Skip to main content

​
Interpreting Compliance Reports

How to read and act on ZebraTruth compliance results.

​
Score & Decision

Score RangeDecisionWhat It MeansAction
80-100PUBLISHContent is compliantSafe to publish as-is
60-79HOLDIssues found, none criticalReview and fix flagged items before publishing
0-59HOLD or BLOCKSignificant or critical violationsMust fix. If BLOCK, at least one critical issue exists

​
Decision Logic

  • BLOCK if any check has status: "block" OR any check has severity: "critical"
  • HOLD if score < 60 OR any check has severity: "high"
  • PUBLISH otherwise

​
Scoring Formula

Starting from 100, each non-pass check deducts:
  • critical: -25 points
  • high: -15 points
  • medium: -8 points
  • low: -3 points
  • info: 0 points
Score is clamped to [0, 100].

​
Checks Array

Each check represents a finding from one agent: 
{
  "agentId": "advertising-law",
  "checkName": "unsubstantiated-claim",
  "status": "flag",
  "severity": "high",
  "message": "Human-readable description of the issue",
  "recommendation": "Specific action to fix it",
  "citation": "Legal reference (e.g., '16 CFR Part 255')"
}

​
Check Status Values

  • pass — No issue found
  • flag — Issue found, review recommended
  • block — Critical issue, must fix
  • escalate — Needs human review (ambiguous)

​
Agent Summaries

The agentSummaries field provides a high-level view per agent: 
{
  "advertising-law": {
    "status": "flag",
    "checkCount": 5,
    "passCount": 3,
    "flagCount": 2,
    "blockCount": 0,
    "summary": "2 advertising claim issues found"
  }
}

​
Version Info

{
  "engineVersion": "1.3.2",
  "rulesVersion": "2026-04-01",
  "agentVersions": { "advertising-law": "1.1.0", ... },
  "modelVersions": { "perplexity/sonar-pro": "sonar-pro-2026", ... }
}
Use this to explain why results may change over time. Rules are updated when platform policies or laws change.

​
Cost Breakdown

{
  "totalCredits": 47,
  "agents": [
    { "agent": "jurisdiction", "stage": "A", "model": "perplexity/sonar-pro", "credits": 2, "cached": true },
    { "agent": "jurisdiction", "stage": "B", "model": "gpt-5.2", "credits": 3 },
    ...
  ]
}
cached: true means the research stage used a cached result (0 provider cost, but logged for analytics).