# What is few-shot prompting? — QANATONE > Few-shot prompting means adding a few worked examples to your prompt. The model picks up the pattern and answers in the same way. Kaynak: https://www.qanatone.com/en/nedir/few-shot-nedir/ --- [Explainers](https://www.qanatone.com/en/nedir/) # What is few-shot prompting? 15 Sep 2026 2 min read Prompting · Few-shot Few-shot prompting means adding a few worked examples to your prompt. The model picks up the pattern and answers in the same way. ## What is few-shot prompting? When you teach someone a new task, you often show two or three examples instead of explaining at length. Few-shot prompting works the same way: you put a few solved examples of the task into the [prompt](https://www.qanatone.com/en/nedir/prompt-nedir/) and the model infers the pattern. With a single example it is called one-shot; with none, [zero-shot](https://www.qanatone.com/en/nedir/zero-shot-nedir/). A model's ability to pick up a new task from examples in the prompt, without retraining, is called in-context learning. It became widely known with the GPT-3 paper in 2020, titled "Language Models are Few-Shot Learners". ## An example Task: label customer reviews as positive, negative or neutral. The prompt could look like this: - Review: "Arrived in a day, nicely packed." Label: positive - Review: "Smaller than in the photo." Label: negative - Review: "Ordered it, have not used it yet." Label: neutral - Review: "Lovely color, but it faded after the first wash." Label: ? The model answers the last review with a one word label in the same format. Without the examples it might have written a paragraph. ## When does it help? When the output format matters (a specific JSON structure, a fixed set of labels or your brand's tone), few-shot is often the cheapest and fastest fix. Including borderline cases, like the "lovely color, but" review above, shows the model how to decide where it would otherwise hesitate. ## Things to watch Keep the examples varied; if they are all positive, the model leans positive. Models are also sensitive to the order of examples, and the last one has an outsized effect. Every example costs [tokens](https://www.qanatone.com/en/nedir/token-nedir/). If you find yourself needing dozens of examples, [fine-tuning](https://www.qanatone.com/en/nedir/fine-tuning-nedir/) may become the cheaper option. ## More articles [Model Training · Fine-tuning ### What is fine-tuning and when do you need it? 15 Sep 2026 · 2 min](https://www.qanatone.com/en/nedir/fine-tuning-nedir/)[Architecture · Memory ### What is memory in AI assistants and agents? 15 Sep 2026 · 2 min](https://www.qanatone.com/en/nedir/ai-memory-nedir/)[Applications · Function Calling ### What is function calling in AI? 15 Sep 2026 · 2 min](https://www.qanatone.com/en/nedir/function-calling-nedir/)[Safety · Guardrails ### What are guardrails in AI? 15 Sep 2026 · 2 min](https://www.qanatone.com/en/nedir/guardrail-nedir/)[Reliability · Hallucination ### What is AI hallucination and why does it happen? 15 Sep 2026 · 2 min](https://www.qanatone.com/en/nedir/halusinasyon-nedir/)[Infrastructure · Inference ### What is inference in AI? 15 Sep 2026 · 2 min](https://www.qanatone.com/en/nedir/inference-nedir/)[Marketing · Influencers ### What is influencer marketing and how does it work? 15 Sep 2026 · 2 min](https://www.qanatone.com/en/nedir/influencer-marketing-nedir/)[Performance · Latency ### What is latency in AI applications? 15 Sep 2026 · 2 min](https://www.qanatone.com/en/nedir/latency-nedir/)