Spec-Driven Development with Kiro

Overview

This two-day, instructor-led course introduces developers, software engineers, and technical leads to agentic coding practices using Kiro, an agentic IDE for software development. The course covers planning and implementing features with Kiro Feature Specs and Bugfix Specs, controlling agent behavior, extending agent capabilities, automating workflows, and configuring projects for team collaboration and enterprise governance. Learners engage in hands-on labs, demonstrations, and group exercises, building and extending applications using Kiro’s capabilities.

Prerequisites

We recommend that attendees of this course have:

• Proficiency in at least one programming language
• Working knowledge of Git version control
• Basic understanding of RESTful APIs and cloud application concepts
• Foundational knowledge of generative AI concepts (LLMs, tokens, inference)

Target audience

This course is designed for:

• Software developers and engineers
• Technical leads adopting AI-assisted development workflows
• Development teams adopting agentic coding practices
• DevOps engineers integrating AI agents into delivery pipelines

Objectives

By the end of this course, learners will be able to:

• Implement spec-driven development workflows using specifications to plan, design, and execute features and fixes
• Configure and control agent behavior using steering files, context providers, execution modes, and custom subagents
• Extend agent capabilities using Model Context Protocol servers and Kiro Powers to integrate external tools, services, and domain expertise
• Automate and scale development workflows using agent hooks, agent skills, shared steering, and custom subagents
• Build and share reusable agent capabilities by creating custom Kiro Powers, agent skills, and custom subagents for team-specific workflows
• Apply enterprise governance controls for MCP registry allowlisting, model governance, and extension management

Outline

Introduction to Agentic Development with Kiro

• The agentic coding paradigm and Kiro core capabilities
• Five principles of effective agentic development
• Kiro IDE vs Kiro CLI
• Vibe sessions, Spec sessions, and model selection

Spec-Driven Development with Feature Specs

• The three-phase spec workflow (Requirements, Design, Tasks)
• Requirements-First workflow and EARS notation
• Design-First workflow (High-Level and Low-Level Design)
• Correctness with property-based testing

Steering, Context, and Agent Control

• Steering files and foundational context
• Custom steering files and inclusion modes (always, fileMatch, manual, auto)
• Workspace and global scope
• Context providers and session management
• Autopilot and Supervised execution modes
• Trusted commands and trusted tools

Bugfix Specs

• When to use Bugfix Specs
• The bugfix analysis phase: current, expected, and unchanged behaviour
• Root cause analysis and design
• Property-based testing for regression prevention

MCP Servers and Tool Integration

• Model Context Protocol fundamentals and client-server architecture
• Configuring MCP servers at workspace and user scope
• Managing servers, tools, and auto-approve
• Using MCP tools in chat and troubleshooting

Kiro Powers

• The context overload problem and how Powers solve it
• Power directory structure (POWER.md, mcp.json, steering)
• Installing and using Powers from the IDE and kiro.dev
• Authoring and sharing custom Powers

Agent Hooks, Skills, and Custom Subagents

• Agent hooks: triggers, actions, and creation
• Agent skills: portable instruction packages with progressive disclosure
• Custom subagents: scoped tool permissions and delegation
• Skills vs Steering vs Powers

Team Collaboration and Enterprise Governance

• Shared workspace configuration through the .kiro directory
• Steering file organisation and spec review conventions for teams
• Enterprise governance: MCP registry allowlisting, model governance, extension registry, web tools

Exams and assessments

There is no certification or exam associated with this course.

Hands-on learning

• Hands-on labs are interleaved with module content throughout each day
• Learners build a weather application using Kiro capabilities on Day 1
• Learners deploy, extend, and team-enable a micro-blogging application on Day 2
• Activities include demonstrations and group exercises