Projekte
Service Copilot from ZEISS – The intelligent assistant every service team desires
The knowledge is there. So is the experience. But every inquiry meant that the service team at ZEISS Research Microscopy Solutions (RMS) had to gather 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 – making 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 that the company has been developing for research and industry for over 175 years. The field service engineers and support teams, who work remotely at different service levels, have a high level of expertise. Training for the job is time-consuming and takes a long time. Numerous source systems with more than 20,000 documents, time-consuming searches, and scattered information on the current service case, the service history of the device, or the customer reduced efficiency. Speed is of the essence, especially when it comes to fault diagnosis and repair. Every minute that the device is not working usually costs money.
Improved service, satisfied stakeholders
The three features of this intelligent solution
The service team now works independently of devices using the same app, Service Copilot, which offers three features. The first is a ticket-oriented approach that particularly supports first-level support. Tickets are documented in the SAP and CRM systems for each service case and can be used as sources for Service Copilot. New, ongoing, and resolved tickets are collected for each customer and displayed centrally as a history so that recurring problems, for example, can be quickly identified.
At the heart of the system is an intelligent chat function that uses a modern system consisting of several AI agents – connected to a knowledge graph to ensure the quality of responses. Thanks to this so-called Agentic RAG system, anyone in the service department – whether remote or in the field – can ask product-related questions and quickly receive a reliable answer. This is based on almost 20,000 documents such as manuals, spare parts catalogs, troubleshooting guides, solution notes, etc., which are stored in various source systems. Each answer always includes the source reference so that the service department can quickly evaluate it. In addition, the AI provides additional information if a similar problem has occurred with another customer in the past and shows the solution.
The third feature comprises a database with special product numbers that refer to the customer’s products. This enables the service to quickly access specific product information for a particular customer.
More than a content delivery portal
The Service Copilot also has a special feature that sets it apart from conventional content delivery portals: while a CDP is designed to provide information efficiently, communication with the intelligent assistant is two-way. The system not only delivers information, but is also fed and improved by user-generated content such as feedback and best practices. In addition, interaction between users and the system takes place in natural language. 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.“ – Sonam Chugh, Machine Learning Engineer, ZEISS
The path to Service Copilot
Over several years, initial ideas and approaches for the intelligent provision of service information emerged in various smaller projects. This phase was important for gathering experience and identifying potential. Ultimately, the project managers at ZEISS and PANTOPIX decided that it was time to take the next step and tackle this issue strategically. On this basis, a sustainable and forward-looking concept was developed.
The start of the “Service Copilot” project was marked by a joint vision workshop in which the target vision and the corresponding roadmap were defined. An important part of this was subsequently consulting with the technical editorial team and setting up a knowledge management system involving all stakeholders. To this end, the product world of ZEISS microscopes and their components was first described in full using semantic techniques. Terminology, thesauri, and ontologies were modeled. A positive side effect was that new internal guidelines for product descriptions were created at ZEISS and implemented as part of a continuous improvement process.
The next step on the agenda was the implementation of a knowledge graph. Data was extracted from various sources (SAP, ERP, CRM, ETK, editorial systems, SharePoint databases) and made available in a knowledge graph database. Metadata modeling ensured the semantic networking of the information. Data from a wide variety of silos is now linked together, making consistent information available across the company, revealing connections, and enabling intelligent applications such as Service Copilot.
The development of Service Copilot was carried out in very close cooperation with ZEISS Digital Partners (ZDP). The PANTOPIX development team provided both consulting and support services for the development of the front and back ends of the application. PANTOPIX contributed its proven expertise, particularly in the area of agent setup for AI-based systems.
Outlook
The Service Copilot is already up and running and currently supports around 1,000 service technicians in their daily work. Further developing the application, integrating additional data sources, and continuously improving data quality are on the agenda in order to take the final step toward a digital information twin.
About ZEISS RMS
ZEISS Research Microscopy Solutions (RMS) specializes in the development and manufacture of microscopes and imaging technologies for various applications. The company offers a wide range of microscopes, from light microscopes and electron microscopes to X-ray microscopes. These instruments are used in various fields, including life sciences, materials science, and industry.
Would you like to support your service with an intelligent assistant?
Feel free to contact us without obligation.
Contact us
Maraike Heim
Head of Marketing
- maraike.heim@pantopix.com
easychat: AI chat assistant from PANTOPIX impresses in live operation
The closer cooperation between gds and PANTOPIX, which began in April 2025, is bearing fruit: both companies are proud to announce that the content delivery portal easybrowse has now been expanded with easychat, an AI-based assistance function.
Improving service quality with networked information
Production processes are being continuously optimized and automation solutions are being promoted. However, in the service department, where customers expect quick responses, precise solutions, and personal support, digital progress all too often comes to a halt.
AI with context: How product ontologies improve technical support chats
If the question-answering system only has generic AI without product-specific context, the answers will also be generic. The article shows how this can be solved with semantic information.