Artificial Intelligence & Machine Learning
We integrate LLMs for text generation and chatbots, and vision AI for image and video analysis, to automate processes and surface knowledge.
devs group builds AI solutions for companies in Switzerland: LLM integration, RAG and agent systems, plus vision AI for image and video analysis. Operated sovereignly on request, on Swiss infrastructure and in line with the revised Swiss Data Protection Act. Our expertise spans two central areas of AI.
Large language models (LLMs)
We build tailored AI solutions on capable large language models. These technologies help you create real value by automating text-based processes.
Text generation: automate the creation of content, reports or marketing material.
Chatbots: build intelligent, interactive chatbots for better customer communication and efficient support.
Knowledge retrieval: pull specific information out of large bodies of data, to speed up decision-making.
Vision AI
In vision AI we specialise in analysing and processing visual data. We help you automate processes and extract valuable insight from images and video.
Image recognition: identify and classify objects, faces or scenes in images.
Object detection: locate and track specific objects in real time.
Video analysis: extract relevant information from video material, to automate or monitor complex processes.
Frequently asked
Can an AI agent comply with the revised Swiss Data Protection Act?
Yes, if the architecture supports it: an audit log under Art. 4 DPO, human-in-the-loop gates for sensitive actions, and clarity about where personal data actually ends up. The four requirements the revised act places on an AI system are set out provision by provision in A revDSG-compliant AI architecture.
Can we run an LLM ourselves in Switzerland?
Yes. For sensitive data we run open-weight models on Swiss infrastructure, with GPU scheduling on Kubernetes. A provider comparison, the cost arithmetic, and the points at which sovereignty breaks are in Sovereign AI inference in Switzerland.
Which models do you work with?
Whichever model fits the task and your data protection requirements: Claude, OpenAI and Gemini through their APIs, or self-hosted open-weight models where data must not leave the building. We build the architecture so the model stays replaceable.
How do you secure quality when AI writes the code?
Through architecture decisions and reviews by people. AI multiplies the amount of code; our job is to make sure that produces less code, not more. How we do that in practice is in AI writes the code. Who writes the architecture?