The Platform Readiness Review

The situation

Nova Reyes goes live on Code Nexus Live in two days. Before the real thing, Kabelo, Priya and Lydia want a full rehearsal: package the release the way it will actually ship, deploy it the way it will actually run, and break something on purpose before anything breaks it for them. What isn't rehearsed now gets discovered live.

What you'll learn

• Combined Docker and Kubernetes practice: audit a runbook, inspect build inputs and digests, rehearse deployment and compatible rollback, diagnose a fixture failure and record evidence and remaining production requirements.
• Review metrics, traces and logs; SLI, SLO, SLA and error budgets; CNCF project maturity, engineering roles, autoscaling, Knative and FinOps. The 19-item programme checkpoint is practice, not an external exam result.

Who you work with

• 

  Kabelo Mokoena

  Platform and DevOps Engineer

• 

  Priya Naidoo

  Cloud Architect

• 

  Lydia Roe

  Security Engineer

Scenes

1. 1.Rehearse the failure, not just the launch
2. 2.Which observability tool?
3. 3.Who and what is cloud native?
4. 4.What the runbook doesn't say
5. 5.Package the launch build
6. 6.Deploy it, then break it on purpose
7. 7.The part nobody scripted
8. 8.Recover it, for real this time
9. 9.Platform readiness gate

What you leave with

The rehearsal proved the season's toolkit works together, not just in isolation: a pinned, scanned, non-root build deployed by digest; probes and a precise Service selector; a bounded rollingUpdate strategy that turned a known-bad drill candidate into a stalled rollout instead of an outage, recovered with a routine rollback. The unrehearsed failure was the runbook's own flagged gap made real — the launch manifest was still pinned to a movable tag, and it moved. Recovery meant redeploying pinned to the tested build without dropping the strategy that keeps recovery itself safe, verified by an actual request rather than a clean-looking dashboard.