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

Spec-Driven Development with AI

Spec-Driven Development with AI

These slides accompany my academic seminar, "Spec-Driven Development with AI," delivered at the Holon Institute of Technology (HIT) in Israel.

As artificial intelligence becomes increasingly capable of generating software, the traditional software development process is undergoing a fundamental transformation. The primary challenge is gradually shifting from writing code to clearly defining requirements, designing systems, maintaining control over AI-generated implementations, and orchestrating AI agents.

This seminar explores Spec-Driven Development (SDD) as an emerging approach to AI-assisted software engineering. Rather than relying on loosely structured prompts, as commonly happens with vibe coding, SDD places specifications at the center of the development process. These specifications capture human intent and guide implementation, testing, architectural decisions, and ongoing maintenance.

The presentation uses Kiro IDE, Amazon's agentic development environment, to demonstrate how Spec-Driven Development can be implemented in practice.

Topics covered in the slides include:

From Code-First to Spec-Driven Development: Understanding why AI-generated code changes the fundamental challenges of software engineering.

The Limitations of Vibe Coding: Exploring the challenges of traceability, reproducibility, maintainability, and preserving human intent.

Specifications as the Foundation: Using structured requirements, technical designs, and implementation tasks to guide AI-assisted development.

Kiro IDE and Its Ecosystem: Introducing Kiro IDE and its tools for agentic software development.

Steering Documents and Development Workflows: Providing AI agents with project context, development guidelines, and architectural constraints.

Agent Hooks: Automating recurring development activities, including security reviews, testing, code formatting, and documentation.

Subagents and Agent Orchestration: Delegating work to specialized agents and exploring common orchestration patterns.

Parallel Task Execution: Understanding how development tasks can be executed concurrently while respecting dependencies.

Kiro Workflows: Coordinating multiple AI agents through sequential steps, parallel execution, and iterative loops.

Cloud-Based AI Agents: Exploring autonomous agents that can execute long-running tasks independently of a developer's local machine.

Persistent Orchestration and Observability: Understanding how autonomous agent activity can be coordinated, monitored, and controlled.

Best Practices: Maintaining specifications, steering documents, and development processes that support reliable AI-assisted software engineering.

Beyond the technical aspects, the seminar examines the evolving role of software developers. As AI agents take on a growing share of implementation work, developers increasingly become responsible for defining intent, designing architectures, establishing constraints, reviewing results, and orchestrating intelligent systems.

After more than 25 years of teaching advanced software development topics in academia, delivering this seminar was a particularly exciting experience. For the first time in my academic teaching career, I felt that I was introducing a topic at the very frontier of software engineering, while the underlying technologies and practices were still rapidly evolving.

The central message is simple: The future of software engineering is not just about generating code faster. It is about developing better ways to translate human intent into reliable, maintainable software through specifications and intelligent AI orchestration.

life michael

October 23, 2026

Transcript

55 slides
  1. 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
  2. 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
  3. 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
  4. The End of Code First Development The large-scale code generation

    shifts the bottleneck from code generation to understanding and control.
  5. The Vibe-Coding Problem The prompts cannot be managed or traced.

    When the systems evolve, intent is lost, and the behavior becomes difficult to explain or reproduce.
  6. 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.
  7. Spec-Driven Development AI Tools Created with ChatGPT. The prompt: Create

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

    and is based on VS Code. Kiro is an Agentic IDE.
  9. 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, and Kiro Crew for persistent, long-running autonomous tasks.
  10. 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
  11. 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
  12. Agent Hooks There are two ways to create new hooks.

    Either you create them manually or you ask Kiro chatbot to create them for you.
  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. Common Orchestration Patterns There are common scenarios and common patterns

    when developing software applications with the help of AI agents: Reviewer Loop One agent produces work, and another verifies it. Event-Driven Agents External events trigger agents to perform specific tasks.
  16. Common Orchestration Patterns Coordinator & Workers One agent divides the

    goal and combines the results. Sequential Pipeline Each agent (specialist) passes its output to the next agent. Parallel Specialists Several (specialist) agents that simultaneously do their work.
  17. 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.
  18. 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.
  19. What is Kiro Workflow? Was created using AI based on

    the diagram at https://kiro.dev/blog/introducing-workflows
  20. 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
  21. 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.
  22. 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
  23. Common Use Cases • Processing Data • Generating Recurring Reports

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

    agent activity, tool calls, approvals, and results as the work progresses.
  25. 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.
  26. 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.
  27. 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.
  28. 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.
  29. The Right Level of Orchestration Effective orchestration is becoming more

    complex. Parallelism does not guarantee better results.
  30. 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.
  31. 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.
  32. 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.
  33. 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