Kiro - the future of IDEs
A few weeks ago, at the NYC Summit, AWS announced the launch of Kiro – a new IDE for AI-native and agentic development. What stood out most to me was not the software itself, but the workflow. AI and its tools are changing the way we think and work, and it would only be natural that the same would be true for the tool we use to code. Kiro reflects the future of software development workflows.
Let me first walk through Kiro’s development process to highlight what sets it apart. Today, most developers who craft agents send large, complex prompts to LLMs that process and output an agent workflow. This approach can cause problems, primarily because it lacks visibility into how the agent makes decisions. LLMs make a lot of assumptions based on gaps in prompts, and it can be hard to identify. To combat this, let’s walk through Kiro’s approach, what they are calling ‘spec (specification) driven development’.
Start by describing the agent decisions or workflow you are looking to solve. Where a tool like Cursor (or any other AI coding assistant) would begin generating code immediately, Kiro takes in your description and returns a set of requirements in natural language that it thinks will meet your description. You exchange feedback on which requirements work and where adjustments are needed.
Once you’re satisfied with the requirements, Kiro will begin to build a design doc, generating technical specifications, architecture diagrams, workflows and subtasks that will be used to achieve the agent logic you described. Again, this is an iterative process. Kiro will take feedback, clarifying any assumptions that it may have made incorrectly.
Finally, task creation begins. Kiro works in autopilot mode to create the code that will characterize your agentic workflow. This can be stopped at any time, and since you iterated beforehand with requirements and specifications, Kiro can adjust without having to start over from scratch.
One of Kiro’s key functionalities is called a hook – an automation tool that performs a task based on an action done by the developer. The simplest example of this is hitting save while coding. You can use a hook based on ‘saving’ to automatically update documentation, generate a unit test based on changes in the file.
Conceptually simple, yet groundbreaking in how developers interact with AI coding assistants today. All the answers aren’t needed from the start – Kiro can help parse out the most important architecture requirements and how it will fit into a larger logic flow as you go.
A perfect use case for Kiro came out of a conversation with, of all people, my father. He recently started working at a startup called Chainguard, a container security company. Chainguard provides secure container images that are free from common vulnerabilities and exposures (CVEs). Picture this: every time a developer saves an updated file, Kiro automatically checks the code against the provided Chainguard images. This hook, designed as a security guardrail, is exactly where Kiro shines.
As I continue to work with my customers on their applications, I’m excited to see how Kiro can fit into their development flow to meet them where they are.
—
Learn more about Kiro here