Service Copilot from ZEISS - The intelligent assistant that every service team wants
The knowledge is there. Experience too. But for the service team at ZEISS Research Microscopy Solutions (RMS), every request meant having to compile information from countless documents in far too many sources. Now they are supported by Service Copilot, an intelligent assistant that links knowledge graphs with Agentic AI – and makes the service for ZEISS microscopes as efficient as research demands.
Challenge: complex products and scattered information
The service tasks at ZEISS RMS are often just as complex and demanding as the microscopy systems the company has been developing for research and industry for over 175 years. The field service engineers and support teams, who work remotely at various service levels, possess a high level of expertise. Training for the job is time-consuming and takes a long time. Numerous source systems containing thousands of documents, a cumbersome search process, and scattered information regarding the current service case, the service history of the device, or the customer all reduced efficiency. Speed is particularly critical when it comes to fault diagnosis and repair. Every minute the device is out of service typically costs money.
Improved service, satisfied stakeholders
A lot has happened since then: Today, Service Copilot supports ZEISS service teams in their daily work, both remotely and in the field. User feedback has been very positive. In practice, it is evident that service processes have become more efficient overall—from faster problem resolution and improved access to information to a reduced need for on-site visits. This has noticeably improved service quality and significantly simplified the daily work of technicians.
The three features of this intelligent solution
The service team now works across all devices using the same app, Service Copilot, which offers three key features. The first is a ticket-based interface designed specifically to support first-level support. Tickets are documented for every service case and can be used as sources for Service Copilot. New, open, and resolved tickets are collected for each customer and displayed centrally as a history, allowing recurring issues, for example, to be quickly identified.
At its core is an intelligent chatbot that utilizes a modern system comprising multiple AI agents—linked to a knowledge graph to ensure high-quality responses. Thanks to this so-called Agentic RAG system, anyone in the service team—whether working remotely or in the field—can ask product-related questions and quickly receive a reliable answer. The foundation is a comprehensive, quality-assured knowledge base containing service- and product-related information from various sources. Every response always includes the source reference, allowing the service team to quickly evaluate it. Additionally, the AI provides supplementary information if a similar issue has arisen with another customer in the past and displays the corresponding solution.
The third feature comprises a database with special product numbers that refer to the customer’s products. This enables the service team to quickly access the specific product information of a particular customer.
More than a content delivery portal
The Service Copilot also has a special feature compared to conventional content delivery portals: While a CDP is designed to provide information efficiently, communication with the intelligent assistant runs in two directions. The system not only provides information, but is also fed and improved by user-generated content such as feedback and best practices. There is also interaction in natural language between the users and the system. Queries from the AI agent enable optimal search results.
Service Copilot is transforming the way technicians access and apply knowledge in their daily work. By combining AI agents with semantic reasoning, Service Copilot enables faster, smarter service decisions at the point of need. This results in quicker resolutions, reduced operational overhead, and empowers technicians with contextual insights that enhance service quality and customer satisfaction.
The path to Service Copilot
Over the course of several years, initial ideas and solutions for the intelligent provision of service information were developed in various smaller projects. This phase was important for gaining experience and recognizing potential. Finally, the project managers at ZEISS and PANTOPIX decided that it was time to take the next step and tackle this topic strategically. On this basis, a sustainable and forward-looking concept was developed.
The launch of the “Service Copilot” project was marked by a joint vision workshop in which the target vision and the corresponding roadmap were defined. A key subsequent step was advising the technical editorial team and establishing a knowledge management system that involved all stakeholders. To this end, the product portfolio of ZEISS microscopes and their components was first fully described using semantic techniques. A uniform semantic structure for service and product information was established. A positive side effect: In the process, new internal guidelines for product descriptions were created at ZEISS and implemented as part of the continuous improvement process.
The next step on the agenda was the implementation of a knowledge graph. Relevant service and product information was centrally consolidated and linked from various company-wide source systems. Metadata modeling ensured the semantic interlinking of the information. As a result, data from a wide variety of silos is now connected, making consistent information available company-wide, revealing relationships, and enabling intelligent applications such as the Service Copilot.
The Service Copilot was developed in very close cooperation with ZEISS Digital Partners (ZDP). The PANTOPIX development team provided both advice and support in the development of the front and back end of the application. PANTOPIX contributed its proven expertise, particularly in the agent setup for AI-based systems.
Outlook
The Copilot service is already up and running and is available to all service technicians in their daily work. Further developing the application, integrating additional data sources, and continuously improving data quality are on the agenda as we take the final step toward a digital information twin.
You can find out more about the architecture of agent-based AI in this project in our case study Agentic AI + Knowledge Graph: How AI works in the Service Copilot from ZEISS.
About ZEISS Research Microscopy Solutions
ZEISS Research Microscopy Solutions is the leading provider of light, electron, X-ray microscope systems, correlative microscopy and software solutions leveraging AI technologies. The portfolio comprises of products and services for life sciences, materials and industrial research, as well as education and clinical routine applications. The unit is headquartered in Jena. Additional production and development sites are located in Germany, UK, USA, China and Switzerland. ZEISS Research Microscopy Solutions is part of the Industrial Quality & Research segment.
Further information at www.zeiss.com/microscopy
