Offline assessment and conversion with AI agents in AWS DMS
Database Blog
This article demonstrates how to use AI agents with AWS DMS Schema Conversion to assess and convert database schemas offline, without connecting to source or target databases.
- Offline source mode (SQL Server, Oracle) and virtual target mode enable schema assessment before infrastructure is ready
- AI agents load the DMS Schema Conversion skill and manage the complete workflow through natural language prompts
- Agents create data providers in Virtual Mode, build migration projects, assess/convert objects, and export results without console navigation
- Example walkthrough shows SQL Server to Aurora PostgreSQL conversion with 99% automatic conversion rate
- Transition to actual target database by switching virtual target to live connection and applying converted code
- Reduces migration planning dependencies, accelerates timelines, and lowers idle resource costs during discovery phase
By combining offline-first assessment with agentic orchestration, teams can begin database migration planning in parallel with infrastructure provisioning while minimizing manual effort.
The AWS News Feed is currently looking for gold sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.
Related articles
Nov 17
2026
2026
Building a gated review pipeline for AI coding agents on AWS
Oct 28
2026
2026
Automating agentic AI Well-Architected reviews with the AWS Agentic AI Lens
Jul 10
2026
2026
AWS DMS Schema Conversion now supports AI agent automation
Oct 21
2026
2026
Mastering automated agent performance evaluations in Amazon Connect Customer
The AWS News Feed is currently looking for silver sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.