Thought Machine has partnered with Amazon Web Services (AWS) on an AI-powered solution for banks moving from legacy systems to its Vault core banking platform.
The solution combines AWS Transform’s mainframe discovery and reverse engineering tools with Vault Forge, Thought Machine’s AI tooling suite.
It aims to reduce the time and cost of core banking migration, according to Thought Machine.
Rather than translating legacy code line by line, the process extracts the business rules behind functions such as interest calculations, fee schedules and loan repayments.
The Vault platform keeps financial product logic separate from its core infrastructure.
This separation allows AI agents to convert legacy rules into product code while bypassing database complexities.
The process runs within the bank’s secure AWS environment.
AWS Transform analyses legacy applications and extracts their business logic into structured specifications.
The pipeline then consolidates redundant legacy product variations before Vault Forge uses AI models through Amazon Bedrock to generate Python-based financial products, test suites and platform configurations.
Bank engineering and risk teams retain sign-off authority through human review stages.
Once validated, the generated products can be deployed to a Vault sandbox for further testing and evaluation.
According to Thought Machine, the approach can compress multi-year processes into days, including work involving millions of lines of mainframe code.
Paul Taylor, CEO of Thought Machine, said:
“For the first time, banks can deploy AI to rapidly convert complex legacy mainframe specifications into simulation-tested, cloud-native financial products.
This gives large financial institutions the execution speed, audit rigor, and confidence required to eliminate technical debt and complete their cloud transition.”
Charith Mendis, Head of Worldwide Banking, Financial Services Industries, AWS, said,
“With Thought Machine’s Vault Forge and AWS Transform’s AI capabilities, we enable banks to safely extract business logic from legacy systems, providing a new continuous, automated path from mainframe code to cloud-native core banking – solving one of the hardest banking modernisation challenges for banks and we believe it will fundamentally change how the industry approaches core transformation.”
Thought Machine is also launching a joint Core Modernisation Accelerator programme with AWS.
Technical architects, product specialists and Thought Machine engineers will work alongside bank engineering teams on implementation, governance and architecture.
Featured image: Edited by Fintech News Singapore, based on image by mrsiraphol via Magnific
