Together with the NETZSCH Group, we designed LabV, took a key role in its development, and brought it to market as a product that helps laboratories make better use of their data:

• Data aggregation: LabV brings together data from laboratory instruments on a central data management platform. A smart mapper is used to process the different data formats and store them in a homogenized format.
• Data integration: The merged data is organized in projects and can be combined with other data sources. This allows project details to be obtained from ERP systems or links to be created between the laboratory data and the associated MES data.
• Data analysis: Data can be searched for specifically within the platform and further analysis can be carried out, e.g., by adding statistical evaluations or graphical representation.
• Data preparation: Project results can be automatically exported to test reports or comparable forms of documentation using Office templates.
• LLM support: With the help of the LabV assistant, further complex searches and analyses can be carried out in the data using natural language instructions. LabV integrates the database with the analysis functions of Wolfram Mathematica and makes it possible to use documents for further research.

Together with the Federal Institute for Vocational Education and Training (BIBB), we designed and developed Lea-KI, an intelligent chatbot for the Leando platform that helps examiners and vocational trainers easily access relevant information and educational resources.

• Natural language assistance: Lea-KI enables users to interact with the platform through intuitive conversations and quickly find answers to questions related to vocational education, examination procedures, and current developments.
• Regulatory guidance: The chatbot provides easy access to information on new regulations, updated standards, and relevant policy changes, helping users stay informed about the latest requirements in vocational training and assessment.
• Source-based information: Lea-KI delivers reliable answers supported by references and official sources, allowing users to verify information and explore topics in greater depth.
• Personalized knowledge discovery: Based on user questions and interests, the system recommends relevant topics, documents, and resources that support continuous learning and professional development.
• Learning pathway recommendations: Users are guided to further websites, educational content, and structured learning journeys, creating a seamless bridge between information retrieval and skills development.

By combining intelligent search, trustworthy information, and personalized recommendations, Lea-KI improves knowledge accessibility across the vocational education ecosystem and helps trainers and examiners efficiently navigate complex and constantly evolving information landscapes.

In this project, a scouting process was conducted to compile a long list of over 50 relevant AI use cases across four different industries, each briefly described according to defined criteria.

‍

A particular focus was on data strategies used in other industries, how data is interconnected, and how companies collaborate with upstream and downstream partners along the value chain to create cross-company platforms.

‍

Six use cases selected by the client were explored in greater depth through deep dives and qualitative interviews.

Determining suitable settings for injection molding machines is often time-consuming, requiring manual trials or complex simulations. Together with Sick AG and the Hong Kong Industrial AI and Robotics Centre (FLAIR), we developed the AI-driven Molding Assistant (AIMA) – a software solution that leverages machine learning to optimize injection molding processes with minimal manual effort.

‍

Key elements of the project:

• Collection of experimental data: Importing datasets from initial experiments or simulations that contain machine settings and the resulting quality key performance indicators (KPIs).
• Training of ML models: Processing the data to automatically train various ML models that map the complex relationships between settings and product quality.
• Integration of an optimization module: Utilizing the trained models in a module that determines the optimal machine parameters based on weighted quality objectives.
• Application for quality prediction: Using the ML models to predict component quality for new, untested machine settings, thus avoiding further costly experiments.

As a result, optimal machine parameters can be determined much faster and more efficiently with the AI-powered assistant. The software simplifies and standardizes the optimization process, lowers the barriers to using statistically sound methods, and thus supports broader application within the company.

‍

Get more insights about AIMA

‍

Together with WIN.DN and Sihl, we developed an AI-powered troubleshooting agent for the production plant “Frieda”, enabling production staff to access operational knowledge through natural language conversations.

• AI-guided troubleshooting: Operators can describe machine issues in natural language and receive concise, action-oriented recommendations for problem resolution.
• Knowledge integration: The solution consolidates information from shift reports, FMEA documentation, technical literature, and project documents into a single conversational interface.
• Source-based recommendations: All answers are grounded in documented knowledge sources and include references to ensure transparency and trustworthiness.
• Continuous learning: A built-in learning loop allows employees to contribute new operational knowledge, which is reviewed and added to the knowledge base through a controlled governance process.

Together with the Hong Kong Industrial Artificial Intelligence & Robotics Centre (FLAIR), we developed the following AI solutions in cooperation with various industry partners:

• Chat With Your Dashboard: LLM-based chat application that can answer questions about data visualized on a dashboard. For example: What was the average OEE in the last week? Was there an anomaly for temperature zone 1 in the last hour?
• AI-Assisted Derivation of Production Parameters: Web app that allows training of selected models on data from an injection molding process.  Subsequently, the trained models can be employed to predict product quality KPIs from the settings of the injection molding machine.
• Maintenance Guidance: LLM-powered application, which has a general understanding of wear components, their failure mode, their causes and the corresponding maintenance and servicing measures to guide and support maintenance personnel.  
• AI Assistant for Assembly Automation Engineers: LLM-based chat application that helps automation engineers make the right machine and equipment selection when designing a new assembly line.