In AI, inference is the process of using a trained model to generate a prediction, classification, or output from new input data.
Inference is distinct from training. Training is the process of building the model by adjusting its parameters on a large dataset. Inference is using the finished model to respond to new inputs — for example, generating a reply to a prompt or classifying a new image.
When you interact with an AI tool, you are triggering inference. The model itself does not update or learn from your interaction during inference (unless the system is specifically designed to do so).