Reservoir modelling workflows are subject to large uncertainties on every step starting from interpretation of exploration data, coming up with a reservoir modelling concept, describing reservoir characteristics and property distribution, integration of dynamic data and model calibration and update as new data become available. Modern development of AI tech opens outstanding opportunities to handle the above generic tasks with the methods designed to handle diverse and noisy data. AI can discover patterns in data, describe complex geological patterns with dependencies learned from data, adapt models to data and search for a range of possible optimal development options subject to uncertainty. Effective AI application to reservoir modelling workflows relies on the ability to ensure interpretability of the machine learning model outcomes. This can be achieved by embedding the domain context into the AI model structure, so the data are no longer treated as merely digital values but the variables with physical meaning and interpretation in the subsurface context. In this overview demonstrates a few examples of how AI tech can help elicit and describe uncertainty in a geologically consistent way to ensure realism of geological interpretations and geomodel outcomes. AI applications will cover several steps of reservoir modelling workflow including: (1) AI seismic segmentation and geobody interpretation with unsupervised learning (Corlay in Fast Detection of Geobodies in 3D Seismic with Unsupervised Segmentation, 2023). (2) Constrain geological conceptual modelling with learning from outcrops (Nathanail in Capturing interpretational uncertainty of depositional environments with Artificial Intelligence, 2023). (3) Populate facies in meandering fluvial reservoir models based on learning from depositional process modelling with generative adversarial networks (GANs) (Sun in Use of Generative Learning to Improve Realism in Fluvial Facies Modelling, 2023). (4) Dynamic and static data integration with variational autoencoders and uncertainty representation via latent space to predict reservoir dynamics (Sishaev History Matching and Uncertainty Qualification of Reservoir Performance with Generative Deep Learning and Graph Convolutions, 2024). The work will demonstrate how to gain better understanding and representation of associated geological uncertainty when geological domain knowledge is embedded into the AI algorithms’ structure.