“Kiro gives me the time and freedom to try new things.” Andrew is a Principal Engineer at SmugMug and Flickr. Cloud architecture is his world, but coding had shrunk to the occasional bug fix squeezed between everything else. Kiro gave him his time back: ∙ Exploring tools and integrations he never had bandwidth for ∙ Learning frontend and niche domains from scratch ∙ Spec’ing out ideas with Kiro before writing a single line of code For a senior engineer who wants to keep building, not just maintaining, that’s everything. Watch the full story 👆
Kiro
Technology, Information and Internet
Agentic AI development from prototype to production.
About us
Kiro helps you do your best work by bringing structure to AI coding with spec-driven development.
- Website
-
https://kiro.dev
External link for Kiro
- Industry
- Technology, Information and Internet
- Company size
- 10,001+ employees
Updates
-
Claude Opus 4.7 is now rolling out in Kiro IDE and CLI. 👻 Opus 4.7 is Anthropic's latest and most capable Opus model, a direct upgrade from Opus 4.6 with stronger agentic coding. Initially available to a subset of Kiro Pro, Pro+, and Power customers, broader availability coming soon. 🚀 Get a full breakdown here:👉 http://spr.ly/6048B6fglr
-
-
As AI agents become more capable, effective guidance requires knowing when to use your steering docs, reusable skills, or delegate to sub agents. Join us as we explore best practices, when to use each, and how to best leverage sub agents without going overboard.
How are you using steering, sub agents and skills?
www.linkedin.com
-
How are you using steering, subagents and skills? 👀 As AI agents become more capable, effective guidance requires knowing when to use your steering docs, reusable skills, or delegate to subagents. Join us as we explore best practices, when to use each, and how to best leverage subagents without going overboard. Listen here 👉http://spr.ly/6040B64MvA
-
-
Kiro CLI 2.0 is here with less friction and more control. ∙ Automate your CI/CD pipelines with headless mode. Invoke the CLI programmatically with the right context and tools, and execute long-standing prompts like troubleshooting production failures or generating and publishing pull requests. ∙ Windows support. We are so excited to announce that all the terminal capabilities you love are now natively available on Windows. ∙ The new UX is now the default experience. Thank you for all your feedback, it helped us shape the new experience and add some new updates like a new sub agent experience and a task list, so you can easily keep track of what the agent is doing. Learn more here 👉 http://spr.ly/6044B62e28
-
Here’s how we proved the value of Kiro to our business 👇 The engineering teams at Codex have been leveraging AI assisted development for years, from Github Copilot through to Cursor. Cursor was a genuine step change for us. But there was one challenge we couldn’t overcome. The impact wasn’t consistent. Some experienced engineers saw their velocity increase significantly. Some less experienced engineers did too, but not to the same degree. The uplift varied across the team. And to be fair, this is exactly what you’d expect. It’s fundamentally a governance and ways of working problem. So we addressed it. We introduced clear AI development principles, built supporting packages, and pushed a requirements driven approach. But governance is difficult to enforce consistently. When we first explored Kiro, we saw something different. Here was a tool that could enforce that structure, rather than relying on individuals to apply it. So we tested it. We had a real problem that had been sitting unresolved for weeks. We gave it to one of our most junior engineers, equipped with Kiro, and let them run with it. 4 days on requirements and design. 1 day to build. Problem solved. The output passed internal checks across security and infrastructure, signed off by our Head of Cloud and Head of Data. That was the moment it clicked. The value wasn’t just in speeding up our best engineers. It was in lifting the baseline across the entire team! That’s what made the decision to move to Kiro a simple one for team Codex. #Codex #Kiro #AWS #Amazon #AgenticDevelopment #AI
-
-
I spent March teaching an AI coding agent how to build AI agents. How? I built a Power for Kiro and used it to build more AI agents. In Kiro powers are essentially a specialised context layer you can load into Kiro on-demand. Think of it like a skill for Claude Code, but deeper, and with MCP tool integration baked in. Why Kiro specifically? Because Kiro is built around two things I believe matter in AI-assisted engineering: specs and tests. I don’t believe AI replaces software engineers, it amplifies them. You cannot build, deploy, and maintain a real software system by winging it with short, vague prompts. You need: - Detailed context so the agent understands the problem. - Clear acceptance criteria so it knows when it's done. - Well-designed guardrails so it doesn't drift or do things it shouldn’t. Kiro's spec-driven development handles the context. Its property-driven testing provides some of the guardrails. Powers tie it together by providing additional context that guides the agent toward best practices and the right tools. So what did I build? I built a Kiro Power to guide Kiro through building AI Agents with Pydantic AI and Logfire. You can find it and the other Powers available for Kiro on the Powers page here: https://kiro.dev/powers/ Like many Kiro powers it’s a public GitHub repo, so if you have suggestions for improvements feel free to add an issue or raise a PR.
-
-
AI makes things faster, but it can also add additional work if you aren't using the right tools with the right context. 👀 That was Arshad’s reality. Every feature, every bug fix, every new build came with the same overhead — document everything upfront, fight the hallucinations, clean up the mess. Then he started using Kiro: ∙ Describes what he wants to ship, Kiro builds the spec ∙ Tasks are created and sequenced automatically ∙ Tests run, and nothing moves forward until they pass Watch how he builds now. 🎥
-
Join us live as we build a feature from scratch, fully utilizing the latest TUI experience in the CLI. We'll show you all the latest tips and tricks, explore how to best leverage subagents and skills into your workflows, and answer any questions you may have.
Have you tried the new Kiro CLI TUI?
www.linkedin.com
-
📣 Going live in 30 minutes. Darko Mesaroš is back with another session as we build a feature from scratch, fully utilizing the latest TUI experience in the CLI. We'll show you all the latest tips and tricks, explore how to best leverage subagents and skills into your workflows, and answer any questions you may have. Listen here and join the conversation 👉 http://spr.ly/6047B6QreN
-