When should an AI agent ask a human for approval before acting?
Agents and tools · Intermediate 3
Short answer
Before actions that are irreversible, costly, affect other people or touch sensitive data: sending messages or email, payments, deleting or changing records, deploying code, or sharing private information. Reading and drafting can usually be automatic; acting on the world should start gated and loosen only as measured reliability grows.
Deeper answer
Think in terms of blast radius: what is the worst outcome if the agent is wrong or manipulated? Low-risk, reversible steps can run freely. High-risk steps need a confirmation that shows the person exactly what will happen.
Approval should not be the only control: also limit permissions so the agent physically cannot do more than the task needs, and log every action. Too many approval prompts train people to click yes without reading, so gate the actions that truly matter.
What a strong answer covers
- Irreversible or costly actions need approval
- Examples: payments, emails, deleting records, deploying
- Sensitive data or other people affected
- Loosen gates only as measured reliability grows
Answer it out loud in the mock interview about 1 min
Follow-ups to expect
- How would you design the approval screen?
- How do you decide when an action can move from gated to automatic?
Common mistakes
- Requiring approval for everything, which makes people stop reading
- Relying on approval without limiting the agent's permissions
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?
- 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?
- When is a multi-agent system worth it, and what are the risks?