Computer vision is becoming a key enabler of smart manufacturing, from quality inspection to robotic automation. Yet traditional development of AI models often requires large datasets, specialized expertise, and significant time. In this talk, we explore how no-code computer vision platforms are changing this landscape allowing engineers, operators, and domain experts to build, train, and deploy models without deep AI backgrounds. We’ll look at real examples from manufacturing and robotics to show how faster iteration, simpler data workflows, and scalable deployment can move automation projects from concept to production.

Computer vision is becoming a key enabler of smart manufacturing, from quality inspection to robotic automation. Yet traditional development of AI models often requires large datasets, specialized expertise, and significant time. In this talk, we explore how no-code computer vision platforms are changing this landscape allowing engineers, operators, and domain experts to build, train, and deploy models without deep AI backgrounds. We’ll look at real examples from manufacturing and robotics to show how faster iteration, simpler data workflows, and scalable deployment can move automation projects from concept to production.

It is possible to implement AI-based solutions without coding. In this workshop, I will reshape an old application of mine for fraud detection. First I will read documents from a dataset of contracts, then find the frauds, and finally use GenAI to send the customer an alert email in their preferred language. It takes just three nodes to generate the email text: Authenticate – Connect – Prompt. With a few more nodes, using RAG, I can also generate the alert email from a context document.