- Learning Path Libraries: This path is only available in the libraries listed. To access this path, purchase a license for the corresponding library.
- Cloud
Cloud Engineering with Kiro, Copilot, and Safe AI-assisted Delivery
Watch coding agents do real work in a real cloud account, then learn what it takes to trust them. Two full demos — one in Kiro, one in GitHub Copilot — bookend practical coverage of how an agent gets access, what it should be allowed to touch, how far it can run unattended, and how to interrogate the infrastructure changes it produces. The judgment moves with you when the tools change.
**This learning path is actively in production. More content will be added to this path as it gets published and becomes available in the library. To view the full list of content to be included in this Path, click the "About this path" tab below.**
Content in this path
Applied Judgment
Where judgment does the work. You'll diagnose an AI-authored deployment that failed a governance control and close the gap that let it through, weigh what carries over when your team changes tools, and see how the way a request is framed determines what an agent gives you back. Start with the Practitioner courses — the hands-on lab assumes the access and boundary decisions covered there.
Try this learning path for free
What You'll Learn
- Give a coding agent working access to a cloud account without handing it more than the task requires
- Set the standing context, automation limits, and run constraints that match an agent's work to the blast radius of the task
- Interrogate what an agent produces — infrastructure changes, summaries, and the requests behind them — and decide what to accept, repair, or reject
- \--- Practitioner ---\
- 1. What AI Changes in Cloud Development \
- 2. Demo: Building a Cloud Change With Kiro \
- 3. Granting Coding Agents Access to Cloud Environments \
- 4. Controlling What an Agent Can Do in Your Cloud Environment \
- \
- -- Applied Judgment ---\
- 5. Remediate an AI-Authored Deployment That Failed Governance \
- 6. Working Across Two Agentic Environments \
- 7. Demo: Specifying a Cloud Change With Copilot
- You should already be using an AI coding assistant in real development work, and be comfortable reviewing generated code, tests, and configuration before it ships. Practical AWS familiarity matters here — particularly IAM and infrastructure as code — because this path is about agents acting on live cloud resources rather than on a local repository. AI-Assisted Cloud Development Workflows is a useful companion if you want the general workflow foundations first, but it is not required. This is not an introduction to cloud fundamentals, prompting, or agentic AI.