The INSPIRE‑KA project aims to enable users with limited IT expertise to perform complex data analyses. The starting point is the challenge of efficiently and transparently evaluating data with spatial and temporal dimensions – such as data from environmental or production systems – without requiring deep IT knowledge. To address this, the project harnesses the potential of large language models (LLMs) to generate interactive and explainable processing pipelines. In this approach, the LLMs do not produce the system’s answer directly; instead, they are used to plan and construct the data‑processing workflow, thereby avoiding typical risks such as hallucinations.