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

AWS Transform adds agentic AI assistant to the AWS Toolkit for Visual Studio

.NET developers can now modernize apps step-by-step with AI directly in Visual Studio — with full control, checkpointing, and no console switching.

View original announcement →

Visual Summary

graph TD A{{AWS Transform Agentic AI}}:::announced B((".NET Developer")):::external C([Visual Studio Toolkit]):::feature D([Kiro / MCP Agents]):::feature E([Code Assessment]):::feature F([Transformation Plan]):::feature G([Interactive Execution]):::feature H([Auto Error Remediation]):::feature I(AWS Transform Console):::compute J([HTML Summary Report]):::feature B ==>|"converses"| C C ==>|"invokes"| A B -.->|"alternative IDE"| D D -->|"invokes"| A A -->|"analyzes code"| E E -->|"generates"| F F -->|"step-by-step"| G G -->|"on build errors"| H G -->|"completes"| J I -.->|"preserves context"| A 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 Transform now includes an interactive agentic AI assistant embedded directly in the AWS Toolkit for Visual Studio, enabling .NET developers to modernize legacy applications through a conversational, step-by-step guided experience without leaving their IDE. The agent analyzes source code, generates a transformation plan, executes modernization tasks interactively, and automatically attempts to fix build errors encountered along the way. Beyond Visual Studio, the same AWS Transform agent capabilities are accessible via Kiro and other AI coding environments through AWS Transform MCP agents.

How It Works

  • The agent begins by analyzing the .NET application's source code and producing a detailed assessment report, followed by a generated transformation plan that the developer can review or replace with a custom-uploaded plan.
  • Modernization tasks are executed interactively and incrementally: the developer can review generated code diffs, edit them, and explicitly approve each step before the agent proceeds, providing fine-grained control over the transformation.
  • Developers can pause the process at any step, inspect changes, and steer the agent using natural language instructions, enabling course corrections mid-transformation without restarting.
  • When build errors are encountered during transformation, the agent automatically attempts to diagnose and fix them, reducing manual debugging overhead.
  • Detailed worklogs are maintained throughout the process for full transparency, and upon completion the agent generates a downloadable HTML summary report with recommended next steps.
  • Projects can be initiated in the AWS Transform web console and seamlessly continued inside Visual Studio, with full context and progress state preserved across both environments.
  • AWS Transform MCP agents extend these capabilities to Kiro and other AI coding assistants, allowing developers to invoke transformation power from their preferred development environment.

Why It's Important

  • .NET modernization projects have historically required developers to context-switch between their IDE and a web console, introducing friction and increasing the risk of workflow disruption; this integration eliminates that overhead entirely.
  • The interactive, step-by-step approval model gives developers meaningful oversight over AI-generated changes, addressing a common concern about fully automated code transformation tools making opaque or undesirable modifications.
  • Automatic build error remediation reduces one of the most time-consuming manual tasks in any modernization effort, accelerating the overall migration timeline.
  • The checkpointing and pause/resume capability means large, complex modernization projects can be tackled incrementally without risk of losing progress, making it practical to modernize enterprise-scale .NET applications.
  • Extending the capability to Kiro and MCP-compatible environments signals a platform strategy that meets developers where they already work, rather than forcing adoption of a single toolchain.
  • The downloadable HTML summary report and recommended next steps provide artifacts that are useful for team communication, compliance documentation, and planning follow-on work.

How It's Different

  • Unlike fully automated batch transformation tools, this agent operates interactively with per-step human review and approval, giving developers control rather than presenting a finished (and potentially incorrect) result.
  • The bidirectional continuity between the AWS Transform web console and Visual Studio is unique: context and progress are preserved across both surfaces, so developers are not forced to choose one environment exclusively.
  • Natural language steering mid-transformation is a differentiator from traditional migration tools that require configuration files or scripted parameters to change behavior.
  • The MCP agent integration allows AWS Transform's capabilities to surface inside third-party AI coding assistants like Kiro, going beyond a single proprietary IDE plugin model.
  • Automatic build error detection and self-healing during transformation is a step beyond tools that simply generate code and leave error resolution entirely to the developer.
  • The custom plan upload feature allows teams with existing migration runbooks or architectural standards to inject their own guidance, rather than being constrained to the agent's default strategy.

When to Prefer It

  • Use this when your team's .NET developers are deeply embedded in Visual Studio and organizational policy or personal preference makes switching to a web console disruptive to productivity.
  • Prefer this approach for complex or large .NET codebases where a fully automated, no-review transformation carries too much risk and incremental, approved changes are required for quality assurance.
  • Ideal when a modernization project spans multiple sessions or team members, since the checkpointing and cross-environment context preservation allow work to be paused and resumed without loss of state.
  • Choose this when your organization has existing migration standards or architectural guidelines that need to be enforced, leveraging the custom plan upload to inject those constraints into the agent's execution.
  • Well-suited for teams already adopting Kiro or other MCP-compatible AI coding assistants who want to consolidate tooling and avoid maintaining separate workflows for transformation versus day-to-day development.
  • Appropriate when auditability and transparency are requirements, since the detailed worklogs and downloadable HTML summary report provide documentation artifacts for governance or compliance purposes.

Availability

  • GA Status: Generally available as of May 14, 2026, via the latest AWS Toolkit for Visual Studio downloadable from the Visual Studio Marketplace.
  • Supported Regions: US East (N. Virginia), Canada (Central), Europe (Frankfurt), Europe (London), Asia Pacific (Mumbai), Asia Pacific (Seoul), Asia Pacific (Sydney), and Asia Pacific (Tokyo).
  • Pricing: No specific pricing details were disclosed in the announcement; costs are expected to follow existing AWS Transform pricing — consult the AWS Transform pricing page for current details.
  • IDE Support: Natively integrated into Visual Studio; also accessible via Kiro and other MCP-compatible AI coding assistants through AWS Transform MCP agents.
  • Limitations: Not yet available in all AWS Regions; developers in unsupported regions will need to use a supported region endpoint or wait for future regional expansion.

Tags

Servicesaws-transform
Typenew-featureintegration
Conceptsagentic-aicoding-assistantgenai
Use Casesdeveloper-toolsmigration
GeographyAMERICASAPJEMEA

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.