# Kiro Agentic development environment for developers to ship engineering work with AI agents. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## The oldest architecture in computing DevFeed: [The oldest architecture in computing]() Original publisher: [Read original article]() Author: werner@allthingsdistributed.com (Dr. Werner Vogels) Published: 2026-09-08T14:00:00Z Content type: opinion Language: en Sources: [All Things Distributed]() Topics: [Kiro](), [Artificial Intelligence](), [GPU](), [Open Source]() Tags: [agents](), [ai](), [gpu](), [kiro](), [memory](), [open-source](), [posts](), [research]() ### AI overview The article argues that AI may automate some work and change job roles, but people can remain relevant by adapting and learning to use new tools. It describes Kiro Crew, an open-source agent workspace used for research, schedule monitoring, cron-job management, and meeting preparation, with particular attention to how its independent agents manage memory and improve over time. The discussion connects these ideas to biological intelligence, including the energy efficiency of the human brain compared with a GPU and research on cortical columns. ### Source excerpt A GPU burns 700 watts and hundreds of thousands of tries to learn Pong. A human brain does it on 20 watts in a handful of attempts. So what can the oldest architecture in computing teach us about where agents and memory are headed? ## Advancing price-performance for developers with GPT-5.6 in Kiro DevFeed: [Advancing price-performance for developers with GPT-5.6 in Kiro]() Original publisher: [Read original article]() Published: 2026-08-24T12:00:00Z Content type: news Language: en Sources: [OpenAI News]() Topics: [Kiro](), [AI Development](), [Artificial Intelligence](), [OpenAI](), [Amazon Web Services](), [coding](), [Software Engineering]() Tags: [ai](), [ai-coding](), [aws](), [building](), [code](), [coding](), [developers](), [development](), [engineering](), [gpt](), [kiro](), [openai](), [product](), [software-development](), [spec-driven-development](), [testing]() ### AI overview GPT-5.6 is now available in Kiro, bringing OpenAI's latest flagship model series to development workflows for planning, coding, review, and testing. The article highlights structured, spec-driven development, complex multi-step coding, property-based testing, and reported cost reductions on Terminal-Bench 2.1. ### Source excerpt GPT-5.6 is now available in Kiro, helping developers plan, build, review, and test software with better price-performance. ## Four Days Left to Enter the Ready, Spec, Ship Hackathon DevFeed: [Four Days Left to Enter the Ready, Spec, Ship Hackathon]() Original publisher: [Read original article]() Author: John Crickett Published: 2026-08-19T08:02:04Z Content type: opinion Language: en Sources: [Coding Challenges]() Topics: [Hackathon](), [Kiro](), [agentic-coding]() Tags: [agentic-coding](), [build](), [coding](), [hackathon](), [kiro](), [project]() ### AI overview A reminder that four days remain to enter the Ready, Spec, Ship Hackathon. Participants may enter individually or in teams of up to three, submit multiple projects, and receive free Kiro credits if their entries are verified. The article also describes the $9,600 prize pool and submission deadline. ### Source excerpt What will you build and could you win a prize? ## Ready, Spec, Ship Hackathon Announces $9,600 Prize Pool and Kiro Credits DevFeed: [Ready, Spec, Ship Hackathon Announces $9,600 Prize Pool and Kiro Credits]() Original publisher: [Read original article]() Author: John Crickett Published: 2026-08-04T15:03:54Z Content type: article Language: en Sources: [Coding Challenges]() Topics: [Hackathon](), [Kiro](), [agentic-coding]() Tags: [agentic](), [agentic-coding](), [coding](), [hackathon](), [kiro]() ### AI overview An announcement for the Ready, Spec, Ship Hackathon, sponsored by Kiro. Participants may enter alone or in teams of up to three, submit multiple projects, and receive Kiro credits for verified entries; submissions close on 23 August. ### Source excerpt Try Kiro for free and win prizes! ## Introducing MCP server for Registry of Open Data on AWS DevFeed: [Introducing MCP server for Registry of Open Data on AWS]() Original publisher: [Read original article]() Author: Guyu Ye Published: 2026-07-07T20:12:39Z Content type: article Language: en Sources: [AWS Open Source Blog]() Topics: [MCP Server](), [Model Context Protocol](), [datasets](), [Amazon Web Services](), [Open Source](), [Claude Code](), [Kiro](), [Artificial Intelligence]() Tags: [ai](), [ai-assistants](), [aws](), [claude-code](), [datasets](), [kiro](), [mcp-server](), [model-context-protocol](), [model-context-protocol-mcp](), [open-source]() ### AI overview AWS introduces an open-source Model Context Protocol server for the Registry of Open Data on AWS. It lets compatible AI assistants search datasets, inspect metadata, explore bucket contents, and sample files, helping researchers evaluate data through a conversational workflow. ### Source excerpt Today, we are launching an open source Model Context Protocol (MCP) server that brings AI-powered dataset discovery to Registry of Open Data on AWS (RODA). As of today, RODA hosts over 1,100 high-value datasets from more than 400 organizations, spanning satellite imagery, life sciences, climate, geospatial, and more. Ask a research question in Kiro, Claude [...] ## Securing the AI coding ecosystem: Chainguard and the AI tools developers use DevFeed: [Securing the AI coding ecosystem: Chainguard and the AI tools developers use]() Original publisher: [Read original article]() Published: 2026-06-24T00:00:00Z Content type: opinion Language: en Sources: [Chainguard: Unchained]() Topics: [chainguard](), [Kiro](), [AI Development](), [cursor](), [Security](), [Containers](), [Open Source]() Tags: [ai](), [ai-agents](), [ai-coding](), [aws-kiro](), [chainguard](), [chainguard-ai-tools](), [chainguard-libraries](), [containers](), [cursor](), [developers](), [kiro](), [open-source](), [secure-by-default]() ### AI overview Chainguard argues that AI coding tools such as Kiro and Cursor need trusted sources for dependencies and container images. The article describes Chainguard Containers, Libraries, and a Kiro plugin intended to move projects from public registries to hardened supply-chain components. ### Source excerpt Chainguard brings secure-by-default containers and libraries to AI coding tools like Kiro and Cursor, making trusted open source the default. ## The Trends #10: Amazon now requires senior approval for AI-assisted code from junior and mid-level engineers DevFeed: [The Trends #10: Amazon now requires senior approval for AI-assisted code from junior and mid-level engineers]() Original publisher: [Read original article]() Author: Dr Milan Milanović Published: 2026-04-09T15:02:37Z Content type: article Language: en Sources: [Tech World With Milan Newsletter]() Topics: [amazon](), [Kiro](), [AI Agent](), [agentic-coding](), [Amazon Web Services](), [Claude](), [Claude Code](), [Cloud](), [cursor](), [debug](), [Resilience]() Tags: [agent](), [agentic](), [agentic-coding](), [ai](), [ai-agent](), [amazon](), [aws](), [claude-code](), [cloud](), [cursor](), [kiro](), [outage](), [permissions](), [production](), [resilience](), [review]() ### AI overview A technology trends newsletter examines Amazon's requirement for senior approval of AI-assisted code from junior and mid-level engineers after production outages involving AI coding tools. It also previews discussions of cloud resilience, AI and mathematics, Claude Code tool selection, LLM debugging behavior, and Anthropic's research on junior developers using AI. ### Source excerpt The Trends filter tracks tech trends: what moved, why it matters, and what to watch next. ## Spec Driven Development isn't Waterfall DevFeed: [Spec Driven Development isn't Waterfall]() Original publisher: [Read original article]() Author: Marc Brooker Published: 2026-04-09T00:00:00Z Content type: opinion Language: en Sources: [Marc Brooker's Blog](), [Marc Brooker's Blog]() Topics: [Spec Driven Development](), [Agile](), [Kiro](), [Software Engineering](), [Artificial Intelligence]() Tags: [agile](), [ai](), [blog](), [development](), [engineering](), [software-development](), [spec-driven-development](), [writing]() ### AI overview The article argues that spec-driven development is not a return to waterfall development. It presents specifications as explicit, versioned, living artifacts that evolve through user feedback and iterative development, with implementation derived from changing requirements and design choices. In this view, AI can accelerate the iteration cycle without making the process rigid or top-down. ### Source excerpt Spec Driven Development isn't Waterfall Write down what you mean. After spending a few months writing (e.g. on the Kiro Blog), and speaking (e.g. Real Python Podcast, SE Radio) about spec-driven development, I've noticed a common misconception: spec driven development is a return to a waterfall style of software development. Specification driven development (in Kiro, for example) isn't about pulling designs up-front, it's about pulling designs up. Making specifications explicit, versioned, living artifacts that the implementation of the software flows from, rather than static artifacts. This distinction is important, because software development (like all complex product development and engineering tasks) is a fundamentally iterative process. It is extremely rare for a software project to know all of the requirements up-front. It's much more common for one of the goals of the development process being to discover requirements, most frequently through engaging users in the cycle of feedback. This is a point that's missed in strict waterfall software development processes, and missed in critiques (like Dijkstra's) of natural language specification (as I have written about before). The Agile movement is often presented as a high-minded set of ideas, but I think it's more accurate to see it as a reflection of a simple fact: as software became more complex, and filled more roles in society, top-down approaches to design simply no longer work. From the Agile Manifesto: Customer collaboration over contract negotiation Responding to change over following a plan These are simple reflections of reality. Software specifications are complex, dynamically changing, internally conflicting, and invariably incomplete. In specification driven development, the specification is the thing being iterated on, rather than the implementation. The iteration cycle is the same as before, but potentially much quicker because of the accelerating effect of AI. So if specifications aren't up-front ## Migrating an 11-Year-Old Blog from Jekyll to Astro with Kiro DevFeed: [Migrating an 11-Year-Old Blog from Jekyll to Astro with Kiro]() Original publisher: [Read original article]() Published: 2026-03-17T00:00:00Z Content type: opinion Language: en Sources: [Alex Korbonits]() Topics: [migration](), [Astro](), [Jekyll](), [Kiro](), [Claude](), [Artificial Intelligence](), [ide]() Tags: [ai](), [astro](), [blog](), [claude](), [commands](), [ide](), [jekyll](), [kiro](), [migration]() ### AI overview The author describes migrating an 11-year-old blog from Jekyll to Astro in one evening with help from Kiro and Claude. Kiro read the existing Jekyll files, generated Astro components, fixed build errors, and iterated on the redesign. ### Source excerpt A year ago this would have taken a week. How I migrated an 11-year-old Jekyll blog to Astro in one evening with two toddlers in the house. ## Apollo Skills: Teaching AI Agents How to Use Apollo and GraphQL DevFeed: [Apollo Skills: Teaching AI Agents How to Use Apollo and GraphQL]() Original publisher: [Read original article]() Author: Dale Seo Published: 2026-02-03T12:00:35Z Content type: article Language: en Sources: [Apollo Blog]() Topics: [GraphQL](), [AI Agent](), [apollo-client](), [apollo-server](), [cursor](), [GitHub Copilot](), [Kiro](), [Structured-data](), [Tooling](), [Open Source]() Tags: [ai-agent](), [ai-agents](), [apollo](), [apollo-client](), [apollo-mcp-server](), [claude-code](), [copilot](), [cursor](), [graphql](), [open-source](), [schema-design](), [tooling]() ### AI overview Apollo describes Apollo Skills, an open-source artifact designed to give AI agents persistent guidance on Apollo and GraphQL practices. The article explains that agents often repeat outdated or suboptimal patterns and says the skills cover Apollo Client, Apollo Server, Connectors, schema design, and operations. The skills work with Claude Code, Cursor, and GitHub Copilot. ### Source excerpt Apollo Skills teaches AI agents to write production-quality GraphQL. Covers Apollo Client, Apollo Server, Connectors, schema design, and operations. Install: npx skills add apollographql/skills. Works with Claude Code, Cursor, Copilot. Open source at github.com/apollographql/skills ## Just Launched: Neon Is Now a Kiro Power DevFeed: [Just Launched: Neon Is Now a Kiro Power]() Original publisher: [Read original article]() Author: Carlota Soto Published: 2025-12-03T17:52:39Z Content type: article Language: en Sources: [Blog -- Neon Docs]() Topics: [Kiro](), [AI Development](), [ide](), [Model Context Protocol (MCP)](), [Spec Driven Development](), [backend-development](), [Deployment]() Tags: [agentic-ai-development](), [ai-development](), [backend-development](), [deployment](), [ide](), [kiro](), [mcp](), [product](), [spec-driven-development]() ### AI overview The article announces Neon as an early launch partner for Kiro powers. It describes a Neon power that lets developers deploy Postgres databases, create production-like branches, run migrations and tests in isolated environments, and revisit past states from within the IDE. It also explains how Kiro powers provide domain-specific tools and knowledge through MCP servers, steering files, and hooks. ### Source excerpt Kiro just announced powers at re:Invent, a new way for developers to access a curated set of tools (each packaged with domain knowledge and best practices) directly from the IDE. Neon is one of the first launch partners, alongside companies like Figma, Stripe, Supabase, Postman,... ## LLMs as Parts of Systems DevFeed: [LLMs as Parts of Systems]() Original publisher: [Read original article]() Author: Marc Brooker Published: 2025-08-12T00:00:00Z Content type: opinion Language: en Sources: [Marc Brooker's Blog](), [Marc Brooker's Blog]() Topics: [Large Language Model](), [systems](), [AI Development](), [Automated reasoning](), [Artificial Intelligence](), [Kiro](), [Amazon Bedrock]() Tags: [ai](), [ai-agent](), [amazon-bedrock](), [automated-reasoning](), [kiro](), [llms](), [reasoning](), [systems]() ### AI overview The article argues that LLMs are most powerful when combined with other system components, such as code interpreters, databases, browsers, algorithms, and SMT solvers. These combinations can solve problems that LLMs alone cannot and can deliver substantially better speed and cost efficiency. Amazon Bedrock's Automated Reasoning Checks illustrate this approach by using LLMs to extract rules and facts, then applying an SMT solver to verify logical consistency. ### Source excerpt LLMs as Parts of Systems Towers of Hanoi is a boring game, anyway. Over on the Kiro blog, I wrote a post about Kiro and the future of AI spec-driven software development, looking at where I think the space of AI-agent-powered development tools is going. In that post, I made a bit of cheeky oblique reference to a topic I think is super important. I asked Kiro to build a Towers of Hanoi game. It's an oblique reference to Apple's The Illusion of Thinking paper, and the discourse that followed it. The question of whether LLMs can scalably play Towers of Hanoi is an interesting theoretically and scientifically, but not the most important question. The more important one is can systems built with LLMs play these games?. By picking me Towers of Hanoi in that other post, I was pointing out that the answer is clearly yes. And has been for several LLM generations. As a system builder, I'm much more interested in what systems of LLMs and tools can do together. LLMs and code interpreters. LLMs and databases. LLMs and browsers. LLMs and SMT solvers. These systems can do things, today, that LLMs alone simply can't, and will never be able to do. More importantly, they can do things today orders of magnitude more cheaply and quickly than LLMs can, even in the case where they can do the same things. You know, this kind of thing: > Generate a python snippet that counts the number of rs in a string. def count_rs(input_string): return input_string.lower().count('r') Trivial? Yes. But I've now created a system that that can solve problems that this LLM can't. A better LLM can, but at about six orders of magnitude higher cost per example. Systems, fundamentally, are more than the sum of their components. A good system can do things that no component can do alone. The trivial example is trivial, but you can imagine how that power could extend to being able to use decades of progress in algorithms. And not only count, but much more powerful things like SMT solvers, or ILP approximation, or