Draft:Kiro

• Comment: Also - this page will require a disambiguation because Kiro is an existing page. Veggiegalaxy (talk) 23:57, 28 April 2026 (UTC)

• Comment: Likely notable, but needs work before acceptance: tone needs work WP:NPOV, WP:PROMO. This draft currently relies heavily on primary sources. The prose also reads as LLM-generated in places. Veggiegalaxy (talk) 18:58, 28 April 2026 (UTC)

---

Kiro
Developer	Amazon Web Services
Release	July 14, 2025 (2025-07-14) (public preview) November 17, 2025 (2025-11-17) (general availability)
Operating system	Microsoft Windows, macOS, Linux
Type	Integrated development environment
License	Proprietary
Website	kiro.dev

Kiro (pronounced keer-oh) is a proprietary integrated development environment (IDE) and command-line interface (CLI) developed by Amazon Web Services (AWS). It was released in public preview on July 14, 2025, and reached general availability on November 17, 2025. Kiro is an agentic, AI-powered IDE built around a methodology called spec-driven development, which is designed to guide software developers from concept to production-ready code through structured planning documents, automated background agents, and persistent project context. It is built on Code OSS, the open-source foundation of Visual Studio Code.

Background

Motivation

Kiro was introduced as an AI-assisted development environment focused on "spec-driven development," which its creators presented as a response to limitations associated with "vibe coding." In launch materials and early coverage, Kiro was presented as addressing cases where prompt-driven coding can leave software harder to document, review, and maintain in larger or production-oriented projects, where requirements can remain unclear, decisions undocumented, and system design harder to understand over time.

In the launch post, Nikhil Swaminathan, Kiro's product lead, and Deepak Singh, AWS Vice President of Developer Experience and Agents, stated that Kiro was intended to improve design alignment, requirements clarity, review rigor, and long-term maintainability in AI-assisted software development.

Early coverage described Kiro as aiming to bridge rapid AI prototyping and production-ready software. GeekWire highlighted the company's tagline "from vibe coding to viable code."

David Yanacek, Senior Principal Engineer and lead advisor on the Agentic AI team at AWS, described the core design intent in a February 2026 interview with Software Engineering Daily: "Spec-Driven Development makes it much easier for the coding agent to make forward progress without making backward progress. It provides the coding agent with the context it needs to build software in an ongoing way."

Announcement and launch

Kiro entered public preview on July 14, 2025, several days ahead of the AWS Summit in New York City, which took place on July 16, 2025. In a post on X (formerly Twitter), Amazon CEO Andy Jassy said Kiro "has a chance to transform how developers build software," and pointed to spec-driven development, intelligent agent hooks, and a purpose-built interface for developer workflows.

Early coverage contrasted Kiro with Amazon Q Developer, describing Q Developer as focused on code completion and chat-based assistance, while Kiro was presented as a standalone IDE built around more autonomous agent workflows. DevClass reported that AWS developer advocate Nathan Peck said Kiro was intended to have a "unique identity outside AWS" to appeal to developers using other platforms. Kiro does not require an AWS account; users can sign in with Google, GitHub, AWS Builder ID, or AWS IAM Identity Center.

During the preview period, Kiro handled more than 300 million requests and processed trillions of tokens as developers explored its capabilities. Over 250,000 developers used Kiro in the first three months, according to figures disclosed by Amazon at the time of general availability.

Kiro reached general availability on November 17, 2025. The general-availability release added property-based testing, checkpointing, multi-root workspace support, the Kiro CLI, and enterprise billing.

GeekWire subsequently described Kiro's general availability launch as a "surprise indie hit," noting that its soft launch and word-of-mouth growth ahead of the official launch was unusual for an AWS product.

Technical foundation

Code OSS base

Kiro is built on Code OSS, the MIT-licensed open-source core of Visual Studio Code, and is compatible with Open VSX registry plugins. This makes it one of several AI-focused IDEs in a growing market of VS Code forks, alongside Cursor, Windsurf, Trae, PearAI, and Void. Because it uses Open VSX rather than Microsoft's proprietary extension marketplace, some Microsoft-exclusive extensions such as the official C# extension are not available in Kiro, which has been noted as a limitation for .NET developers.

AI models

Kiro uses AI models developed by Anthropic, primarily members of the Claude family. As of April 2026, supported models include Claude Sonnet 4.6 and Claude Opus 4.6, both of which support a 1 million token context window and are generally available on Pro, Pro+, and Power tiers. Kiro has also added experimental support for third-party open-weight models, including MiniMax M2.5 (with a 200K context window and 0.25x credit multiplier) and GLM-5, a model suited for large-codebase migrations and cross-file reasoning. All models can be selected from the Kiro model selector inside both the IDE and CLI.

Enterprise administrators can restrict which models are available to their organization, which is particularly relevant for data residency requirements where models using global cross-region inference may need to be excluded until regional inference becomes generally available.

Language support

Kiro supports a broad range of programming languages, including Python, Java, JavaScript, TypeScript, C#, Go, Rust, PHP, Ruby, Kotlin, C, C++, shell scripting, SQL, Scala, JSON, YAML, and HCL, among others.

Core IDE features

Spec-driven development

Spec-driven development is Kiro's primary differentiating feature. Rather than generating code immediately in response to a natural language prompt, Kiro first produces a set of structured planning documents, collectively called a spec, before writing any code. A spec consists of three markdown files:

• requirements.md — A requirements document written using EARS notation (Easy Approach to Requirements Syntax), a method for writing unambiguous textual requirements originally developed at Rolls-Royce for safety-critical aerospace systems. Requirements are expressed as user stories with detailed acceptance criteria covering edge cases.
• design.md — A system design and architecture document that records technology stack selections, component interactions, data flows, and architectural decisions made to fulfill the requirements.
• tasks.md — A dependency-ordered implementation checklist with concrete tasks that AI agents execute sequentially, including optional comprehensive tests.

These documents serve as a durable source of truth for both human developers and AI agents. Analysts have identified Kiro as the only major AI coding tool as of 2026 that produces an auditable trail from requirement to implementation, making it particularly valuable for teams in regulated industries that require traceability.

Amit Patel, an engineer on the Kiro team, wrote in Built In that the spec approach "requires us to think through requirements up front, consider edge cases and design for maintainability, all while using AI to execute the complex implementation details." Patel documented a case in which the Kiro team used Kiro itself to build a real-time notification feature that would typically take two weeks of development; using spec-driven development, the feature was delivered in two days.

Spec types

As of version 0.10 (February 2026), Kiro supports two distinct spec types:

• Feature Specs — Available in two variants:
  • Requirements-First: The standard workflow, where the developer describes a feature in natural language and Kiro generates EARS-notation requirements, followed by a design document and task list.
  • Design-First: Introduced in version 0.10 for situations where the developer begins with a technical architecture, pseudocode, or system diagram. Kiro derives requirements from the design rather than the other way around, which is useful when non-functional constraints or an existing design must be ported.
• Bugfix Specs — Also introduced in version 0.10, this workflow guides the developer through structured root cause analysis, fix design, and regression prevention. The result is a bugfix.md document capturing current behavior, expected behavior, and guardrails for the agent before any code is modified.

Agent modes

Kiro offers two modes for controlling how autonomously the AI agent operates, which can be toggled at any time from the chat interface:

• Autopilot mode is the default setting. The agent operates autonomously, making multiple changes across the codebase without requiring approval for each action. Developers can review a comprehensive diff of all changes through a "View all changes" option. Recommended for well-understood tasks such as adding tests, aligning documentation, or generating boilerplate.
• Supervised mode requires the agent to pause after each turn that involves file edits, presenting changes as individual hunks (as of version 0.10) so developers can review and approve each change before it is applied. Recommended for critical components such as authentication systems and infrastructure code.

Both modes work in both vibe chat and spec chat sessions.

Agentic chat (Vibe mode)

In addition to its structured spec-driven workflow, Kiro includes a free-form conversational coding mode known as vibe mode or agentic chat, intended for quick, ad-hoc coding tasks where the full spec workflow would be disproportionate. This mode supports multimodal inputs including code files, images, URLs, and terminal output. As of early 2026, users can also attach documents directly to chat messages in formats including PDF, CSV, DOCX, XLSX, HTML, TXT, and Markdown, with up to five documents per message.

Hooks

Kiro Hooks are event-driven automations that trigger background agent tasks in response to developer actions. Hooks can be configured to fire on events such as saving a file, creating a new file, modifying an API endpoint, or making a commit to a repository. As of version 0.10, hooks can also trigger on spec task events. Common use cases include automatically generating unit tests when source files are modified, refreshing documentation when API routes change, enforcing naming conventions on file creation, and running lint or security scans on specific file paths. Kiro also supports manually triggered hooks using the userTriggered type.

Steering files

Developers can define persistent steering files, stored as markdown files in a .kiro/steering/ directory, that encode project-wide behavioral guidelines for the AI agent. Steering files persist across sessions and can capture preferred tech stack, code style conventions, architectural patterns, security requirements, or framework-specific rules. The agent applies these rules consistently without the developer needing to re-specify them in each conversation.

Checkpointing

Kiro supports checkpointing, which allows developers to revert the workspace to a previous conversation state at any time. This enables developers to undo AI agent changes at the conversation level rather than line by line, and return the filesystem to a prior state.

Property-based testing

Kiro includes property-based testing (PBT) support, introduced at general availability. Unlike standard unit tests, property-based tests run hundreds of times with randomly generated inputs to detect edge cases that specific, manually chosen test values would not reveal. Kiro generates property-based tests from the acceptance criteria defined in specification documents, using them as verification evidence for spec requirements.

Model Context Protocol (MCP) support

Kiro includes native support for the Model Context Protocol (MCP), allowing the agent to connect to external tools and data sources such as documentation servers, API clients, database interfaces, and cloud platform integrations. As of version 0.10, MCP servers can also surface prompts, templates, and elicitation support directly in the Kiro chat interface.

Kiro Powers

Kiro Powers are first-party and third-party extensions that augment the core Kiro agent with purpose-built context and tooling for specific workflows. Powers are installed directly from within the Kiro IDE or web interface without requiring manual MCP server configuration, and provide agents with only the tools and context relevant to a given task. Powers launched at AWS re:Invent 2025 with integrations for Figma (design integration) and Netlify (hosting and deployment). A subsequent Power released in February 2026 added AWS IAM Policy Autopilot, enabling developers to generate baseline IAM policies from within the IDE without leaving their coding workflow.

Kiro CLI

Launched at general availability in November 2025, the Kiro CLI brings Kiro's agentic capabilities to the terminal. It supports agent modes, MCP servers, steering files, and custom agents. As of CLI version 2.0 (early 2026), the CLI added native Windows 11 support and headless mode, enabling non-interactive use in CI/CD pipelines and automation scripts via a KIRO_API_KEY environment variable.

The CLI supports the Agent Client Protocol (ACP), an open standard that allows Kiro to function as an agent within ACP-compatible editors including JetBrains IDEs and Zed, extending Kiro's spec-driven capabilities beyond its own IDE interface.

A built-in Plan Agent, accessible via Shift+Tab or the /plan command, gathers structured requirements through interactive questions, researches the codebase in read-only mode, and produces a detailed implementation plan before handing off to the execution agent.

Autonomous agent

At AWS re:Invent 2025, Amazon announced the Kiro Autonomous Agent as part of a new class of AI systems AWS termed "Frontier Agents," which are autonomous agents capable of operating independently for extended periods across multiple tasks and repositories. The Autonomous Agent was made available in preview to Kiro Pro, Pro+, and Power subscribers.

Unlike standard agentic coding sessions that reset when closed, the Kiro Autonomous Agent maintains persistent context across sessions, repositories, and pull requests. It learns from developer code review feedback and applies those preferences to future work automatically. Key capabilities include:

• Asynchronous task execution in isolated sandbox environments
• Multi-repository coordination, letting a single task trigger coordinated pull requests across multiple codebases
• Persistent cross-session memory of team conventions and past decisions
• Automatic spawning of specialized sub-agents for components of a complex task

AWS CEO Matt Garman announced at re:Invent 2025 that Amazon is standardizing its own internal software development teams on Kiro, describing it as "the agentic development environment for structured AI coding."

Availability and pricing

Platforms

Kiro is available as a desktop application for macOS, Windows, and Linux. The Kiro CLI is available on macOS and Linux, with native Windows 11 support added in CLI version 2.0. A GovCloud deployment is also available for US government and regulated-industry customers, with inference processed through Amazon Bedrock in AWS GovCloud (US-West). GovCloud authentication is handled exclusively via AWS IAM Identity Center. Individual login methods such as Google, GitHub, and AWS Builder ID are not available in GovCloud regions.

Pricing tiers

Kiro was offered free of charge during its public preview period (July–November 2025). Following general availability, pricing is credit-based, with overage charged at $0.04 per credit on paid plans. As of early 2026, the public pricing tiers are:

Tier	Monthly Price	Credits per month	Notes
Free	$0	50	Standard models ( sonnet 4.5 & Haiku ) & open-weight models only
Pro	$20	1,000	Includes Claude Sonnet and Opus 4.6; content not used for model training
Pro+	$40	2,000	Autonomous Agent access
Power	$200	10,000	Enterprise-scale usage; Autonomous Agent access

Credits do not roll over between billing periods. New users receive a 30-day trial bundle with 500 bonus credits. Eligible university students receive one full year of free access with 1,000 credits per month. A startup program is available for companies that have raised up to Series B funding, providing AWS credits toward Kiro Pro+. Content from paid-tier users is not used to train AI models. Free-tier users may opt out in settings. Telemetry is disabled by default for enterprise users.

Reception

Press coverage

Upon its launch, Kiro received coverage from technology publications including CNBC, The Register, GeekWire, DevClass, TechTarget, TechRadar, and Visual Studio Magazine. The Register characterized the product's approach as a counterpoint to "vibe coding" tools, noting that its spec-driven methodology "will help to mitigate the sometimes-disorderly outcomes from AI-driven coding."

TechTarget analyst Jason Andersen of Moor Insights & Strategy highlighted spec-driven development and limited AWS lock-in as Kiro's two most distinctive qualities.

Constellation Research analyst Holger Mueller commented that the product reflects a fundamental change in the field, observing that "software development and coding are not the same anymore in the era of genAI."

Developer community analysis published in late 2025 identified Kiro, Cursor, and Windsurf as the three dominant forces in the agentic IDE market, each representing a distinct philosophy: Cursor optimizing for speed and iterative developer flow, Windsurf targeting enterprise monorepos, and Kiro targeting structured, spec-first, auditable development.

RedMonk analyst Kate Holterhoff identified Kiro as an industry benchmark for transparent usage reporting in a December 2025 analysis of developer tooling trends.

Spec-driven development as a methodology received dedicated editorial coverage in InformationWeek and was the subject of a March 2026 episode of the Software Engineering Radio podcast featuring Marc Brooker, VP and Distinguished Engineer for Agentic AI at AWS. Turing Post, covering the topic in March 2026, cited Brooker as saying SDD "provides the coding agent with the context it needs to build software in an ongoing way."

A comparative review covering seven major AI coding tools published in March 2026 noted that Kiro is the only tool that "creates an auditable trail from requirement to implementation," making it specifically suited for teams in regulated industries.

Criticism and limitations

Reviewers and analysts noted several limitations at launch and during the early GA period. DevClass observed that Kiro's default Autopilot mode, in which the agent can make code changes autonomously, may concern developers unfamiliar with its behavior, and noted that the Open VSX registry's exclusion of Microsoft's C# extension was a friction point for .NET developers.

Credit consumption rates by operation type were criticized as inconsistently published, making cost forecasting difficult for teams at scale. AWS acknowledged early bugs that caused unexpected credit drainage. Analysts at Augment Code noted that Kiro lacked a public trust center and comprehensive audit documentation as of early 2026, creating challenges for independent compliance evaluation without direct AWS sales engagement.

Enterprise adoption

At AWS re:Invent 2025, Delta Air Lines presented a detailed case study of its enterprise deployment of Kiro. The airline reported a 1,948% increase in Amazon Q Developer adoption within six months, driven by a trust-building rollout through internal developer champions. Delta reported a 94% developer satisfaction score from pilot users and successfully delivered its first intelligent developer portal using Kiro, with developers shifting focus from writing implementation code to reviewing and directing architecture.

Rackspace Technology used Kiro to complete what it estimated as 52 weeks of software modernization work in three weeks, according to figures disclosed by Amazon executives at the time of general availability. Following general availability, AWS disclosed that enterprises including Rackspace, SmugMug, and Netsmart had adopted Kiro's spec-driven development approach across engineering teams, with reported efficiency increases of up to 90% in some cases.

Comparison with related tools

Kiro occupies a distinct position in the AI-assisted development market. Unlike most competitors, which prioritize speed of code generation and conversational iteration, Kiro enforces upfront structured planning before generating any code. Builder.io described the contrast: "Cursor optimizes for fast iteration inside a familiar editor; Kiro optimizes for teams that need every change to be justified, reproducible, and easy to audit months later."

Kiro is the only major agentic IDE as of 2026 to offer a GovCloud deployment, giving it a distinct advantage in US government-regulated environments and industries such as defense and healthcare that require FedRAMP-level compliance.

AWS also maintains Amazon Q Developer, a separate AI coding assistant that offers inline suggestions and chat-based assistance integrated into existing IDEs such as VS Code and JetBrains. Kiro is positioned as a complementary product to Q Developer, targeting developers who want full agentic project management rather than inline assistance.

See also

• Amazon Web Services
• Visual Studio Code
• GitHub Copilot
• Amazon Q
• Model Context Protocol
• Vibe coding
• EARS notation

References

Category:Amazon Web Services Category:Integrated development environments Category:Software development tools Category:Artificial intelligence applications Category:2025 software Category:Command-line software