LLM Foundations · 3 to 4 hours
Select a model under quality, cost, and latency limits
Recommend a model or routing policy from measured quality, cost, and latency, say what evidence is still missing, and revise the decision when the traffic mix changes.
Hard
System Design
4 h
Premium
Used in interview rounds:
Technical Screen (Hard)1
Step 1: The question
Using the selection scenario, recommend a model or routing policy. Calculate aggregate quality and monthly token cost for each option, explain what additional evidence you need before committing, and revise the decision if complex questions grow to 40% of traffic.
Constraints
- Every acceptance criterion is a mandatory gate
- Token averages and per-group success rates stay the same when the mix changes
- Router cost and router latency are unknown
Deliverables
- Recommendation for today's 80/20 mix, with the calculations
- The evidence you need before committing, and why
- Revised decision for a 60/40 mix
- What would make you reconsider
Hard questions are part of Premium: the study guide, reference answer, rubric, and exercises unlock with Premium.