HardSystem designSystem design30 min to answer

Design an agent that can safely call external tools.

1Give yourself 30 minutes

2Answer out loud, not in your head

3Then compare with the answer below

Stuck? Show a way to structure it+

01Clarify the objective, user, constraints, and acceptable failure modes.
02Structure the response around tool schemas, permissions, state machine, recovery.
03Compare credible alternatives and state the decision criteria.
04Finish with validation, monitoring, and what would change the decision.

Reference answer

strong answer

I would first define the outcome and acceptable error boundary. I would explicitly cover tool schemas, permissions, state machine, recovery. I would select an approach only after comparing quality, latency, cost, safety, and operational complexity, then validate it with representative cases and production monitoring.

tool schemas
permissions
state machine
recovery

Must be adapted to the interviewer’s scenario
Would benefit from concrete numbers and personal examples

alternative answer

A second valid approach is to begin with the highest-risk assumption and test it cheaply. I would explicitly cover tool schemas, permissions, state machine, recovery. I would select an approach only after comparing quality, latency, cost, safety, and operational complexity, then validate it with representative cases and production monitoring.

tool schemas
permissions
state machine
recovery

Must be adapted to the interviewer’s scenario
Would benefit from concrete numbers and personal examples

Grade yourself

tool schemas

weight 30%

StrongExplains tool schemas concretely and ties it to a decision or measurable outcome.

WeakMentions tool schemas without implications, trade-offs, or evidence.

permissions

weight 25%

StrongExplains permissions concretely and ties it to a decision or measurable outcome.

WeakMentions permissions without implications, trade-offs, or evidence.

state machine

weight 25%

StrongExplains state machine concretely and ties it to a decision or measurable outcome.

WeakMentions state machine without implications, trade-offs, or evidence.

recovery

weight 20%

StrongExplains recovery concretely and ties it to a decision or measurable outcome.

WeakMentions recovery without implications, trade-offs, or evidence.

Then expect these follow-ups

What assumption is most fragile?
Tests: depth
What alternative did you reject and why?
Tests: adaptability
How would you validate this in production?
Tests: adaptability

Free to read · better with Enzo

Practice this out loud with Enzo

Enzo runs it as a mock interview, pushes back with follow-ups, and grades you on the rubric.

Continue with Enzo Sign up free

Next question

When should you use an agent instead of a deterministic workflow?