In-context learning (ICL) allows large language models to adapt to new tasks by embedding demonstrations directly within the input prompt, eliminating the need for parameter updates or fine-tuning. This paradigm shift enables models to learn from examples at inference time, making it a cornerstone technique for prompt engineering and rapid task adaptation. Unlike traditional training approaches, ICL leverages the model's pre-existing knowledge and pattern recognition capabilities to generalize from a small number of contextual examples. The effectiveness of ICL depends critically on example selection, ordering, and formatting—subtle variations can dramatically impact model performance, making prompt design as important as model architecture itself.