AWS · MLA-C02 · BETA
CI/CD, deployment strategies, and testing
MLA-C02 · Lesson 18 of 23 · 2:21:07
YouTube loads only after you press play. This chapter opens at its timestamp in the full course. Watch on YouTube ↗
In this lesson
Lesson 18 of the free MLA-C02 beta series (AWS Certified Machine Learning Engineer – Associate, domain 3, deployment and orchestration). In this lesson: the AWS developer tools and troubleshooting a pipeline, blue-green, canary, linear, and rolling deployments, tests for ML and for AI, and Amazon Bedrock Prompt Management. With three quick checks and a recap, and AnyCompany Mobility, a car sharing service, as the running example.
Preview the topics
- The team keeps its code in GitLab, and wants every merge to the main branch to build, test, and deploy the model. A person must approve before production. Which combination fits?
- A new demand model must reach production with little risk. The team wants ten percent of the traffic on it first, then all of it, and an automatic return to the old model if the error alarm fires. What should the ML engineer configure?
- Product owners edit the support prompt in Prompt Management several times a day. Production must keep the prompt that passed the regression tests, until the next release. What should the application call?