Design Pattern AI Interview Questions

**Mechanics** Assistant message may include tool_use blocks with id, name, input JSON; user message returns tool_result tied to id.

Prompt injection is the #1 security interview topic for agents that read untrusted text.

Hard RAG pattern question on corrective retrieval and gated web fallbacks.

**Proxy layer** Backend holds keys; assigns budgets per customer/plan.

**Concept** Responses treat interaction as structured items (messages, tool calls, outputs) with native support for reasoning models and built-in tools — reducing glue code.

**Supervisor pattern** Central node decides next worker or FINISH based on plan and worker outputs — alternative to flat handoff messages.

**Pattern** Planner node outputs list of work items → map workers process each (possibly subgraph) → reducer synthesizes executive summary or ranked list.

**Parallelism model** LangGraph can schedule independent nodes in same superstep concurrently — e.g., search three sources at once. Reducers combine outputs into unified state field.

**Why subgraphs** Parent graph orchestrates; subgraphs own domain logic — billing dispute flow, code review pipeline. Teams ship subgraph versions independently.

Long-running tools expose gaps between synchronous tool calling and real workloads.

Database MCP is high risk/high value — interviewers probe your safety instincts hard.

Enterprise MCP rarely connects laptops directly to SaaS MCP servers. The gateway is the control plane interviewers want you to design.

Building a custom MCP server is a common system-design follow-up to "what is MCP?" Strong candidates describe end-to-end architecture, not just SDK boilerplate.

Brute-force exact search thresholds, ANN recall trade-offs, and hybrid exact re-rank on shortlists.

Multi-agent prompt patterns where distinct personas argue, review, or refine outputs before final synthesis.

Medium AI Agents interview question on openai swarm / agents sdk patterns — architecture, trade-offs, eval, and production patterns.

Hard AI Agents interview question on multi-agent debate and critique patterns — architecture, trade-offs, eval, and production patterns.

Medium AI Agents interview question on plan-and-execute vs react — architecture, trade-offs, eval, and production patterns.

Easy AI Agents interview question on the ReAct pattern — Thought/Action/Observation loops, trade-offs, and production guardrails.

Medium RAG interview question on small-to-big retrieval patterns — architecture, trade-offs, eval, and production patterns.

Hard Anthropic company question — least-privilege tools, confirmation flows, injection defense, and constitutional guardrails.

Scenario question comparing CoT prompting with calculators, code interpreters, and search tools for reliable reasoning.

Scenario question on LLM guardrails — prompt injection defense, output validation, NeMo/Guardrails patterns, and policy layers.

Hard model question comparing CAI, RLHF (PPO), and DPO — data efficiency, stability, and production fine-tuning trade-offs.