Code modernization solutions update older applications, codebases, or platforms to current technologies and architectures. They address maintenance risk, limited scalability, and difficulty integrating legacy systems with modern tools.
Use cases
14
Examples
14
Industries
7
Timeline
10 mo
Data updated 1 day ago
Adoption over time
Documented cases per month
By case publish month · completed months only
12 cases documented across 37 months (Jul 23 – Jul 26), peaking at 4 in May 2026.
AI Use Cases Hub
1 earlier case before Jul 23 not shown
Each column counts every documented case of this type by its publish month, across the full corpus. The in-progress current month is excluded from columns and surfaced separately, and cases published before the charted window are summarized as earlier cases instead of plotted.
4.2Innovativeness4.2/5Advanced4.2/5 - Advanced. Compared with recent Alibaba-style cloud modernization cases around the high-2s to mid-3s, this is more novel because it combines graph modeling, agent specialization, graph traversal, and vector search for legacy software modernization. It is still a pilot rather than a broadly scaled breakthrough, so it fits the low-4 band rather than the top end.
Siemens and Google Cloud created Knowledge Fabric to help modernize large industrial software codebases and the applications that run on them.The system ingests the software ecosystem into an intelligent agentic workflow that can reason across code, Jira, Confluence, and PDF documentation while preserving explainability and traceability.
4.1Innovativeness4.1/5Advanced4.1/5 - Advanced. Compared with recent healthcare agentic-AI calibration cases, this is similarly advanced but not frontier: the novelty is in applying specialized agents to large-scale migration planning and discovery across 29 data centers, not in inventing a new model architecture.
CSL is a global biotechnology company modernizing its business-critical operations by exiting legacy on-premises infrastructure and moving to the cloud.The company faced technical debt across 29 data centers, with 5,000 VMware servers and more than 1,000 applications, plus fragmented documentation and complex dependencies that slowed migration planning.CSL used Amazon Q Business to index more than 17,000 pages of infrastructure requirements and AWS Transform for VMware to analyze VMware environments, map dependencies, and generate migration wave plans.The company is also using AWS for RISE with SAP as part of its broader modernization program.
2.8Innovativeness2.8/5Differentiated2.8/5 - Differentiated. Useful but still an incremental enterprise developer-productivity deployment: the differentiator is MCP-based context integration across code, Jira, Bitbucket, Figma, and databases, but the core pattern remains a packaged coding assistant workflow. Compared with recent Amazon Q Developer modernization cases, it is comparable rather than materially more novel.
Altisource, a US real estate and mortgage technology company, used Amazon Q Developer to modernize legacy software and accelerate delivery across its enterprise applications.The company introduced generative AI into its AWS environment and embedded Amazon Q Developer into the development workflow to work across large legacy applications and new feature delivery.Altisource connected Amazon Q Developer to Jira, Bitbucket, Figma, and internal database servers through MCP servers so the tool could use project, design, and code context during development tasks.
3.5Innovativeness3.5/5Advanced3.5/5 - Advanced. The implementation combines managed Kubernetes, Vertex AI prototyping, and secure single-tenant AI-assisted product features to modernize enterprise workflows, but it remains an applied cloud modernization pattern rather than a novel AI architecture.
FlowX.AI builds an AI-powered application modernization platform for global financial institutions.The company uses Google Cloud to scale R&D, prototype AI-assisted features, and create secure single-tenant environments for developing and testing customer functionality.
3Innovativeness3/5Differentiated3/5 - Differentiated. The case shows differentiated applied use of Amazon Q Developer Agent for automated code transformation plus internal knowledge base support, but it is still a modernization workflow rather than a novel architecture.
Novacomp, a Costa Rica–based IT services company, modernized legacy Java applications to reduce maintenance burden and technical debt.The company needed to upgrade a project with more than 10,000 lines of Java 8 code to Java 17 while improving security and compliance for its clients.
4.3Innovativeness4.3/5Advanced4.3/5 - Advanced. This is more advanced than a basic copilot or single-pass summarization flow because it combines agentic orchestration, retrieval-augmented generation, multi-stage document generation, and bottom-up diagram composition; it is comparable to recent AgentCore cases around the mid-4s rather than 2-3 level productivity bots.
Toyota Motor Europe (TME) built a proof of concept with Deloitte and the AWS Generative AI Innovation Center to automatically generate documentation from legacy NCL source code.The solution produces technical YAML documentation, business HTML reports, and Mermaid process-flow diagrams from a legacy warranty-handling application, using Amazon Bedrock, Strands Agents SDK, Amazon Bedrock AgentCore, and an Amazon Bedrock Knowledge Base.The workflow uses agentic orchestration, retrieval-augmented generation, and bottom-up diagram composition to overcome context-window limits and preserve embedded business logic for modernization.
2.8Innovativeness2.8/5Differentiated2.8/5 - Differentiated. This is a practical code-analysis use of watsonx Code Assistant for Z, but the article only shows dependency mapping and blueprint creation for modernization planning. Similar recent banking and developer-assistance cases are incremental rather than breakthrough.
Royal Bank of Canada used watsonx Code Assistant for Z to identify dependencies, data flows, structure, and organization of existing mainframe applications.The tool was used to create a modernization and change-management blueprint for core system applications.
4Innovativeness4/5Advanced4/5 - Advanced. It describes an end-to-end, agentic modernization operating model spanning automated discovery (Azure Migrate), IDE-integrated plan generation/execution, and post-migration SRE AI monitoring with quantifiable reductions.
Microsoft's AI agents platform automates enterprise-scale migration and modernization of .NET and Java applications, reducing what was once a months-long process to days. Azure Migrate automatically inventories and assesses legacy application portfolios, streamlining discovery of dependencies, OS, and frameworks. GitHub Copilot and agentic workflows help developers plan and execute modernization with minimal manual effort by generating migration plans, handling dependency updates, and automating workflows from Visual Studio or JetBrains IDEs. Early use within Microsoft's Xbox team and Ford China resulted in dramatic, quantifiable reductions in migration effort and technical debt. The solution improves developer productivity, reduces security risk, and enables organizations to tackle projects previously deemed too complex or risky to address using agentic, cloud-native patterns. Post-migration, built-in SRE AI agents maintain and optimize migrated workloads with proactive performance analysis and recommendations.Modernizing legacy applications is essential to address security vulnerabilities, technical debt, and to harness new cloud capabilities, but the complexity and time required has long discouraged innovation. Azure Migrate initiates comprehensive automated discovery, while cloud-based AI agents dynamically generate actionable migration plans. Developers hand off migration workflows directly from familiar coding environments and maintain total oversight while benefiting from greatly reduced developer toil.App portfolios are migrated to Azure, codebases are updated and optimized, and organizations use additional tools (e.g., AppCAT) for ongoing cloud optimization. Broadened support for various IDEs, databases, and integration of operations AI completes the modernization lifecycle. This solution represents a paradigm shift in enterprise IT management, offering speed, predictability, and reduced operational risk.
5Innovativeness5/5Breakthrough5/5 - Breakthrough. A modular, multi-agent 'COBOL Agentic Migration Factory' orchestrated with Semantic Kernel automates analysis, dependency mapping, and code conversion/testing for massive legacy modernization in-house.
Bankdata, a consortium of Danish banks, faced the challenge of modernizing their vast COBOL-based mainframe legacy systems to cloud-native platforms due to growing technical debt, rising maintenance costs, and limited access to legacy experts. The organization aimed to retain more control over project costs and intellectual property, moving away from traditional approaches heavily reliant on global system integrators. Leveraging state-of-the-art Microsoft technologies, Bankdata and partners developed a modular, agent-based migration factory that uses multiple orchestrated AI agents to analyze, convert, and test COBOL code into maintainable Java running on modern platforms. This system underpinned the transition by extracting business logic, visualizing and mapping dependencies, and ensuring that legacy business processes are accurately transformed. Sophisticated orchestration with Microsoft Semantic Kernel enabled precise management of worker agents, intelligent handling of code context, and conversion consistency. Using GPT-4, GitHub Copilot, and Azure OpenAI, the framework delivers robust code translation, dependency mapping, call chain analysis, and quality assurance through test suite automation. The project significantly reduced manual workload, improved code quality and maintainability, and accelerated transformation timelines, all managed in-house at Bankdata.
4Innovativeness4/5Advanced4/5 - Advanced. More advanced than a typical modernization case because it combines AWS Transform with a composable multi-agent framework, partner-built agents, and MCP-based orchestration; calibration cases around basic claims migrations scored 2, while similar agentic enterprise systems score around 4.
Western Union and Unum partnered with AWS and Accenture/Pega to modernize their mainframe-based legacy systems using AWS Transform, an agentic AI service designed for large-scale migration and modernization.Western Union aimed to modernize its 35-year-old money order platform to support growth targets and improve back-office operations, while Unum sought to streamline Colonial Life claims processing and remove fragmented workflows.
How many code modernization use cases are documented?
The AI Use Case Hub documents 14 real code modernization deployments across 7 industries, with 14 detailed company examples you can browse.
Which industries adopt code modernization the most?
Code modernization is most common in Finance (29%), Tech & Comms (21%) and Insurance (14%).
Which countries lead in code modernization?
United States leads documented code modernization deployments, followed by Japan and Switzerland.
What technologies are used for code modernization?
Teams most often build code modernization with GitHub Copilot, Azure OpenAI and Azure.
What AI capabilities power code modernization?
Across the documented deployments, the most common capability patterns are Agent (64%), Copilot (29%) and Multi-agent (29%).
What results do companies report from code modernization?
Across the 14 deployments reporting outcomes, companies most often cite speed & agility (79%), new product / capability (57%) and cost efficiency (57%). Where impact is quantified, the strongest evidence is in productivity & throughput: a median +35% across 3 reported metrics.