{"slug":"bankdata-pilots-microsoft-s-agentic-cobol-migration-factory-against-its-70-million-line-mainframe-estate","url":"https://findausecase.com/use-cases/bankdata-pilots-microsoft-s-agentic-cobol-migration-factory-against-its-70-million-line-mainframe-estate","title":"Bankdata pilots Microsoft's agentic COBOL Migration Factory against its 70-million-line mainframe estate","description":"Bankdata, a technology company owned by a consortium of Danish banks representing over 30% of the Danish banking market, has over 70 million lines of code still running on the mainframe. Bankdata worked with Microsoft to build the COBOL Agentic Migration Factory (CAMF), a multi-agent system built on Semantic Kernel with specialized agents (COBOLAnalyzerAgent, JavaConverterAgent, DependencyMapperAgent) that analyze, map dependencies for, and convert COBOL programs into modern Java Quarkus applications. Microsoft tested the framework on a small COBOL module donated by Bankdata, progressively validating it on more complex COBOL call chains reaching a call-chain depth of level 3 as the tool matured into its current multi-agent form.","company":"Bankdata","industry":"Financial Services","country":"Denmark","aiCapabilities":["Code Generation","Agentic AI"],"technology":["Microsoft Semantic Kernel","GPT-4.1","AutoGen","Azure OpenAI"],"deployment":"Public Cloud","problemStatement":"Bankdata, a technology company owned by a consortium of Danish banks representing over 30% of the Danish banking market, has over 70 million lines of code still running on the mainframe. Modernizing away from the mainframe is complex because many COBOL modules are tied to non-functional behaviors such as batch throughput, I/O handling, JCL orchestration and strict SLAs, and re-platforming has historically been a manual, time-consuming and costly affair, compounded by a shrinking pool of COBOL experts and loss of institutional knowledge.","solutionApproach":"Microsoft, in collaboration with Bankdata, built the COBOL Agentic Migration Factory (CAMF), a multi-agent system orchestrated via Microsoft Semantic Kernel with specialized agents — COBOLAnalyzerAgent, which scans COBOL files to understand their structure and logic; JavaConverterAgent, which converts COBOL source code to Java Quarkus; and DependencyMapperAgent, which analyzes copybook dependencies and generates diagrams — that automates analysis, transformation, dependency mapping and reporting for migrating COBOL programs into modern Java Quarkus applications.","evidence":{"band":"high"},"sourceUrl":"https://devblogs.microsoft.com/all-things-azure/how-we-use-ai-agents-for-cobol-migration-and-mainframe-modernization/","dates":{"publishedAt":"2026-08-23T09:02:00.503Z","publishedAtSource":"pipeline","updatedAt":"2026-08-23T09:02:00.503Z"},"license":"Open for reading and citing with a link to https://findausecase.com/use-cases/bankdata-pilots-microsoft-s-agentic-cobol-migration-factory-against-its-70-million-line-mainframe-estate. Bulk republication requires permission."}