Using Spec-Driven Development for Production Workflows - Erik Hanchett, AWS

AI Engineer · Intermediate ·☁️ DevOps & Cloud ·2w ago

About this lesson

AI coding assistants are great at completing small tasks or features. However, what do you do when you are working with more complex code bases, and you need to build in-depth features that need upfront planning? This talk explores spec-driven development as a solution to this problem. I'll show you how modern AI coding assistants (like Kiro) can help break down complex tasks into three distinct phases. We'll look at the real-world tradeoffs of this approach, and most importantly and how you can use it in your own projects right away. Speakers: - Erik Hanchett (Amazon Web Services): Erik Hanchett is a Senior Developer Advocate at AWS who teaches developers how to build with modern web, AI, and the cloud. X/Twitter: https://x.com/erikch LinkedIn: https://www.linkedin.com/in/erikhanchett/ GitHub: https://github.com/erikch

Original Description

AI coding assistants are great at completing small tasks or features. However, what do you do when you are working with more complex code bases, and you need to build in-depth features that need upfront planning? This talk explores spec-driven development as a solution to this problem. I'll show you how modern AI coding assistants (like Kiro) can help break down complex tasks into three distinct phases. We'll look at the real-world tradeoffs of this approach, and most importantly and how you can use it in your own projects right away. Speakers: - Erik Hanchett (Amazon Web Services): Erik Hanchett is a Senior Developer Advocate at AWS who teaches developers how to build with modern web, AI, and the cloud. X/Twitter: https://x.com/erikch LinkedIn: https://www.linkedin.com/in/erikhanchett/ GitHub: https://github.com/erikch
Watch on YouTube ↗ (saves to browser)
Sign in to unlock AI tutor explanation · ⚡30

Related Reads

📰
I Vibe-Coded a Feature Into Production. Cleanup Cost More Than Writing It
Learn how vibe-coding a feature can lead to costly cleanup and how to avoid it in the future
Medium · DevOps
📰
The Outage Ended. Then RestartSec Synced 400 Services Into One Thundering Herd
Learn how to avoid synchronized restarts that can take down a database after an outage, and why it matters for system reliability
Medium · Programming
📰
The Outage Ended. Then RestartSec Synced 400 Services Into One Thundering Herd
Learn how to avoid synchronized restarts that can cause secondary outages after an initial recovery, and why it matters for maintaining system stability
Medium · DevOps
📰
Python Celery Beat Ran Every Scheduled Job Twice After Our RedBeat Migration
Learn how a typo in a Redis lock key caused Celery Beat to run every scheduled job twice after a RedBeat migration and how to avoid similar issues
Medium · Programming
Up next
AWS, Azure, GCP: The One Thing Every Business Gets Wrong
AI Daily
Watch →