AI engineering learning path
Data and engineering quality
Use metrics, experiments, tests, and documented decisions as evidence.
Suggested background: Be able to read Python, tables, and basic statistical expressions; no real business data is required. Offline examples check core mechanisms; full platforms and projects require the implementation and acceptance steps described in each guide.
Support engineering decisions with checkable evidence.
Support engineering decisions with checkable evidence.
Chapters
Connect metrics, charts, and experiments to a question
Use synthetic directory data to examine denominators, missing values, latency distributions, and experiment assignment, separating descriptive differences from evidence for a product decision.
Define the purpose and boundaries of event data
Define purposes, minimal fields, versions, and lateness rules for course-completion events, then trace how duplicates, missing records, and deletion affect derived metrics.
Support code evolution with tests and decision records
Use an integer discount rule to define behavior, rounding boundaries, and test layers, then preserve the rationale for small refactors through decision records.