AWS Kiro: 5 Key Features To Amazon’s New AI Coding Tool

‘Kiro is all-new, and it’s going to change how developers work,’ says AWS CEO Matt Garman. Here are the five key features in AWS Kiro that partners need to know.

Amazon Web Services’ new Kiro developer coding tool helps users write code with help from AI and is “going to change how developers work,” said CEO Matt Garman.

“AI has changed how quickly we can write code, but there’s still a gap between generating a quick prototype and shipping quality software,” said AWS CEO Garman in a LinkedIn post. “That’s why I’m thrilled to introduce Kiro, an agentic IDE that gets developers from prototype to production with the structure that production-ready code requires.”

AWS’ Kiro is a new agentic IDE (integrated development environment) program that helps customers deliver code from concept to production through a simplified developer experience for working with AI agents. An IDE is a software application that helps programmers develop software code efficiently.

“Kiro’s strength is getting those prototypes into production systems with features such as specs and hooks,” said Nikhil Swaminathan, product lead for the AWS Agentic AI Developer group.

Here are five key features in Kiro’s innovation that every channel partner, customer and developer should know about.

‘It Understands What You’re Trying To Build;’ Kiro Specs

Garman said Kiro “understands what you’re actually trying to build” when developers are writing code.

“Kiro introduces spec-driven development that lets you communicate your intent through natural language and diagrams. Instead of endless prompt tweaking, you can clearly express what you need, and Kiro delivers better results with fewer iterations,” he said.

Kiro specs are artifacts that prove useful any time users need to think through a feature in-depth, refactor work that needs up-front planning, or when users want to understand the behavior of systems.

‘Handles All The Production-Readiness Work Automatically;’ Kiro Hooks

Kiro has capabilities that “handle all the production-readiness work automatically,” which is a key feature for AI developers, Garman said.

“All those things that separate prototype code from production code—documentation, tests, performance optimization—Kiro’s intelligent agent hooks handle these tasks in the background while you focus on core functionality,” he said.

Kiro hooks act like an experienced developer catching things users miss or completing boilerplate tasks in the background as they work. These event-driven automations trigger an agent to execute a task in the background when users save, create, delete files or on a manual trigger.

Anthropic AI Models, MCP Support

Beyond specs and hooks, Kiro includes features customers expect from an AI code editor, including Model Context Protocol (MCP) support for connecting specialized tools, steering rules to guide AI behavior across projects, and agentic chat for ad-hoc coding tasks with file, URL and Doc’s context providers.

The program leverages AI models from Amazon-backed AI startup superstar Anthropic, but alternative AI models will soon be compatible.

“Kiro is built on Code OSS, so you can keep your VS Code settings and Open VSX- compatible plugins while working with our IDE,” said AWS’ Swaminathan. “You get the full AI coding experience, plus the fundamentals needed for production.”

‘Fits Into Your Existing Workflow’

Kiro doesn’t have to be a big implementation—in fact, it “fits into your existing workflow” regardless of what a coder is trying to achieve, Garman said.

“Whether you’re a chat-based developer or prefer working with structured specifications, Kiro’s purpose-built interface adapts to your style while keeping you firmly in control,” he said.

“Kiro keeps everything you love about rapid AI development while automatically handling the critical engineering work so you can focus on building features that matter instead of handling repetitive work,” Garman added.