AWS unveils AI agent that modernizes code across thousands of repos
AWS announced a new AI‑driven agent designed to tackle one of the most stubborn problems in software development: modernising legacy code at scale. The service, unveiled under the banner “AI agent that modernises code across thousands of repos,” promises to automate the tedious work that usually eats up engineering bandwidth and inflates technical debt. While the idea of a bot that can rewrite code isn’t new, the claim here is that it can operate across “hundreds or even thousands of repositories” without a human hand‑over for each project.
The company says the tool pulls from existing documentation, natural‑language prompts and code examples, then refines its output by watching how developers correct its suggestions. If it lives up to those expectations, teams could see a shift from reactive bug‑fixing to proactive, systematic upgrades. That’s the promise behind the technology, and the following statement explains exactly how the learning loop is supposed to work.
Transform custom applies its learned transformation patterns across large codebases, including hundreds or even thousands of repositories. It learns from documentation, natural-language instructions, and code samples, and then improves over time by analysing developer feedback and the manual fixes teams make during the modernisation process. The service includes a CLI and a web interface.
The CLI supports conversational inputs for defining and executing transformations locally or in CI/CD workflows, while the web interface offers campaign-level tracking for modernisation projects across teams. AWS said the agent supports runtime upgrades for Java, Python and Node.js, and can execute complex transformations such as migrating Spring Boot applications or shifting workloads to AWS Graviton. It can also learn enterprise-specific coding patterns and apply them consistently.
"The service understands not only the mechanical aspects of API changes, but also recognises best practices and optimisation opportunities available in newer SDK versions," the company said. Transform custom extends to Infrastructure as Code, with support for CDK-to-Terraform conversions and CloudFormation updates.
Can an AI agent truly automate code modernisation at scale? AWS says Transform custom does, applying learned patterns across hundreds or thousands of repositories. The service blends pre‑built transformations with organisation‑specific rules, learning from documentation, natural‑language instructions and code samples.
Early adopters claim up to an 80 % cut in execution time, freeing developer hours for product work. Yet the reports come from a limited set of customers, and it’s unclear whether similar gains will materialise in more complex environments. Because the agent refines itself through developer feedback and manual fixes, its performance may evolve, but the pace of that improvement remains uncertain.
The offering is now available through AWS, positioned as a tool for reducing technical debt. While the initial metrics are encouraging, broader validation will be needed to confirm that the claimed efficiencies hold across diverse codebases and organisational practices. For now, the data points to a potentially useful addition to the modernisation toolkit, pending further evidence.
Further Reading
- New Agentic Capabilities in AWS Transform Enable Rapid Modernization of Any Code or Application - Business Wire / Morningstar
- Introducing AWS Transform custom: Crush tech debt with AI-powered code modernization - AWS Blog
- AWS Transform: Agentic AI Automates Legacy Code Modernization and Reduces Technical Debt - Security Online
- AWS Transform launches an AI agent for full-stack Windows modernization - AWS What's New
- Top announcements of AWS re:Invent 2025 - AWS Blog
More in Business & Startups
Runway launches General World Model with three versions and Gen‑4.5 upgrades
Runway just dropped a new AI suite that promises more than a single‑purpose generator.
Disney sues Google over AI “virtual vending machine” after USD 1 bn OpenAI deal
Disney has filed a lawsuit against Google, accusing the tech giant of using its...
NVIDIA invests USD 5 billion in Intel, gaining a significant equity stake
Why does a chipmaker best known for graphics cards suddenly pour billions into a rival’s balance...
Broadcom discloses USD 21 B Anthropic order for Google’s 7th‑gen TPUs
Broadcom’s latest filing reveals a $21 billion purchase from Anthropic, the AI startup that has...
Harness secures USD 240 M E round, led by Goldman Sachs, for AI software delivery
Harness just closed a $240 million Series E, with Goldman Sachs heading the round, to fund its...
Common Questions Answered
What is the name of the AWS AI‑driven service that modernises code across thousands of repositories?
The service is called Transform custom. It is an AI agent that learns transformation patterns from documentation, natural‑language instructions, and code samples, then applies them across large codebases.
How does Transform custom improve its code‑modernisation capabilities over time?
Transform custom continuously refines its transformations by analysing developer feedback and the manual fixes teams make during the modernisation process. This iterative learning enables the agent to adapt to organisation‑specific rules and improve accuracy.
What interfaces does AWS provide for interacting with the Transform custom AI agent?
AWS offers both a command‑line interface (CLI) and a web interface for Transform custom. The CLI supports conversational inputs, allowing developers to define and execute transformations locally, while the web UI provides a visual workflow.
According to early adopters, what impact does Transform custom have on execution time for code modernisation?
Early adopters report up to an 80 % reduction in execution time when using Transform custom. This speedup frees developer hours for product work and helps lower technical debt associated with legacy code.