← Back to all announcements
★★☆☆☆ 14/05/2026

AWS Transform introduces the agent builder toolkit Kiro power for building customized transformation agents

Partners and customers can now build and publish custom modernization agents that plug directly into AWS Transform's agentic AI platform via the Kiro marketplace.

View original announcement →

Visual Summary

graph TD A{{Agent Builder Toolkit Kiro Power}}:::announced B(AWS Transform):::compute C([Custom Agents]):::feature D([Knowledge Bases & Workflows]):::feature E((Partners & ISVs)):::external F((Customers)):::external G([Kiro Marketplace]):::feature H([Agent Discovery & Registry]):::feature E ==>|"build agents"| A F ==>|"build agents"| A A -->|"integrates with"| B A -->|"creates"| C A -->|"embeds"| D C -->|"registered in"| H H -->|"enables discovery"| B C -.->|"distributed via"| G G -.->|"shared across"| E classDef announced fill:#ff9900,stroke:#ec7211,color:#fff,font-weight:bold classDef compute fill:#e3f2fd,stroke:#1565c0,color:#1565c0 classDef storage fill:#e8f5e9,stroke:#2e7d32,color:#2e7d32 classDef feature fill:#fff3e0,stroke:#e65100,color:#e65100 classDef external fill:#f5f5f5,stroke:#616161,color:#616161

What's New

AWS has announced the general availability of the agent builder toolkit powered by Kiro, a new capability within the AWS Transform composability initiative. This toolkit enables AWS Partners, ISVs, and customers to build, share, and register custom transformation agents that integrate seamlessly with AWS Transform's agentic AI platform. The release marks a significant expansion of AWS Transform's extensibility, allowing specialized modernization logic to be packaged and distributed through the Kiro marketplace.

How It Works

  • Build: Developers use the Kiro-powered agent builder toolkit to construct custom transformation agents, embedding specialized tools, knowledge bases, and workflows tailored to specific modernization scenarios (e.g., mainframe refactoring, custom framework migrations).
  • Integrate: Custom agents connect directly with AWS Transform's existing agentic AI capabilities, including its assessment, code analysis, dependency mapping, and transformation planning engines, ensuring interoperability within the platform.
  • Share: Completed agents can be shared within internal teams or distributed across partner networks, enabling reuse and collaboration across organizations.
  • Register: Agents are registered with AWS Transform's discovery layer, making them findable and deployable by other users or partners within the ecosystem.
  • Distribute: The agent builder toolkit and finished agents are available through the Kiro marketplace, providing a centralized distribution and discovery channel.
  • Lifecycle management: The toolkit covers the full end-to-end agent lifecycle—from initial development through sharing, versioning, and production registration.

Why It's Important

  • Extensibility at scale: AWS Transform was previously limited to AWS-built agents; this toolkit opens the platform to a broad ecosystem of partner- and customer-built agents, dramatically expanding the range of supported modernization scenarios.
  • Partner differentiation: Migration and Modernization Competency Partners and ISVs can now encode their proprietary methodologies and domain expertise into agents, creating defensible, differentiated offerings on top of AWS Transform.
  • Reduced custom development overhead: Customers with unique legacy environments no longer need to build bespoke tooling from scratch; they can extend AWS Transform directly rather than maintaining parallel toolchains.
  • Ecosystem network effects: As more agents are registered and shared, the Kiro marketplace becomes a compounding resource—each new agent increases the platform's value for all participants.
  • Accelerated modernization timelines: Custom agents can automate organization-specific transformation patterns that generic agents cannot handle, reducing manual effort on complex, one-of-a-kind migrations.

How It's Different

  • Platform composability vs. monolithic tooling: Unlike traditional migration tools that offer fixed workflows, AWS Transform's composability initiative allows agents to be mixed, matched, and layered, giving teams fine-grained control over their transformation pipeline.
  • Kiro-native development: Agents are built using the Kiro IDE/power environment, which provides an AI-assisted development experience purpose-built for agentic workloads, rather than requiring generic coding frameworks.
  • First-class marketplace distribution: The Kiro marketplace provides a structured, discoverable channel for agent distribution—distinguishing it from ad-hoc script sharing or proprietary partner portals.
  • Seamless AWS Transform integration: Custom agents inherit AWS Transform's shared workspaces, natural language chat, progress tracking, and parallel execution capabilities without additional integration work.
  • Partner-grade lifecycle support: The toolkit is explicitly designed for Migration and Modernization Competency Partners, meaning it meets enterprise-grade standards for sharing, versioning, and governance—not just developer prototyping.

When to Prefer It

  • Organization-specific legacy patterns: When a customer has proprietary frameworks, internal APIs, or custom codebases that AWS Transform's standard agents do not cover out of the box.
  • Partner-led engagements: When a Migration and Modernization Competency Partner wants to deliver a repeatable, branded transformation methodology across multiple customer engagements using a single registered agent.
  • ISV product differentiation: When an ISV wants to embed its modernization tooling within the AWS Transform ecosystem rather than maintaining a standalone competing product.
  • Large-scale parallel modernization: When hundreds of applications need to be transformed simultaneously and custom automation logic is required to handle edge cases at scale.
  • Knowledge base integration: When a team has accumulated deep institutional knowledge (runbooks, transformation rules, architectural standards) that should be codified into an agent rather than applied manually each time.
  • Cross-team agent reuse: When multiple internal teams or business units need access to the same specialized transformation logic and a governed sharing mechanism is required.

Availability

  • GA Status: Generally available as of May 14, 2026.
  • Access point: Available through the Kiro marketplace; agents are registered with AWS Transform for discovery.
  • Supported workloads: Designed to complement AWS Transform's existing support for mainframe, VMware, Windows (.NET/SQL Server), and custom code modernization scenarios.
  • Eligible builders: AWS Migration and Modernization Competency Partners, ISVs, and direct customers can all build and register agents.
  • Pricing: Specific pricing details were not disclosed in the announcement; refer to the AWS Transform pricing page (aws.amazon.com/transform) for current information.
  • Regional availability: Specific supported AWS regions were not detailed in the announcement; consult the AWS Transform documentation for region-by-region availability.
  • Limitations: The announcement does not specify API quotas, agent size limits, or governance controls; further technical documentation via the AWS Transform page is recommended before production use.

Tags

Servicesaws-transformkiro
Typega-launchnew-feature
Conceptsagentic-ai
Use Casesmigrationdeveloper-tools
GeographyGlobal

AI Radar AWS

AWS AI/ML news — curated, researched, explained

An automated intelligence platform that curates, researches, and analyzes AWS AI/ML/GenAI announcements daily. Every report is backed by real research — the system reads linked blog posts and documentation to provide accurate, in-depth analysis.

How Each Report Is Generated

  1. Collection — Daily monitoring of the AWS "What's New" RSS feed
  2. Filtering — AI-powered relevance detection for AI/ML/GenAI topics
  3. Taxonomy Tagging — LLM-based classification across 6 dimensions
  4. Importance Scoring — Point-based system with tag bonuses (1-5 stars)
  5. Research Phase — Follows links to blog posts and documentation
  6. Report Generation — Claude Sonnet produces structured 6-section analysis
  7. Visual Summary — Claude Opus generates Mermaid diagrams for key items
  8. Publishing — Static website rebuilt and deployed via CloudFront

Features

  • Faceted filtering by service, type, concept, and more
  • Multi-dimensional taxonomy with 80+ tags across 6 dimensions
  • Geographic availability badges (Global, APJ, EMEA, AMER) with filtering
  • Timeline visualization of announcement volume
  • PDF export for offline reading
  • Mermaid visual summaries for key announcements
  • Daily automated updates — no manual curation
What makes this different: Each report involves a dedicated research phase where the system reads linked blog posts and AWS documentation pages. This produces analysis that goes beyond the original announcement text.

Technology

Built with Python, AWS Lambda, Amazon Bedrock (Claude Sonnet 4.6, Opus 4.6, Haiku 4.5), S3, CloudFront, WAF, EventBridge, and CDK.

Open Source

This project is open source. Fork it, customize it for your needs, and deploy your own instance.
📦 github.com/bbonik/ai-radar-aws

How Importance Scoring Works

Each announcement receives a point score based on multiple factors. The total score maps to a 1-5 star rating:

1★ < 2 pts 2★ ≥ 2 pts 3★ ≥ 3.5 pts 4★ ≥ 5 pts 5★ ≥ 6.5 pts

Point Breakdown

FactorPointsWhen
Core AI service (Bedrock, AgentCore, SageMaker AI)+4Service named in title
Key AI service (SageMaker, Kiro, QuickSight)+2Service named in title
Other AI-related service+1Default
Blog post link+3Link to aws.amazon.com/blogs/
GitHub samples link+2Link to github.com/aws*
Documentation link+1Link to docs.aws.amazon.com/
New model+1.5Tagged as "new-model"
New service+1Tagged as "new-service"
New feature+0.5Tagged as "new-feature"
Anthropic / OpenAI provider+2Provider explicitly mentioned
Instance / notebook announcement-2Hardware/capacity, not feature
Performance / pricing / security-0.5Incremental updates
Region expansion to APJ+1Expands to Asia Pacific
Region expansion (non-APJ only)-1.5Only expands to other regions

Geographic Relevance Badges

Each announcement card shows a small badge indicating whether the feature is available in your region:

🌐 Global Available in all regions
🌏 APJ Asia Pacific
🌍 EMEA Europe / Middle East / Africa
🌎 AMER Americas (US, Canada, South America)
No badge Geography unknown
How geography is detected: The system detects ALL geographies mentioned in each announcement. If the text mentions specific regions (Tokyo, Frankfurt, Oregon, etc.), the corresponding geography badges are shown. If it says "all regions" or is a new feature with no region specified, it gets the Global badge. Geography is also filterable — click a geo chip to see only announcements available in that region.