AI/ML Systems

Learn AI/ML Patterns Observe

AI/ML Systems

Home Learn Patterns Observe

Opening…

failure-lab · coming next

Find the error family

one move: group failures before fixing them

This lab is authored next in the plan. Its questions below are ready to practice now.

6 practice questions attached

THEORY-003Construct a distribution shift that breaks this model: trained on weekday ticket traffic, served on weekends.construction · Distribution shiftpractice →
MODEL-010Explain one false positive and one false negative of the bug detector to a non-technical stakeholder.communication · Error taxonomypractice →
EXP-009Classify these errors by root cause: too-short tickets, rare vocabulary, duplicate training rows, and a leaked eval row.implementation · Error taxonomypractice →
EXP-010From this error taxonomy — 60% vocabulary errors, 25% duplicates, 15% short-text — choose the next experiment and predict its effect.prediction · Largest error familypractice →
EVAL-004Design slice evaluation for these user segments: mobile, desktop, and API-only users.construction · Slice evaluationpractice →
MLOPS-005Detect data drift before quality collapses: live traffic now uses 40% new vocabulary, model F1 still looks fine. Which alert fires first?debugging · Drift detectionpractice →

Prerequisite chain

This lab loads the previous artifact and asks you to keep, revise, or reject it — the artifact chain is the spine.