Machine Learning
Milestone 5 of 7 ยท industry roleplay

Launch, A/B test & on-call

Launch with an A/B test, let a reinforcement-learning bandit choose reminders safely, handle a 2 a.m. production incident, and write a blameless postmortem. Includes 5 hands-on Python coding tasks (pandas, scikit-learn), checked by automated tests.

Rigour50Communication50Ethics50Impact50Teamwork50
Mon 10:00Launch readiness reviewMon 12:00Code it: package the model for productionMon 14:00Design the A/B testWeek 5, TueThe results are inWeek 5, WedCode it: the A/B test statisticsWeek 6Which reminder works best?Week 6Code it: Thompson samplingWeek 9Something is wrong2:40 amFind the root cause3:15 amCode it: a drift monitorWeek 9, ThuCode it: a data contractWeek 9, FriBlameless postmortem
Mon 10:00Launch readiness reviewGo / no-go meeting
Launch checklistWhat must be true before go-live?
Maya Chen: Go/no-go meeting. Tick everything that must be in place before the no-show system goes live.

Bluegum Health, Riverside Clinics and every person here are fictional. The decisions, tools and practices are modelled on how real ML teams work.

Ready