Upgrade to Pro — share decks privately, control downloads, hide ads and more …

Spec-Driven Development with Kiro IDE: Building...

Sponsored · Ship Features Fearlessly Turn features on and off without deploys. Used by thousands of Ruby developers. →

Spec-Driven Development with Kiro IDE: Building AI-Aligned Software Through Living Specifications

As Artificial Intelligence becomes increasingly capable of generating code, the challenges of software development are shifting from writing code to defining requirements, managing complexity, maintaining control, and ensuring that AI-generated solutions align with human intentions.

Spec-Driven Development (SDD) introduces a structured approach in which specifications become the central source of truth, guiding AI agents throughout the software development lifecycle.

In this presentation, Haim Michael explores how Kiro IDE, Amazon's agentic development environment, supports Spec-Driven Development and enables developers to build reliable, maintainable, and AI-aligned software.

The presentation covers several key topics:

The End of Code-First Development: Understanding why AI-generated code shifts the bottleneck from implementation to specification, coordination, and verification.

The Limitations of Prompt-Driven Development: Exploring why relying on individual prompts makes it difficult to preserve intent, trace decisions, and maintain consistency.

Spec-Driven Development: Using living specifications to capture requirements, constraints, architecture, and acceptance criteria.

Kiro IDE and Its Ecosystem: Introducing Kiro IDE, CLI, Web, Mobile, and Crew.

The Development Process: Moving from steering documents and EARS-based requirements to technical design, implementation tasks, and AI-assisted execution.

Agent Hooks: Automating recurring activities such as code reviews, security checks, testing, formatting, and documentation.

Subagents and Parallel Execution: Delegating specialized tasks to AI agents and executing independent development tasks concurrently.

Kiro Workflows: Orchestrating complex, multi-step development processes using sequential tasks, parallel agents, and iterative loops.

Cloud-Based AI Agents: Enabling autonomous agents to handle long-running activities, monitoring, incident response, code reviews, and recurring tasks.

Persistent Orchestration and Observability: Using Kiro Crew to coordinate ongoing activities while maintaining visibility into agent execution, approvals, and results.

Best Practices: Keeping specifications updated, maintaining detailed steering documents, reviewing technical designs, optimizing AI capabilities through MCP servers, Skills, and Powers, and choosing the appropriate level of orchestration.

The central message is that the future of software development is not about generating more code. It is about defining intent precisely, orchestrating AI agents effectively, and maintaining control over the entire development process.

As code generation becomes increasingly inexpensive, software developers move to a higher level of abstraction, focusing on architecture, requirements, constraints, quality assurance, and coordination.

Living specifications become the foundation that keeps humans and AI agents aligned, enabling software systems to evolve without losing their original intent.

About the Speaker

Haim Michael is the Founder and CEO of Zindell Technologies, a software architect, author, university lecturer, and technology trainer with more than 25 years of programming experience. He is also a Kiro Ambassador, AWS Community Builder, and Oracle ACE Associate.

Website: https://blog.lifemichael.com
LinkedIn: https://linkedin.com/in/lifemichael
Kiro IDE: https://kiro.dev
Blog Post: https://lifemichael.com/en/full-stack-conf-sofia-2026-exploring-spec-driven-development-and-ai-agent-orchestration-with-kiro-ide/

life michael

October 30, 2026

Transcript

49 slides
  1. Spec-Driven Development with Kiro IDE Building AI-Aligned Software Through Living

    Specifications Haim Michael Founder & CEO @ Zindell Technologies www.zindell.com | blog.lifemichael.com life michael
  2. My name is Haim Michael. I live in Tel Aviv,

    and I am the CEO & founder of Zindell Technologies, Ltd. My passion lies in teaching and lifelong learning. I have been into programming since my childhood. I have extensive experience with Java (30+ yrs), JavaScript (30+ yrs), C++ (30+ yrs), C# (20+ yrs), TypeScript (12+ yrs), Python (15+ yrs), PHP (20+ yrs), Scala (16+ yrs), and Kotlin (12+ yrs). Teaching advanced computer science topics at the university. blog.lifemichael.com Tel-Aviv, Israel
  3. XtremeJ XtremePython XtremeAI xtremej.dev xtremepython.dev meetup.com/lifemichael xtremeai.dev More Than 18000

    Followers https://linkedin.com/in/lifemichael Kiro Ambassador XtremeJS xtremejs.dev More Than 2800 Video Clips youtube.com/lifemichael blog.lifemichael.com Conferences, Meetups & Community
  4. Jacado - More Than 200 Games for Mobile Telephones –

    Years 2001- 2008 Zindell - Building AI Aligned Companies – Years 2026 - … nana.events prompo.ai zindrex.com ngager.pro jacado.games blog.lifemichael.com Passion to Build
  5. The End of Code First Development The large-scale code generation

    shifts the bottleneck from code generation to understanding and control.
  6. The Prompt Driven Problem The prompts cannot be managed or

    traced. When the systems evolve, intent is lost, and the behavior becomes difficult to explain or reproduce.
  7. Specs as the Missing Layer Specs capture what the system

    must do, what it must never do, and under which conditions behavior changes. They translate human intent into a form that humans and machines can review, version, validate, and share. Both by humans and by machines.
  8. Spec-Driven Development AI Tools Created with ChatGPT. The prompt: Create

    a table that compares all the AI tools that support Spec-Driven Development.
  9. The Kiro IDE The Kiro IDE was developed by Amazon

    and is based on VS Code. Kiro is an Agentic IDE.
  10. The Kiro Tools Family Kiro enables agentic development across multiple

    environments: Kiro IDE for visual development, Kiro CLI for terminal-based workflows, Kiro Mobile for managing agent sessions on the go, Kiro Web for the web browser, and Kiro Crew for persistent, long-running autonomous tasks.
  11. The Development Process Steering Specs Documents Mermaid Diagrams Execution Requirements

    Design Phase List of Tasks EARS Easy Approach to Requirements Syntax The tasks are performed by the agents
  12. What are Agent Hooks? Agent hooks are automated triggers that

    execute predefined agent prompts or shell commands when specific events occur in your IDE. Rather than manually asking for routine tasks to be performed, hooks set up automated responses to events such as: Linting Updating Other Files Create Tests Static Analysis Tools Code Formatting Updating Related Files Generating Documentation
  13. What are Subagents? The subagents allow Kiro to run multiple

    tasks parallelly or to delegate specific tasks to subagents that specialize in those tasks.
  14. Executing Subagents Manually We can launch subagents manually by instructing

    Kiro to do so via a prompt such as ”run subagents to do this and that...".
  15. Running Tasks in Parallel When we click "Run all Tasks"

    on a spec, Kiro analyzes the task list and figures out which tasks can run at the same time, and builds a dependency graph from the task list.
  16. What is Kiro Workflow? Kiro Workflows automate complex, multi-step tasks

    by orchestrating multiple AI agents through sequential steps, parallel execution, and iterative loops. Each agent operates in an independent session, enabling reusable workflows that run with minimal human supervision.
  17. What is Kiro Workflow? Was created using AI based on

    the diagram at https://kiro.dev/blog/introducing-workflows
  18. What is Kiro Workflow? { "name": "deliver-change", "inputs": { "task":

    "prompt", "workdir": "string" }, "steps": [ { "type": "step", ”id": "plan", "agent": "wf-planner", … }, { ... } ] } Was created using AI based on the diagram at https://kiro.dev/blog/introducing-workflows
  19. AI Agents in the Cloud Cloud-based AI agents can operate

    continuously without relying on a developer’s local machine. They can respond to events, execute longrunning tasks, collaborate with other agents, and scale dynamically while maintaining secure access to development tools and organizational resources.
  20. Common Use Cases There are various cases in which having

    AI agents on the cloud can be highly useful: • Monitoring Systems • Responding to Incidents • Reviewing Code
  21. Common Use Cases • Processing Data • Generating Recurring Reports

    • Handling Support Requests • Complex Development Tasks • Running Tests
  22. Agents Observability Agent orchestration must remain observable. Kiro Crew exposes

    agent activity, tool calls, approvals, and results as the work progresses.
  23. Update Spec First Whenever you add a new feature or

    fix a bug, start by updating the spec. The code, including the tests, should be aligned with the spec.
  24. Detailed Steering Documents When having detailed steering documents, the steps

    that follow will produce better results. By doing so, you reduce re-work, backtracking, and misalignment across humans and the AI.
  25. Technical Design When we finish with the requirements, Kiro produces

    the design artifacts: diagrams, interfaces, schemas, and API endpoints. Make sure you carefully review these documents. Introducing AI-driven changes might pose technical challenges you will need to overcome.
  26. AI Optimization Make sure to configure the relevant MCP servers

    and to install the skills and powers that will assist AI. Powers bundle MCP tools with knowledge and workflows. They activate dynamically based on context. Skills are portable instruction packages that bundle instructions, scripts, and templates, and Kiro can activate them when relevant to your task.
  27. The Right Level of Orchestration Effective orchestration is becoming more

    complex. Parallelism does not guarantee better results.
  28. Coding is Cheap AI dramatically reduces the cost of generating

    code. The real challenges now lie in defining intent, controlling execution, verifying results, and preserving knowledge over time.
  29. Specs Coordinate The Development Specs provide agents with shared requirements,

    constraints, design decisions, and acceptance criteria. They allow humans and multiple agents to work toward the same outcome.
  30. Higher Level of Abstraction Developers increasingly define goals, architecture, constraints,

    and quality standards while AI agents perform most of the coding. The developer becomes the orchestrator of software creation.
  31. Q&A nana.events Thanks for attending my talk :) nana.events WhatsApp

    +972.54.6655837 prompo.ai [email protected] https://blog.lifemichael.com prompo.ai ngager.pro life michael zindrex.com XtremeJ xtremej.dev life michael XtremeJS xtremejs.dev XtremePython xtremepython.dev XtremeAI xtremeai.dev lifemichael.com meetup.com/lifemichael Monolith vs Microservices

More Decks by life michael

Other Decks in Technology