AI Governance Interview Questions

A production Claude Code rollout is an agent platform problem, not a 'give everyone a CLI' problem.

Cursor rules are context engineering in disguise.

This is an enterprise platform design question spanning agents, MCP, governance, and observability.

MCP (Model Context Protocol) defines a clean separation:

MCP multiplies agent power and attack surface.

Governance is becoming the bottleneck — not model IQ.

Product teams shouldn't each reinvent agent security.

**Architecture** LangGraph with interrupt before sensitive tools (lg-004); Bedrock or enterprise API.

**Bedrock** AWS-native security, CloudTrail, existing EA — model versions may lag.

**Azure benefits** VNet, Azure AD auth, Microsoft compliance certifications, existing EA billing.

**Use cases** Where zero-shot vision fails consistently on proprietary visual patterns.

Company-based MCP questions assess platform leadership, not wire protocols alone.

Dangerous tools are why agents aren't auto-root on production.

MCP testing maturity separates hobby servers from production integrations.

This question tests integration strategy, not religious protocol loyalty.

Encryption at rest/transit, tenant isolation, ACL on metadata filters, PII in embeddings, and audit logging.

Hybrid designs where LLMs handle language but calculators, rules engines, and APIs enforce deterministic outcomes.

Centralized prompt storage with versioning, approvals, environment promotion, audit trails, and runtime serving.

Medium AI Agents interview question on human-in-the-loop agent workflows — architecture, trade-offs, eval, and production patterns.

Hard RAG interview question on databricks interview: lakehouse rag — architecture, trade-offs, eval, and production patterns.

Hard project question on LLM gateway — auth, routing, rate limits, logging, key management, and multi-provider abstraction.

Hard Microsoft company question — enterprise copilot grounding, Graph permissions, tenant isolation, and compliance.

Hard Meta company question — Llama serving, GPU clustering, quantization, batching, and open-weight ops.

Hard scenario on PII in LLM systems — detection, redaction, DPA compliance, log minimization, and regional deployment.