Quality is decisive for success or failure in production. Even small defects — be it a scratch, a dimensional deviation or a faulty weld — can lead to costly problems later on. Classic visual inspections by employees quickly reach their limits: they are time-consuming, subjective and can hardly be carried out seamlessly with high production volumes. Modern systems for automated visual inspection therefore rely on cameras, edge devices and cloud-based analyses to identify errors quickly, reliably and scalably.

LLMs are strong in general knowledge but fail because of company data. The Model Context Protocol (MCP) breaks down data silos and creates a standard that allows AI systems to directly access tools such as Jira, CRM or databases. Read the blog to find out why MCP is becoming a game changer for productive AI.

This article discusses a technically proven architecture for transmitting industrial sensor data via MQTT to the Azure cloud, presents relevant components and highlights challenges and solutions during implementation.

Public tenders play a major economic role for many companies. At the same time, tendering processes on the bidder side are extremely labor-intensive and prone to errors. This blog posts suggests solutions that improve efficiency and precision in tender management while ensuring compliance with all compliance requirements.

In a world where physical and digital boundaries are becoming increasingly blurred, merger strategies — the integration of physical products, digital services, and interdisciplinary ecosystems — are becoming increasingly important. These approaches not only create new added value, but also define the business models of the future. But how can data and AI be seamlessly integrated into products, services and systems?

Visual inspection is an essential part of quality assurance in industrial production. It is used to identify faulty products before they reach the end customer. While manual visual inspection was the standard for decades, modern technologies based on artificial intelligence and image processing are bringing significant improvements. In this article, we look at the challenges of manual inspection, the benefits of automated testing, and the technical design of such systems.

In today's data-driven world, manufacturing companies are faced with the challenge of using large amounts of operating and machine data efficiently. This data is often stored in isolated systems, which makes holistic analysis difficult. Deploying a central data lake with integrated data visualization using dashboards provides a powerful solution for aggregating, analyzing, and presenting data from various sources in real time. In the following, we look at how such an approach can be implemented technologically, what opportunities this offers for companies and which problems can be solved as a result

Digital transformation is driving companies to fundamentally rethink and modernize their business processes. In this context, AI-based workflow automation is gaining in importance, as it promises huge efficiency gains. However, AI-based workflows go one step further: They not only enable processes to be carried out more quickly and efficiently, but also enable data-driven analyses to make complex decisions in real time and to adaptively control processes.

In recent years, technological developments in artificial intelligence (AI) and machine learning have opened up many new possibilities. Two concepts that repeatedly emerge in this context are Large Language Models (LLMs) and Data Lakes. When used together, both technologies have the potential to significantly transform how companies handle data, analyze it, and extract knowledge.

Federated Learning offers an innovative solution by enabling collaborative learning from distributed data without centralization. This approach effectively enhances machine performance, preserves data privacy, and promotes efficient knowledge sharing among decentralized participants. In this article, we delve into the fundamentals of federated learning, its functionality, and real-world success stories.

To start and successfully run an IoT project, you need to be able to easily access and process information from many different devices, sensors, and machines in your IoT network. To do this, it is important that all these components can exchange data with each other in the same way: The OPC UA protocol provides the bridge to make this possible.

Industry 4.0 evolution depends on the transition to Edge AI, particularly following the era of cloud computing and the IoT. The adoption of Edge AI becomes the logical next step, as it holds the key to unlocking Industry 4.0's full potential.