FREE STUDY NOTES · AI-300

Safe rollout and rollback on managed online endpoints

Blue-green deployments, traffic splitting, mirroring and instant rollback.

From Ultra Transcenders AI-300 by Tony Rough (publishing soon)

Updating a production model should never mean downtime or a risky cut-over. Managed online endpoints support a blue-green pattern in which the old and new models run side by side behind one address.

Blue-green rollout

  1. A managed online endpoint hosts several deployments behind one scoring URI.
  2. Add the new model as a green deployment with 0% traffic and test it directly.
  3. Optionally mirror live traffic to it.
  4. Shift a small share of traffic (for example 90/10) and increase it while the metrics look good.

Rollback

Clients call one scoring URI on a managed online endpoint. A traffic rule sends 90% to the blue deployment and 10% to the green deployment, and a dashed path shows optional mirroring of live traffic to green. A rollback panel shows traffic set to blue=100 green=0, which is immediate because blue is still provisioned. A strip below lists the four rollout steps.
Figure 5.1: Blue-green rollout and rollback on one managed online endpoint

Common trap: A separate staging endpoint, a new registry version, or deleting and redeploying - a staging endpoint gets no production traffic and forces clients to change URLs, a registry version doesn’t route traffic, and deleting and redeploying is slow. Shift traffic between deployments on the same endpoint instead.

Get the whole book

This note is one section of Ultra Transcenders AI-300: Operationalizing Machine Learning and Generative AI Solutions, an independent study guide that explains every topic the exam covers by technology, with comparison tables, diagrams and the common traps, plus a glossary linked to Microsoft Learn.

Amazon.co.ukKindle: coming soonPaperback: coming soon
Amazon.comKindle: coming soonPaperback: coming soon

Publishing soon on Amazon in Kindle and paperback editions.

About the book · Free AI-300 glossary · All AI-300 study notes

More AI-300 study notes