← All learning paths
Learning path · 5 steps
Ship an Azure AI workload safely
Design explicit identity and network boundaries, test untrusted input, and make a release decision with evidence.
Cloud engineers & application teams
- 01
Practical guide
Start Azure AI access with workload identity
Select the correct runtime identity, API and role scope.
Open guide → - 02
Practical guide
Verify Azure AI network isolation end to end
Verify inbound, outbound and dependency network paths.
Open guide → - 03
Practical guide
Build a prompt-injection defense test plan
Exercise untrusted-input and unauthorized-action scenarios.
Open guide → - 04
Practical guide
Build an AI telemetry baseline you can investigate
Confirm that expected logs reach the investigation workspace.
Open guide → - 05
Practical guide
Use an evidence-based AI release checklist
Record evidence, exceptions and a rollback owner before release.
Open guide →