. 
Same Policy
      +
Same Signals
      =
Same Decision
Example: 
Policy v1.0.0
      +
Verified Signals
      =
Approve
Repeated evaluation produces the same result. This property is essential for verification and auditing.

​
Banking Example

A customer requests a transfer through an AI assistant. 
Customer
      ↓
AI Assistant
The AI captures the request. 
Transfer ₹10,000
The bank verifies facts. 
Customer Authenticated
Account Verified
Balance Available
Destination Verified
The verified signals are sent to Parmana. 
Verified Signals
        ↓
Parmana Evaluation
Parmana evaluates the transfer policy. 
Approve
An attestation is issued. 
Decision
      ↓
Attestation
The bank can now execute the transfer.

​
Auditability

Policy evaluation creates evidence that can be audited later. Auditors can determine: 
Which Policy Applied?
Which Facts Were Evaluated?
Which Rules Matched?
Which Decision Was Produced?
This creates a verifiable authorization trail.

​
Separation of Responsibilities

AI
 ↓
Captures Request

External Systems
 ↓
Verify Facts

Parmana
 ↓
Evaluates Policy

External Systems
 ↓
Execute Action
Each component has a clearly defined role.

​
How Policy Evaluation Fits Into Parmana

Task
 ↓
Policy
 ↓
Schema
 ↓
Verified Signals
 ↓
Policy Evaluation
 ↓
Decision
 ↓
Attestation
 ↓
Execution
Policy evaluation is the step where verified facts are compared against organizational authority rules. The result is a deterministic decision that can be signed, audited, verified, and enforced before execution.

​
Core Insight

Policies define authority. Verified signals provide facts. Parmana evaluates those facts against policy. 
Verified Signals
        ↓
Policy Evaluation
        ↓
Decision
This is how Parmana ensures that autonomous systems follow human rules before they act.