Nº 27

This week at Roark

March 7 to 7, 2026


01

🛡️ Compliance Analysis Package

A new analysis package that evaluates whether your AI agents comply with regulatory requirements, safety boundaries, and organizational policies — across healthcare, finance, and legal verticals.

9 compliance metrics out of the box:

MetricTypeWhat it measures
Regulatory AdherenceScale (1–5)Compliance with industry-specific regulations (HIPAA, PCI-DSS, GDPR, etc.)
Consent & DisclosureBooleanWhether the agent obtained required consent and provided necessary disclosures
Prompt Injection ResistanceBooleanWhether the agent resisted manipulation attempts to override its instructions
Identity ConsistencyBooleanWhether the agent maintained its assigned identity throughout the call
Hallucination BoundaryScale (1–5)Whether the agent avoided fabricating information and deferred when unsure
Unauthorized CommitmentBooleanWhether the agent made promises or commitments outside its authority
Sensitive Data HandlingScale (1–5)Whether the agent properly handled PII, PHI, and financial data
Escalation ProtocolBooleanWhether the agent correctly escalated when required by policy
Scope AdherenceScale (1–5)Whether the agent stayed within its defined role and topic boundaries

Key features:

  • Segment-level findings — For 5 metrics (prompt injection, identity, unauthorized commitment, escalation, consent), results include the specific agent statements where issues were detected
  • Customizable prompts — Every metric accepts optional additional evaluation criteria so you can tailor compliance checks to your organization's specific policies
  • Works with policies — Add compliance metrics to metric policies to automatically evaluate every production call

Also in this update:

  • Multi-select metric picker — The metric selector now stays open for multi-select with checkboxes, and supports "Select all" at the package level
  • View-only metric settings — System metric output configuration (boolean labels, scale ranges) is now visible in the metric library in a read-only mode
  • Optional/Required prompt labels — Metric settings now clearly indicate whether the LLM prompt is optional or required

From

James