Spec-Driven Development with Kiro

This 2-day course introduces AI-assisted, agentic development and shows how to apply it with Kiro, the agentic IDE for software development.

The Spec-Driven Development with Kiro course teaches the principles of agentic coding and how to plan and implement features using Kiro Feature Specs and Bugfix Specs. Participants learn the three-phase spec workflow of requirements, design, and tasks, work with EARS notation, and explore correctness through property-based testing. They also learn to control agent behavior with steering files, context providers, and the Autopilot and Supervised execution modes.

On Day 2 the focus shifts to extending and scaling what the agent can do. Topics include Model Context Protocol (MCP) servers, Kiro Powers, agent hooks, agent skills, and custom subagents, as well as creating and sharing your own reusable capabilities. The course finishes with configuring projects for team collaboration and applying enterprise governance controls such as MCP registry allowlisting and model governance.

The course includes presentations, demonstrations, group exercises, and hands-on labs woven through both days. On Day 1 participants progressively build a weather application as each Kiro capability is introduced. On Day 2 they deploy, extend, and team-enable a pre-built micro-blogging application.

The course is intended for software developers and engineers, technical leads adopting AI-assisted development workflows, development teams adopting agentic coding practices, and DevOps engineers integrating AI agents into delivery pipelines. It is recommended that attendees are proficient in at least one programming language, have working knowledge of Git, understand RESTful APIs and cloud application concepts, and know the basics of generative AI such as LLMs, tokens, and inference.

← All AWS courses