What better way to launch into the AI segment for developer productivity than by releasing an IDE made specifically to aid with the rapid changes in software development and programming that have followed its revolution? This is what AWS did with the unveiling of its Kiro Integrated development environment, which aims to dislodge VS Code to become the code editor of choice for the AI Generation.
To paraphrase the announcement press release, Kiro’s objective is to help developers scale through the hurdle of fuzziness that comes with building software applications from prompts.
In this article, we go over this announcement and intersperse it with commentary from elsewhere on the internet about Kiro to gauge its reception.
What Is This New IDE and How’s It Different?
“I’m sure you’ve been there: prompt, prompt, prompt, and you have a working application. It’s fun and feels like magic. But getting it to production requires more. What assumptions did the model make when building it? You guided the agent throughout, but those decisions aren’t documented. Requirements are fuzzy and you can’t tell if the application meets them. You can’t quickly understand how the system is designed and how that design will affect your environment and performance. Sometimes it’s better to take a step back, think through decisions, and you’ll end up with a better application that you can easily maintain. That’s what Kiro helps you do with spec-driven development. —Kiro
As mentioned, Kiro is an AI IDE that helps developers deliver ‘from concept to production through a simplified developer experience for working with AI agents.’
Its creators envision it to be the go-to code editor for the modern way of programming and building applications, which is significantly more creative and interactive.
AWS launches Kiro IDE in preview mode.
AWS’s New AI IDE is intended to think like the modern developer who may not want to be bogged down with or understand the complete spec and structure of the app they build with coding assistants and AI agents.
That said, Kiro itself is an AI Agent too. Aside from basic coding assistant features, the editor packs two main features according to its doc:
Kiro specs: Kiro’s specs feature helps developers think through an in-depth feature and refactor work that needs upfront planning, or when you want to understand the behavior of systems. Specs were intended to guide AI agents to a better implementation of a program’s requirements.
Kiro hooks: Quoting directly from the doc, Kiro hooks act like an experienced developer catching things you miss or completing boilerplate tasks in the background as you work. These event-driven automations trigger an agent to execute a task in the background when you save, create, delete files, or on a manual trigger.
In the example code provided in the release document, Kiro is said to have the ability to unpack requirements from a single prompt like «Add a review system for products.» According to the doc, it can generate user stories for viewing, creating, filtering, and rating reviews from this single prompt.
To Kiro’s creators, developing this way with specs keeps the fun of vibe coding, but fixes some of its limitations, including that vibe coding can require too much guidance on complex tasks or when building on top of large codebases, where context can be misinterpreted.
The Thing About Vibes Or Conversational Coding
Definition:
Vibe coding is a modern approach to programming where users can express their intentions using natural language, and AI transforms those intentions into executable code. This method allows for a more creative flow in software development, reducing technical barriers and enabling users to build applications without traditional coding skills. Essentially, vibe coding involves giving an AI a programming task, which it then completes by generating code and making architectural decisions based on the user’s vague concepts. —adapted from Times of India, Arstechnica
This is because, when implementing a task with vibe coding, it’s difficult to keep track of all the decisions that were made along the way and document them for your team. By using Kiro’s specs feature, the editor works with you hand in hand to define requirements, system design, and tasks to be implemented before writing any code. According to the doc, this approach of explicitly documenting the reasoning and implementation decisions allows Kiro to implement more complex tasks in fewer shots.
AWS was criticized for trying to capitalize on “Vibe Coding”
However, among the critiques of the app, according to conversations online, is that for advanced coders, Kiro can feel a bit controlling. For developers who have fine-tuned their AI-driven workflow over the years and crave flexibility, Kiro’s structured approach, although brilliant for newer developers, can feel like it’s holding the reins too tight for those who want to steer the direction of their work.
Should You Switch?
So what’s the big picture, you may ask? Well, Kiro’s launch raises a deeper question about the future of coding, like:
- Are we ready to hand over so much of our workflow to AI?
- Will tools like this make us better architects or just lazier coders?
- Could a hybrid mode—guided for beginners, freeform for pros—be the answer?
Kiro is currently in public preview mode at kiro.dev. Although the tool’s creation is in line with AWS’s broader vision, its release may also mark a turning point in the evolution of programming customs and tools that we might look back upon in the future as the golden age of programming, just as older developers do with programming from the 80s and 90s.
Looking for help building a product idea? Reach out to us through the form below. We help businesses like yours build and deliver big ideas. See our case studies for more.
Also read: Untested Code Is Costing Enterprises Millions — and It’s About to Get Worse
