Spec-Driven Development with Kiro empowers development teams to build software faster using AI-assisted, agentic development workflows.

This course provides the practical knowledge to implement spec-driven development, configure AI agent behavior, extend capabilities with Model Context Protocol (MCP), and automate development workflows using Kiro.

  • Why get trained: Learn how to create Feature and Bugfix Specs, control AI agents with steering files and execution modes, integrate external tools through MCP servers, automate workflows with agent hooks, and build reusable agent skills for your team.
  • Why it matters: AI agents are transforming the software development lifecycle by accelerating coding, testing, and collaboration. Organizations need developers who can effectively supervise AI agents while maintaining governance, consistency, and code quality.
  • Who should attend: Software Developers, Software Engineers, Technical Leads, DevOps Engineers, and development teams adopting AI-assisted and agentic software development practices.

Gain the skills to design, automate, and govern AI-powered software development workflows with Kiro. HRD Corp Claimable.

Overview

Spec-Driven Development with Kiro is a two-day, instructor-led training course designed for developers, software engineers, and technical leads adopting AI-assisted, agentic development practices. The course teaches the principles of agentic coding and how to apply them using Kiro, the agentic IDE for software development.

Participants learn to plan and implement features through Kiro Feature Specs and Bugfix Specs, control agent behavior with steering files and execution modes, and extend agent capabilities with Model Context Protocol (MCP) servers and Kiro Powers. The course also covers automating workflows with agent hooks, packaging reusable expertise with agent skills and custom subagents, and configuring projects for team collaboration and enterprise governance. Hands on labs are interleaved with module content throughout each day.

On Day 1, learners progressively build a weather application using each Kiro capability as it is taught. On Day 2, learners deploy, extend, and team-enable a pre-built micro-blogging application.

Skills Covered

In this course, you learn to do the following:

  • 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 (Autopilot and Supervised), and custom subagents
  • Extend agent capabilities using Model Context Protocol (MCP) 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

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

  • 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

Course Curriculum

Day 1

Module 1: 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

Module 2: 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

Module 3: 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

Module 4: Bugfix Specs

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

Day 1 Lab: Kiro Spec-Driven Development Foundations

Day 2

Module 5: 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

Module 6: 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

Module 7: 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

Module 8: Team Collaboration and Enterprise Governance

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

Day 2 Lab: Extending and Automating with Kiro

Dates & Locations

Let’s make it work for you

Can’t find a date that fits? Need to train your whole team? Looking for a discount?
Speak to one of our learning experts today.

x Clear all selections

September 10, 2026 - September 11, 2026

Location: Kuala Lumpur
Modal: ILT
Availability: TBC
RM 3600

September 10, 2026 - September 11, 2026

Location: Online
Modal: VILT
Availability: TBC
RM 3600

October 8, 2026 - October 9, 2026

Location: Kuala Lumpur
Modal: ILT
Availability: TBC
RM 3600

October 8, 2026 - October 9, 2026

Location: Online
Modal: VILT
Availability: TBC
RM 3600

November 19, 2026 - November 20, 2026

Location: Kuala Lumpur
Modal: ILT
Availability: TBC
RM 3600

November 19, 2026 - November 20, 2026

Location: Online
Modal: VILT
Availability: TBC
RM 3600

December 10, 2026 - December 11, 2026

Location: Kuala Lumpur
Modal: ILT
Availability: TBC
RM 3600

December 10, 2026 - December 11, 2026

Location: Online
Modal: VILT
Availability: TBC
RM 3600
Trainocate exam and cert

Exam & Certification

There is no exam directly associated with this course. However, AWS offers an extensive portfolio of industry-recognized certifications that can help you stand out as a tech professional in 2026 and beyond. Achieving AWS credentials is one of the most effective ways to validate your skills and accelerate your career.

With our expert-led training, you’ll be prepared to:

  • Master in-demand capabilities across Cloud, Data & AI, and Cybersecurity — areas driving global digital transformation.
  • Prove your expertise with a globally respected credential recognized by employers worldwide.
  • Advance your career by enhancing your credibility, increasing your earning potential, and opening doors to new opportunities.

Explore our top AWS Certifications for 2026 and start building the skills that matter today.

Training & Certification Guide

Frequently Asked Questions

Spec-driven development uses structured requirements, designs, and implementation tasks to guide AI-assisted software development before code is written.

Instead of prompting an AI coding assistant to immediately generate code, Kiro Specs establish what needs to be built, how it should be designed, and which tasks need to be completed. The AWS-SDDK course teaches this structured approach through Feature Specs and Bugfix Specs, alongside practical agentic development workflows.

Kiro’s spec workflow centers on three core stages: Requirements → Design → Tasks, creating a traceable path from an initial idea to implementation.

Pro Tip: If you already use AI coding assistants, compare how you currently prompt for complex features with Kiro’s structured spec workflow. This will help you identify where clearer requirements and design decisions could reduce rework.

AWS-SDDK: Spec-Driven Development with Kiro is designed for software professionals who want to integrate AI agents into structured, production-oriented development workflows, in addition to the following audiences:

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

Learners should already be proficient in at least one programming language and have working Git knowledge, basic familiarity with RESTful APIs and cloud application concepts, and foundational understanding of generative AI concepts such as LLMs, tokens, and inference.

Pro Tip: This is an intermediate course, so strengthen your Git, API, and programming fundamentals before attending if you have limited development experience.

You will learn to design, control, extend, automate, and govern AI-assisted software development workflows using Kiro.

Learners develop practical skills across the AI-assisted software development lifecycle, including:

  • Creating Feature and Bugfix Specs
  • Building requirements, designs, and implementation tasks
  • Controlling agent behaviour with steering files
  • Using Autopilot and Supervised execution modes
  • Integrating external capabilities through MCP servers
  • Creating and using Kiro Powers
  • Automating development activities with agent hooks
  • Building reusable agent skills and custom subagents
  • Applying team and enterprise governance controls

The course is hands-on. On Day 1, learners progressively build a weather application; on Day 2, they deploy, extend, and team-enable a pre-built micro-blogging application.

Pro Tip: Pay particular attention to steering, specs, and reusable agent capabilities. These skills help you move from simply using AI to establishing repeatable AI-assisted engineering practices across a development team.

Vibe coding typically moves quickly from natural-language prompts to generated code, while spec-driven development establishes requirements, design, and implementation tasks first.

Kiro is designed to bring greater structure to complex AI-assisted development. Specs formalize important decisions before implementation and provide clearer tracking and accountability throughout development. AWS describes this approach as particularly useful when traditional AI coding assistants struggle with complex project requirements.

This does not mean every development task requires a detailed specification. Kiro supports different approaches depending on the complexity and certainty of the task.

Pro Tip: Use quick conversational AI coding for small, well-understood tasks, but consider a spec-driven workflow when requirements, dependencies, architecture decisions, or acceptance criteria become more complex.

Kiro provides controls that help teams standardize how AI agents access tools, follow project conventions, select models, and execute development tasks.

AWS-SDDK moves beyond individual AI coding productivity into team and enterprise implementation. The course covers shared .kiro workspace configuration, steering-file organization, spec review conventions, MCP registry allowlisting, model governance, extension registries, and web tools.

This is particularly relevant when organizations want the productivity benefits of agentic development without allowing every developer or AI agent to operate independently of engineering standards and governance.

Pro Tip: If your organization is already experimenting with AI coding tools, use the governance section to think about which development standards should be enforced consistently across your entire team.

Malaysia’s growing AI economy is increasing demand for professionals who can move beyond basic AI use and apply AI to real development and engineering workflows.

AWS reported in 2025 that AI adoption among Malaysian businesses increased 35% year-on-year, with approximately 2.4 million businesses using AI. However, 73% remained focused on basic AI applications, highlighting the gap between adopting AI tools and using AI for more advanced innovation.

The talent requirement is equally significant. An AWS case study on its collaboration with MDEC reports that 81% of employers have difficulty finding AI talent for current roles.

MDEC also reported that AI-related digital investments accounted for 8,328 projected jobs in Q3 2025, representing 38% of total projected employment generated by approved Malaysia Digital investments during the quarter.

For software developers and engineers, this strengthens the case for progressing from basic generative AI usage toward structured skills in agentic development, AI-assisted software engineering, automation, and governance.

Pro Tip: Treat AI-assisted development as an extension of your existing software engineering skills. Programming, Git, APIs, testing, architecture, and code quality remain important when AI agents become part of your development workflow.

Speak to a Training Consultant

All courses are HRD Claimable.
Get in touch with our team via the form or WhatsApp us on +6011-5119 6631

Preferred mode of training
Checkboxes