Dan Kiuna

“They wrote plan.md. Now have the agent misinterpret half the tasks. Good. Have it burn tokens implementing the wrong thing. Now have it pass the tests anyway. They’re testing it. Figuring out they built the wrong thing. More tokens refactoring. Nice. But now there’s an undefined state they totally missed. Their users won’t. Cancelations coming in better than expected. Let them spend two weeks figuring out requirements analysis would have caught all of this.”

AI coding gets really interesting when the bottleneck shifts from writing code to coordinating teams, requirements, testing, and production systems. That's what @kirodotdev solves. And it's why thousands of startups applied for Kiro credits last round. We've opened the program again. Up to a year of Kiro Pro+ for pre-seed to Series A startups. Applications open now. kiro.dev/blog/bringing-…

Three updates to Kiro specs today. Faster to start, faster to finish, and smarter before you build.

Go for it Lakers!

What are you gonna ship this weekend??

We’re excited to introduce the Kiro sign-up bonus: First-time upgrade to any paid plan gets you $20 worth of usage credits. That is 1000 worth of credits, double the current 500. Get started today 👉spr.ly/6011BBmN5H

Come join the Kiro Ambassadors program!

We have now fully rolled out Opus 4.7 to all paid Kiro users. Happy coding!

🚀 Today we're announcing the first managed end-to-end payment capabilities for autonomous agents in preview in Amazon Bedrock AgentCore. Built with Coinbase and Stripe, so developers can focus on what their agents do, not on how they pay. The agentic economy is just getting started. Here's a first look at AgentCore payments ➡️ aws.amazon.com/blogs/machine-…

Are you automating your deployment pipelines? 👀 Kiro CLI's headless mode lets run Kiro non-interactively from CI/CD workflows, shell scripts, or any automated environment. No terminal babysitting required. Join this weeks livestream, we'll be live coding through key use cases: automating code generation, wiring Kiro into a CI pipeline, and scripting multi-step dev tasks. Listen here 👉spr.ly/6019BBdF2W

Reminder 📣 Kiro Startup Credits Program is still open! If you’re an early-stage to Series A founder, part of a dev team, or a solo dev building something real, you can apply for up to 1 year of free Kiro Pro+ credits. Applications are reviewed on a rolling basis. If it’s on your radar, now’s the time. Apply today 👉spr.ly/6018BBdPT6

We're doing it again.

When we open-sourced Strands Agents SDK last year, we wanted to bring builders an easier way to build and run AI agents with just a few lines of code. Since then, the Strands Python SDK has been downloaded more than 25 million times, with more developers building with it every day. Now, TypeScript developers can enjoy the same experience, with full type safety, custom tools, and the ability to run agents in both Node.js and the browser. Strands is an agent harness SDK that goes beyond the core agent loop. It gives developers the default tools and control layers they need to build agents that can execute code, work with files, manage their own context, and stay on task as they scale. TypeScript 1.0 ships these harness capabilities built into the SDK. Default tools for shell execution, file editing, HTTP access, and structured notes, alongside customizable hooks and plugins that give developers control at every point in the agent lifecycle. All you need is a few lines of code to get started. We're building this in the open and contributions are welcome. Whether it's a bug fix, a new feature, or a cool example, we'd love to see what you build. Join us on GitHub and let us know what you think. strandsagents.com/blog/strands-a…

our team has been recording an amazing series of videos geared towards developers who are new to the cloud. if you're a vibe coder wanting to learn the fundamentals, a student ramping up on the fundamentals, etc. they're basically free high quality courses!

52K tokens → 2K tokens. Same query, same result. From @TheNewStack, Morgan Willis breaks down how intent-based tool design in @StrandsAgents slashed AI agent token usage by 96%. The takeaway: design tools around outcomes, not API endpoints. 🔗 go.aws/4tEfivT

Would love to see what your headless setup looks like!

The Quick desktop app is here, and it’s compelling. Connects to your email, calendar, Slack, local files, and several other apps to flag important communications, retrieve and summarize info, make recommendations, send communications, and create agents that do work you used to have to do yourself. Gets smarter and more personalized the more you use it. Been using it a lot recently and is changing how I work. It’s allowing me to use applications like my inbox more like an archive, and Quick as my personalized, prioritized, productivity hub that can multi-task various needs. Still early days, and a lot more coming, but excited for folks to start using it to make the undifferentiated work so much less complicated. aboutamazon.com/news/aws/amazo…

RT @SwamiSivasubram: Amazon Quick changes how you work. Today we're releasing it in desktop mode—a proactive AI assistant that connects to…

Kiro CLI has a headless mode — and your pipelines will thank you. Drop it in your CI/CD pipeline, pass a prompt with --no-interactive, and Kiro executes it end-to-end. Try it out today👉 spr.ly/6011BBztPN

Kiro x ElevenLabs hackathon is live 🛠️ This weekend is the perfect time to build. Write specs, let Kiro's AI agent implement them, and ship a voice-powered app before submissions close Wednesday. Prize pool: $10k cash + credits. What are you building? spr.ly/6015B6AMBx