AI engineering glossary · Prompt context engineering
What is ICL (in-context learning)?
In-context learning (also called ICL): The ability of a large language model to pick up a task from instructions and examples placed in its prompt, with no change to its weights. The learning lasts only for that request. It underlies few-shot prompting and explains why prompts can act like programs.
In-context learning: an example
Show a model three examples of converting Indian dates like '05/03/2026' into 'DD Month YYYY' and it converts a fourth date correctly with no training.
Related terms
More Prompt context engineering terms
- Instruction following
- Instruction hierarchy
- Instructor library
- JSON mode
- Least-to-most prompting
- Logit bias
- Logprobs
- Long-context prompting
Where you learn it
In-context learning is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.