my thoughts on Kiro

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 is changing the way we think and how we work, and it would only be natural that the same would be true for the tools we use to code. Kiro is just at the start of transforming how we interact with software tools, and I want to share my thoughts.

I’ve been hearing a lot about vibe coding these days, from customers, coworkers, and friends alike (for those unfamiliar, vibe coding is a style of software development where AI agents generate the majority of the actual code, less hands-on-keyboard work for coders). As someone who does not come from a traditional software development background, Kiro is the perfect tool to add more structure to vibe coding, bringing up concerns or ideas I hadn’t considered, or helping me brainstorm how I might improve an idea before coding even begins.

Before I get into the actual workflow of the tool for those interested, I want to highlight a key feature of Kiro. A hook is an automation tool that performs a task based on an action done by the user. The simplest example of this is hitting save while coding (you can think of this similarly to saving a word document). You can create a hook based on ‘saving’ to automatically update documentation or generate a new unit test based on changes in the file. These tasks can be tedious for developers and devops teams to maintain and can slowdown deployment of production-ready code.

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 vulnerability and exposures (CVEs). Picture this: every time a developer saves a file, Kiro automatically checks the code against the provided Chainguard images for malicious code. This hook designed as a security guardrail is exactly where Kiro shines.

I do want to spend time exploring the details of Kiro’s workflow, but I’ll start by touching on how the development process of creating an AI agent works today. Most developers who craft agents send large, complex prompts to LLMs that process and output an agent workflow. This can be problematic for a lot of reasons, the main one being a lack of visibility into how the agent will be making decisions. Transparency and explainability are key concerns. LLMs make a lot of assumptions based on gaps in prompts and how it was trained, both of which can be hard to identify. To combat this, let’s walk through Kiro’s approach, what they are calling ‘spec (specification) driven development’.

1. 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 chat back and forth, giving feedback about the requirements you like, and where you want adjustments made.

2. 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.

3. 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 its output without having to start over from scratch.

Simple conceptually, but groundbreaking in terms of how a developer interacts with an AI coding assistant 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 logical flow as you go. By deep diving into details, the agent coding experience is more enterprise-grade and production ready.

As I continue to work with my customers on their applications, I’m excited to see how Kiro can support their AI development process and meet them where they are. While Kiro remains in private beta, we are eager to get more feedback on the tool, make it faster, and support more LLM models.

—

Learn more about Kiro here

WSJ’s Future of Everything Conference Recap

Earlier this summer, I had the opportunity to attend WSJ’s Future of Everything Conference, which focused on technological innovation across industries like aviation, finance, healthcare, culture, and infrastructure. While broad in scope, the core themes discussed throughout the conference centered on accessibility and democratization—largely driven by the productivity gains expected from generative AI. This technology is advancing at an unprecedented pace, with implications for both the near and long term—faster than any previous technological revolution.

The first and most AI-focused topic was enterprise infrastructure. The conference featured a co-founder of Groq and the COO of OpenAI, both optimistic about the opportunities ahead. Groq develops inference chips using a tensor streaming processor that delivers ultra-low latency and deterministic inference performance. OpenAI, in contrast, is focused on offering best-in-class LLMs through API layers that support a wide variety of use cases. While their approaches differ, both speakers predicted major implications for the labor market. Groq’s founder highlighted three key outcomes: people will become more productive, more businesses will emerge due to increased accessibility, and goods may become cheaper as production costs decline. In theory, this could even allow people to retire earlier. Predictions aside, one thing is clear: the workforce is on the brink of significant change. Increased productivity and broader access to information will empower more people to pursue new business ideas without needing initial investment.

Beyond infrastructure, healthcare was the most prominently featured industry at the conference. It’s a natural fit for AI applications focused on improving efficiency, accuracy, and outcomes—particularly in drug discovery and access to care. Innovations in clinical trials aim to make them safer and more effective. Scientists have spent decades working on treatments for diseases like cancer and other currently incurable conditions. AI has the potential to accelerate that progress, enabling more personalized care, better R&D insights, and more accurate predictions.

A final recurring theme across sessions was the democratization of technology—how platforms, transportation, and education are empowering people to do more with fewer resources. In aviation, modernization and sustainable fuels promise to make flying more accessible and climate-conscious. In fintech and cybersecurity, automation and AI are expected to drive new efficiencies. Digital platforms are also evolving toward more community-driven experiences, shaped by both content creators and active users. This shift brings new models of crowdsourced trust, content moderation, and participation. From reducing the paradox of choice on dating apps to rethinking how online opinions are verified and rewarded, companies are leaning into transparency, experimentation, and culture-first innovation.

A quote that captures the moment well:
“Progress is exponential: we tend to overestimate the short term and underestimate the long term.”

One thing is certain—change is inevitable in today’s technological and social environment. We’re only beginning to tap into AI’s potential, and there’s much more to learn about how it will reshape society, culture, and the workplace. AI will soon be embedded into nearly every aspect of technology. Embracing this shift and educating ourselves is the first step toward understanding its full impact.

Something I heard recently helped frame this rapid evolution of AI and the commoditization of knowledge: while knowledge and technology may become commoditized, agency—the human capacity to choose and act—will remain our defining trait.