Many typical best practices still apply to GPT-4.1, such as providing context examples, making instructions as specific and clear as possible, and inducing planning via prompting to maximize model intelligence. However, we expect that getting the most out of this model will require some prompt migration. GPT-4.1 is trained to follow instructions more closely and more literally than its predecessors, which tended to more liberally infer intent from user and system prompts. This also means, however, that GPT-4.1 is highly steerable and responsive to well-specified prompts - if model behavior is different from what you expect, a single sentence firmly and unequivocally clarifying your desired behavior is almost always sufficient to steer the model on course. - https://cookbook.openai.com/examples/gpt4-1_prompting_guide

Few-shot learning lets you steer a large language model toward a new task by including a handful of input/output examples in the prompt, rather than fine-tuning the model. The model implicitly "picks up" the pattern from those examples and applies it to a prompt. When providing examples, try to show a diverse range of possible inputs with the desired outputs.

Typically, you will provide examples as part of a developer message in your API request. Here's an example developer message containing examples that show a model how to classify positive or negative customer service reviews. - https://platform.openai.com/docs/guides/text?api-mode=responses#few-shot-learning

https://docs.anthropic.com/en/docs/build-with-claude/prompt-engineering/overview

https://www.lennysnewsletter.com/p/ai-prompt-engineering-in-2025-sander-schulhoff

https://learnprompting.org/blog/the_prompt_report

https://cookbook.openai.com/examples/gpt4-1_prompting_guide

https://platform.openai.com/docs/guides/text?api-mode=responses#few-shot-learning - Few Shot Learning

https://cookbook.openai.com/examples/partners/model_selection_guide/model_selection_guide