Agentic Engineering Interview
Every question shows beginner, strong and expert answers side by side, green and red flags, follow-ups and a practical scenario. The goal is judgment: does the candidate ask whether the agent is needed at all?
Interviewing someone?
Hiring guides: 5-minute screen, scoring levels, tiered questions →
FundamentalsBeginner
What makes a system agentic?
What makes an AI system 'agentic'?
FundamentalsBeginner
Agent vs workflow
What is the difference between an agent and a workflow, and why does the distinction matter in practice?
FundamentalsIntermediate
Plain LLM vs RAG vs agent
Given a new feature request, how do you decide between a plain LLM call, RAG, and an agent?
ArchitectureIntermediate
Choosing a workflow over an agent
When would you choose a workflow over an autonomous agent?
ArchitectureIntermediate
Architecture for a support bot
Design the architecture for a customer support assistant that answers product questions and can process refunds. Which architecture do you choose and why?
ArchitectureIntermediate
Router vs supervisor
What is the difference between a router architecture and a supervisor architecture, and when would you use each?
Tool CallingIntermediate
Preventing destructive tool misuse
How would you prevent an agent from calling a destructive tool incorrectly?
Tool CallingBeginner
Designing a tool schema
How do you design a good tool schema for an LLM, and what makes a schema bad?
Tool CallingIntermediate
Handling tool errors and retries
A tool called by your agent fails intermittently. How do you handle errors, retries, and timeouts?
RAGIntermediate
RAG retrieves well but answers wrong
Your RAG system retrieves relevant documents but still produces incorrect answers. How would you debug it?
RAGIntermediate
Choosing a chunking strategy
How do you choose a chunking strategy for a RAG system, and how do you know it is working?
RAGIntermediate
When to use hybrid search
When should you use hybrid (dense + sparse) retrieval instead of pure vector search?
MemoryIntermediate
What belongs in long-term memory
What information should and should not be stored as long-term agent memory?
MemoryIntermediate
Why more memory is not better
Why is giving an agent more memory or more context not automatically better?
MCPBeginner
What MCP solves
What problem does MCP solve compared with implementing every integration directly?
MCPIntermediate
MCP vs function calling
How does MCP relate to native function calling, and when would you use one, the other, or both?
Multi-AgentAdvanced
When multiple agents help or hurt
When does splitting a system into multiple agents improve it, and when does it make the system worse?
Multi-AgentAdvanced
Multi-agent made it worse
A team split a single agent into a supervisor with four workers and quality dropped. What are the likely causes and what would you do?
EvaluationAdvanced
Is version B actually better?
How would you determine whether version B of an agent is actually better than version A?
EvaluationIntermediate
Choosing eval metrics
How do you choose evaluation metrics for an agentic system, and what goes wrong when you pick the wrong ones?
EvaluationAdvanced
LLM-as-judge pitfalls
What are the pitfalls of using an LLM as a judge, and how do you mitigate them?
SecurityAdvanced
Indirect prompt injection
How can indirect prompt injection compromise a tool-using agent?
SecurityIntermediate
Least privilege for agent tools
How do you apply least privilege to an agent's tools, and why is it harder than for a normal service?
ProductionAdvanced
Works in demos, fails in production
An agent works well in demos but fails unpredictably in production. How would you investigate it?
ProductionIntermediate
Agent that never terminates
Your agent sometimes loops indefinitely or runs far longer than expected. What causes this and how do you prevent it?
ProductionIntermediate
Cost blew up after launch
Costs of your agent grew ten times faster than traffic after launch. How do you find the cause and bring it under control?