Learn

Zero-shot: asking with no examples at all

Zero-shot is asking a model to perform a task using only an instruction, with no worked examples in the prompt. The model relies entirely on what it learned during training to produce the answer.

At a glance

What it is
Asking with an instruction only, no examples in the prompt
What it leans on
What the model already learned in training
Opposite of
Few-shot, where you include a handful of examples
The upside
The shortest prompt, leaving the most room in the context window

What is zero-shot?

Zero-shot is the plainest way to ask: you give the model an instruction and nothing else, no worked examples, and let it answer from what it already learned in training. “Summarise this in one sentence.” “Classify this message as urgent or not.” If the model has seen enough of that kind of task during training, it just does it. The prompt carries the request and only the request.

It is the natural default, and often the right one. For common tasks a capable model handles zero-shot cleanly, and you have spent no examples to get there. That keeps the prompt short, which leaves more of the context window for the actual input and the answer.

When does zero-shot start to wobble?

Zero-shot leans entirely on the model’s training, so it wobbles exactly where that training is thin or your needs are specific. The answer may be correct but in the wrong format, or it may drift from one run to the next because nothing in the prompt pinned down the shape you wanted.

That is the moment to add examples and move to few-shot. The trade is simple: a zero-shot prompt is shorter and faster to write, while a few-shot prompt spends context on examples to buy consistency. Start zero-shot, and reach for examples only when the plain instruction stops being enough.

Zero-shot fits when

  • The task is common and the model clearly already knows how to do it
  • A plain instruction is enough to get the format you want
  • You want the shortest prompt, saving context for the input and answer
  • You are testing what the model can do unaided, with no leading examples

Reach for few-shot when

  • The output format keeps drifting and an example would pin it down
  • The task is easier to show than to describe in words
  • Tone or style matters and a sample anchors it faster than instructions
  • Zero-shot answers are inconsistent run to run

Related terms

← All terms Reviewed: June 2026