AWS Kiro has rebranded itself as an “agentic development environment,” moving away from its previous identity as an integrated development environment (IDE) to better assist in software development from prototype to production. The transformation includes the introduction of Kiro Crew bots, which act as named, long-running agents that manage specific tasks while maintaining their own memories and sessions. This evolution aims to enhance developer workflows, as Kiro Crew operates within a shared workspace, allowing developers to efficiently manage multiple agents without the need for duplicated context.
AWS: AWS is the cloud computing division of Amazon, providing infrastructure and services for building and running applications at scale. In this development, AWS is extending its AI-focused tools by expanding Kiro with new bot orchestration capabilities to address developer needs in managing complex agentic workflows.
Kiro: Kiro is AWS’s AI-powered development environment available across desktop, command-line, web, mobile, and personal agent formats. It has evolved from an IDE to an agentic development platform that incorporates users from Amazon Q Developer and now includes persistent agent infrastructure to support long-running tasks.
Kiro Crew: Kiro Crew serves as the persistent, open-source development workspace within Kiro that underpins its web, IDE, and CLI interfaces. It now hosts Kiro Crew bots, which are named, long-running software agents with individual memory and sessions designed to handle specific ongoing responsibilities like intake, build monitoring, code review, and release processes.
Agent Management: Kiro Crew bots allow developers to structure agentic work with named, persistent agents that maintain separate memories and sessions while sharing the same workspace, tools, and codebase.
Product Evolution: AWS has reoriented Kiro from an IDE toward an agentic development environment to better support prototype-to-production software building through multiple agent interfaces.
AI tools built by Emerald Force
Built and supported by Emerald Force.
You might also like
- Few-Shot Prompting: Learning from a Few Examples
- Inference Cost: The Compute Behind Model Outputs
- How to Benchmark Tools Before Buying: A Practical Guide
- Can AI Remove Backgrounds? A Proven Vision Use Case
- How AI Clusters Customer Feedback and Detects Sentiment
- AI Center of Excellence: Standards and Adoption
- Where AI Coding Excels: Tests, Refactors, Scaffolds
- AI Can Fake Documents-Why Verification Is Essential
- Can AI Identify You From a Photo? Key Risks
AI Models Explained: From Inputs to Outputs