Interview review on the AI Agents track. Interviewers ask you to design an agent with tools, a stop rule, a risky action, and an eval. They want boundaries more than model names.
This lesson assumes you already worked through Getting unstuck.
The idea in practice
Practice a five-minute answer: goal, tools, loop, human gate, and how you would know it failed. Mention injection and idempotency.
A concrete check
goal = {
'track': 'AI Agents',
'lesson': 'Interview review',
}
checks = [
'input available at decision time',
'score matches the real decision',
'failure case written down',
]
print(goal['lesson'])
for item in checks:
print('-', item)
Run the sketch locally if you have Python. The printout is a reminder of the checks, not a trained model. Replace the strings with the real inputs from your own example before you treat it as a design.
What usually goes wrong
An answer that is only 'use GPT and a vector database' does not show you can ship safely. When this happens, stop adding parameters or tools. Fix the check, the data, or the permission, then run the same example again.
What to write down
- The input you are allowed to use at decision time.
- The output and the score or pass rule.
- One failure you will test on purpose.
- What you will not claim the system can do.
Practice
Give that five-minute answer out loud for a returns agent. Record the gaps.
Self-check
- Say Interview review in one sentence that mentions an input and an output.
- Name the failure mode in this lesson and the check that would catch it.
Done when: you can explain this lesson without the page open, and you have a written failure case.