When is a multi-agent system worth it, and what are the risks?
Agents and tools · Pro 1
Short answer
Use several agents when a task splits into parts that need different tools, instructions or context, or can run in parallel, such as research across many sources with an orchestrator and sub-agents. Risks: more tokens and cost, harder debugging, agents miscommunicating or duplicating work, and errors compounding. Start with one agent and split only when evals show a gain.
Deeper answer
Anthropic reported that its multi-agent research system beat a single agent on broad research tasks while using many times more tokens, which shows the trade-off clearly: parallel exploration helps when the task is wide and the value justifies the cost.
Design tips: give each sub-agent a clear, bounded task and output format; have the orchestrator check results; and trace every agent so you can find where things went wrong.
What a strong answer covers
- Worth it when work splits by tools, context or parallelism
- Orchestrator and sub-agents pattern
- Costs more tokens
- Harder to debug; errors compound
- Start single and prove gains with evals
Answer it out loud in the mock interview about 2 min
Follow-ups to expect
- How would sub-agents share information?
- What would you measure to justify a multi-agent design?
Common mistakes
- Starting multi-agent by default
- Ignoring token cost
Learn it
- What are common failure modes of agents, and how do you guard against them?
- What kinds of memory can an agent have, and how do you implement them?
- Your agent ran overnight and ran up a large API bill. What probably happened, and what do you change?
- How would you design a harness for an agent that has to work on one task for several hours?
- What is the difference between an agent and a workflow?
- What are computer-use or browser agents good for, and what are their risks?
- What is context engineering, and why does it matter for agents?
- An agent completes a task correctly most of the time but sometimes goes badly wrong. How do you debug it?
- What makes a good tool for an agent?
- Design an agent that handles refund requests for an online store.
- You changed your agent's harness. How do you prove the change made it better?
- What are verification gates in an agent harness, and how would you add them to a coding agent?
- How does tool calling work?
- When should an AI agent ask a human for approval before acting?
- Explain state, nodes, edges and checkpoints in LangGraph.
- What are planning and reflection in agents, and when do they help?
- Two coding agents use the same model, but one solves far more of your tasks. Why could that be, and how would you find out?
- What is an agent harness, and what is harness engineering?
- What is the Model Context Protocol, and why does it matter?