MediumTechnical screen10 min to answer

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

1Give yourself 10 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 open-endedness, environment feedback, risk, predictability.
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 open-endedness, environment feedback, risk, predictability. I would select an approach only after comparing quality, latency, cost, safety, and operational complexity, then validate it with representative cases and production monitoring.

open-endedness
environment feedback
risk
predictability

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 open-endedness, environment feedback, risk, predictability. I would select an approach only after comparing quality, latency, cost, safety, and operational complexity, then validate it with representative cases and production monitoring.

open-endedness
environment feedback
risk
predictability

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

Grade yourself

open-endedness

weight 30%

StrongExplains open-endedness concretely and ties it to a decision or measurable outcome.

WeakMentions open-endedness without implications, trade-offs, or evidence.

environment feedback

weight 25%

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

WeakMentions environment feedback without implications, trade-offs, or evidence.

risk

weight 25%

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

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

predictability

weight 20%

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

WeakMentions predictability 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

Design an agent that can safely call external tools.