Module 9

Compliance & Data Privacy

Before deploying to a regulated client, an architect must know exactly which features are Zero Data Retention eligible, how to prevent PHI leakage through schema caching, and how US-inference pricing affects committed capacity.

Answer key Module9_Complete.ipynb

1. ZDR Eligibility Matrix

Zero Data Retention means Anthropic does not store inputs or outputs beyond serving the request. Know this table for the exam.

Feature ZDR Eligible? Reason if Not
Adaptive ThinkingYesN/A
Effort parameterYesN/A
CitationsYesN/A
Structured OutputsYesN/A
Web Search / Web Fetch (standard)YesN/A
CompactionYesN/A
Bash, Computer Use, Text EditorYesN/A
Message Batches APINoInputs/outputs stored server-side up to 29 days
Files APINoFiles stored server-side
Code ExecutionNoExecution state held server-side
Agent SkillsNoSkill data follows standard retention
MCP ConnectorNoRequires server-side routing
Web Search/Fetch + Dynamic FilteringNoCode execution required; stores intermediate state

2. HIPAA Safeguards: Schema Caching Risk

For healthcare-related marketing, PHI must never appear in JSON schema definitions.

  • Why: Structured output schemas (tool definitions, output_config) are compiled and cached separately from message content, they may be treated differently under your BAA.
  • Rule: Field names in schemas should be generic ("patient_id""record_id"). Actual PHI values belong in message content only, never in schema property names or descriptions.

3. US Inference Pricing Multiplier

Setting inference_geo: "us" restricts compute to US infrastructure and incurs a 1.1x pricing multiplier on all token categories for models starting with Claude Opus 4.6.

  • Priority Tier impact: Each token processed with inference_geo: "us" draws down 1.1 tokens from your committed TPM capacity, the multiplier applies to Priority Tier burndown, not just standard billing.
  • ZDR compatibility: Data Residency (inference_geo) is ZDR-eligible. You can combine US-only inference with ZDR for the highest data protection posture.
Architect Tip for the Exam

The 1.1x multiplier applies to Opus 4.6 and above, not to Haiku or Sonnet models below that threshold. When a client asks for US-only inference on a cost-sensitive workload, recommend Haiku 4.5 (unaffected by the multiplier) for high-volume steps and reserve Opus for strategic reasoning only.

Lab Exercise: Compliance & Data Privacy Review

Self-driven lab Module9_Self_Driven_Lab.ipynb

Objective: evaluate an agent architecture for ZDR, regional inference, and regulated-data risks.

  1. Create a feature matrix that marks each component ZDR-eligible or not.
  2. Add `inference_geo: "us"` where appropriate and calculate the policy/cost implication.
  3. Review schema caching or prompt caching choices for regulated data exposure.
  4. Define a human escalation trigger for privacy-sensitive or policy-uncertain actions.
Expected Deliverable

A compliance review memo for the advanced agent architecture.