147. Spec coding with Kiro
What if AWS built an IDE to rival your favorite editor? Turns out they did! In this episode of AWS Bites, we dive into Kiro, an AI centric fork of VS Code that tries to turn an empty repo and a loose idea into working software. Kiro imports your VS Code world, then guides you through requirements, design, and a clear task plan before an agent gets to work. We share what clicked, what tripped us up, and how Kiro’s spec driven approach compares to Cursor or Claude Code. We also cover status, limits, pricing, and what this could become if AWS leans in with deep cloud integration. Stick around for our take on whether you should switch or wait. 💰 SPONSOR 💰 Big shoutout to fourTheorem for powering yet another episode of AWS Bites. At fourTheorem, we believe the cloud should be simple, scalable, and cost effective, and we help teams do just that. Whether you are diving into containers, stepping into event driven architecture, scaling a global SaaS on AWS, or trying to keep cloud spend under control, our team has your back. Visit fourTheorem.com to see how we can help you build faster, better, and with more confidence using AWS cloud. 🔖 Chapters: 00:00 Intro 01:05 What is Kiro? 03:35 Example use cases for Kiro like onboarding, documentation, and greenfield development 04:07 The current status of Kiro 05:06 Kiro's spec-driven development approach 07:38 How Kiro helps you to define a specification 12:03 The value of spec-driven development and the difference between vibe and spec 13:34 A real-world example project tested with Kiro's spec workflow 15:54 The provided prompt and the generated spec 19:03 Hitting a nasty bug 22:11 Additional Kiro features like agent hooks and steering 23:56 Discussion of Kiro's pricing model 29:21 Assessment of Kiro's value proposition compared to other tools 31:15 Debate around whether AWS seems fully committed to Kiro 32:39 Recommendations on whether to migrate to Kiro from your current IDE 34:50 Opinion that the bigger opportunity for Kiro is tighter AWS ecosystem integration 37:19 Conclusion and request for feedback on trying Kiro 📚 Resources mentioned in this episode: Kiro website: https://kiro.dev/ Kiro docs on Agent Hooks: https://kiro.dev/docs/hooks/ Kiro docs on Steering: https://kiro.dev/docs/steering/ Kiro pricing plans blog: https://kiro.dev/blog/pricing-plans-a... Cargo Lambda: https://www.cargo-lambda.info/ Episode 64: how do you write Lambda functions in Rust? https://awsbites.com/64-how-do-you-wr... Kiro GitHub issue: https://github.com/kirodotdev/Kiro/is... Amazon Q developer CLI: https://github.com/aws/amazon-q-devel... You can listen to AWS Bites wherever you get your podcasts: Apple Podcasts: https://podcasts.apple.com/us/podcast... Spotify: https://open.spotify.com/show/3Lh7Pzq... Google: https://podcasts.google.com/feed/aHR0... Breaker: https://www.breaker.audio/aws-bites RSS: https://anchor.fm/s/6a3312a0/podcast/rss Do you have any AWS questions you would like us to address? Leave a comment here or connect with us on BlueSky or LinkedIn: https://bsky.app/profile/eoin.sh | / eoins https://bsky.app/profile/loige.co | / lucianomammino

148. Lambda and Java with Mark Sailes

Transforming Dev Practices with Kiro’s Spec-Driven Tools | Nikhil and Richard

#26 Vibe Engineering - agentic IDE - mysql component, live

143. Is App Runner better than Fargate?

Zig 2026: No-AI Policy, $670K Foundation, Left GitHub & Why Zig Isn’t 1.0 - Andrew Kelley Explains

AWS re:Invent 2025 - Spec-driven development with Kiro (DEV314)

KIRO For Dummies: The Complete Beginner's Guide (Install → Build → Powers)

151. Lambda Managed Instances: No Cold Starts, EC2 Pricing, New Scaling Rules

152. Exploring Lambda Durable Functions

145. We Tried Amazon DSQL So You Don’t Have To (But You Might Want To)

142. Escape from S3

Kiro Has Changed How I Build Software

The Great Bun Rewrite

Andrej Karpathy: From Vibe Coding to Agentic Engineering w/ Stephanie Zhan

China Is About To Pop The AI Bubble

DO NOT BUY: LG’s Spyware TVs, Monitors, and Wiretapping Concerns

Spec Kit: How to Build Production-Ready Apps with AI Agents

153. LLM Inference with Bedrock

Full Walkthrough: Workflow for AI Coding — Matt Pocock

Keynote: After the AI Hype – What’s Real, and What’s Next - Richard Campbell - 2026

The Rise and Fall of the AI Bubble

150. Exploring All-New ECS Managed Instances (MI) Mode

Software engineering at the tipping point

Head of Claude Code: What happens after coding is solved | Boris Cherny

We Relocated the Handwheel on Our MONSTER Lathe | Megabore Lathe Setup

