Season 8: You Own the Release · Episode 6 of 8
Creator Night: The Feed Is Failing
You play: AI Engineering Intern
Included with Core programme and Certification prep
The situation
It is Code Nexus Live: Creator Night. Creators are streaming, chat is full, and errors are rising in more than one region. Support is hearing about it long before the monitors do.
What you'll learn
- Incident response under pressure: ordering actions into stabilise, diagnose and follow up; scoping a failure from logs; recording hypotheses with evidence; mitigating with a verified rollback; reasoning about a latent defect and the missing guard that spread it; communicating accurately without overclaiming; and writing a blameless, checkable incident record.
- Azure Monitor, Log Analytics, Application Insights, Container insights and VM insights; reading basic KQL (where, summarize, project, ago); distributed tracing; alerting on customer-visible symptoms.
Who you work with
Kabelo Mokoena
Platform and DevOps Engineer
Jax Rivera
Creator Partnerships Lead
Priya Naidoo
Cloud Architect
Scenes
- 1.The monitors say green
- 2.What comes first
- 3.Which KQL query answers it?
- 4.Find the pattern, write it down
- 5.Stop the harm
- 6.The fault nobody rehearsed
- 7.Just tell them it's fixed
- 8.The blameless record
- 9.Handover
What you leave with
You worked an incident nobody had rehearsed: ordered the response, counted errors from the log and wrote a testable hypothesis, rolled the feed back and proved it with a request, identified a latent defect and the missing guard that let one valid config reach every region, wrote a status update that stayed true, and filed a blameless record anyone can check.