Thought Machine and Amazon Web Services have announced an AI-powered migration solution to accelerate banking modernisation with AWS Transform, targeting major national and global financial institutions still running legacy mainframes.

Announced on September 29 in London and New York, the solution combines AWS Transform tooling for mainframe reverse engineering with Thought Machine’s Vault Forge, an AI tooling suite. Banks can reimagine millions of lines of mainframe code such as COBOL into tested financial products in a live sandbox, compressing multi-year processes into days.

Rather than translating code line by line, the joint pipeline extracts pure business intent inside the customer’s secure cloud environment. The pipeline runs four stages: extraction of business logic into structured specifications, consolidation of hundreds of redundant legacy product variations, synthesis of Python financial products and test suites via Amazon Bedrock, and validation through human-in-the-loop review gates.

Thought Machine is also launching a joint Core Modernisation Accelerator programme, with its engineers working alongside bank teams. The company’s Vault platform, which defines financial products entirely as code using Python, is trusted by more than 65 leading banks worldwide.