The challenge: A legacy system no one could fully explain Our client, a leading advisory firm specialising in risk management, insurance, and pension benefits faced an IT system that worked, but no one knew exactly how. With highly specialised expert teams, the firm delivers comprehensive, tailored solutions that help organisations navigate complexity, manage uncertainty, and secure long-term resilience. Yet they still depended on outdated IT systems that lacked the reliability today’s challenges demand. As Zühlke joined the project, certain well-known patterns quickly emerged. Change was risky. Maintenance was expensive. And despite its importance, the system could not keep up with the pace of business. Millions of lines of legacy code, no reliable documentation, and business logic scattered through years of exception-based rules made the client’s digital landscape a black box. It was fragmented, complex, and held together by assumptions no one could trace. The goal: A modern, AI powered solution to enhance clarity, speed and scalability The client needed support in fully rebuilding and modernizing their legacy technology stack to bring clarity, speed, and scalability back to the heart of its operations.With our long-standing business relationship, the client chose Zühlke based on our track record in successfully reconstructing intricate systems, paired with the expertise to ensure continuity, stability, operational efficiency and scalability. The solution and tools Faced with this intricate challenge, the Zühlke team decided to leverage AI to augment our methods of working, addressing complexities, accelerating processes, and laying the groundwork for future innovation and sustained competitiveness. About the Cybernetic Delivery Platform (CDP) The Cybernetic Delivery Platform (CDP) is Zühlke’s way to deliver digital products and services with AI-augmentation. It serves as an execution platform for the AI-augmented delivery method (CDM), by embedding CDM patterns, tools and AI accelerators thereby equipping teams to adopt AI-augmented delivery from day one. It is a modular and adaptable platform that allows clients to integrate only the necessary components, such as Zühlke’s AI accelerators, quickly, without the need for a complete infrastructure overhaul. Visit our landing page to learn more about CDP. About the Cybernetic Delivery Method™ (CDM) As the engine behind CDP, the Cybernetic Delivery Method™ (CDM) enables teams to embed AI into their workflows and lays the foundation to redesign those processes for even greater efficiency. Teams measure what works, share proven augmentation patterns, and scale success across the organisation. This is how Zühlke drives real agility - by learning fast and scaling what works. Learn more about the CDM in this blogpost. Here, CDM was the methodology of choice to deliver the specific capabilities required. The AI-driven analysis—powered by CDM—accelerates the delivery of digital products and services, enhancing agility, efficiency, and impact. By leveraging proven, reusable AI augmentation patterns rooted in best practices, CDM enabled rapid identification and deployment of the most suitable solutions.Furthermore, CDM is Zühlke’s approach to building an adaptive, learning organization and turning that learning into impact, fast. In a world where AI and delivery landscapes evolve rapidly, CDM provides a practical, repeatable cycle that helps teams adopt and scale AI responsibly. It’s a closed learning loop — one that evolves with every project. And because it’s grounded in real delivery, it helps teams stay adaptive, aligned, and in control. Even as tech and business needs shift.When the organisation started applying CDM to enable AI-augmented delivery and teams started using CDM patterns provisioned by CDP to deliver value they observed improved pace, productivity and reported work as being ‘more joyful’: AI is well-supervised, eliminating most routine work so the teams can focus on innovating much faster. Humans decide what is the right thing to do and AI does things right.The outcome was improved productivity and speed across disciplines: AI-enabled analysis and AI-driven acceleration helped team move from task-level automation to transformative workflow improvements, and to deliver substantial productivity gains that translate into measurable business outcomes. Technical implementation / features / methodology When Zühlke stepped in, the client’s IT infrastructure needed more than a facelift. Together with the in-house project team, we set out to transform the central reporting, steering, claims & task management platform into a truly future-ready solution.AI became a team-driven experiment within the client’s organisation – not a side project, but an evolving practice integrated by the team across the software development lifecycle.The team actively explored AI tools to tackle complexity and accelerate delivery. While some tools are already showing value, others remain promising experiments with future potential. Here’s how the team is working with AI today:Business Analysts & Architects use ChatGPT to reverse-engineer undocumented legacy code and complex data structures. Business Analysts are enabled with tools like SQL-Query GPT to help them question the database in the natural language or Story-GPT to generate new user stories with the standardized formatting.Developers benefit from tools like GitHub Copilot, ChatGPT, and custom GPTs enriched with the team’s coding guidelines. These tools, supplemented with team context speed up development, ensure consistency, and explore unfamiliar parts of the system. Code reviews are supported by the Review Bot, catching style and quality issues earlier in the process.Quality Assurance (QA) plays a crucial role in the project, with AI actively supporting quality assurance throughout development. CDM patterns combined with the power of tools like ChatGPT and GitHub Copilot are used to generate additional test cases and act as sparring partners to identify potential gaps in coverage – helping the team catch edge cases early and maintain high confidence in their deliverables. AI-powered DevOps cycle – intelligent support from planning to operations. The results All in all, leveraging CDM as an underlying methodology for augmenting the software delivery lifecycle with AI, the team now: • Works smarter, from planning to implementation • Codes faster, with improved quality and fewer manual errors • Automates the repeatable tasks – freeing up time for high-impact thinkingOutcome: by streamlining processes and reducing waste, the team reported ~30% efficiency gains while building a modern, maintainable platform. The increased clarity and confidence also translated into a boost in productivity.The efficiency improvement achieved here is a strong result, especially given the extreme complexity of the client’s legacy landscape. It laid the foundation for improved productivity, a meaningful outcome that reflects the strength of the approach even in tough conditions. ' Zühlke were there before the AI hype started. As the project evolved, we seamlessly integrated AI tools and practices into the delivery process, helping the project team to shift from a critical phase to a stable and future-proof solution. The outcome—a 30% boost in efficiency—was a remarkable achievement that delivered clear value to the client. ' Andrija Ljubojevic Principal Software Engineering Consultant, Zühlke Our work GRP logo GRIP_logo_Horiz Healthcare providers, Pharma Revolutionising the Alzheimer’s research ecosystem Learn more Banking, Commerce & retail Zühlke's GenAI Project Finder boosts presales efficiency Learn more Pharma Berlinger pioneers smarter medication shipments with IoT Learn more Go to case studies Deliver transformative impact with Zühlke. Speak to our team today. Get in touch
' Zühlke were there before the AI hype started. As the project evolved, we seamlessly integrated AI tools and practices into the delivery process, helping the project team to shift from a critical phase to a stable and future-proof solution. The outcome—a 30% boost in efficiency—was a remarkable achievement that delivered clear value to the client. ' Andrija Ljubojevic Principal Software Engineering Consultant, Zühlke