Flashcard: what is few shot prompting and what does the 'few' actually refer to? · Zenaique

Attempt it

Few shot prompting includes 2-8 worked input output examples in the prompt before the actual query. The 'few' is the count of demonstrations. The model imitates the demonstrated pattern at inference time through in context learning, with no weight updates: nothing is being fine tuned. Examples are usually placed close to the query (at the end of the prompt) so attention can use them, and they should be diverse enough to cover the kinds of inputs the model will see in production. Few shot is the standard upgrade from zero shot when a task has an unusual output format or a domain specific label set.

Your answer

Quick reference

TL;DR

Few shot prompting prepends 2-8 worked input-output examples to the query so the model can imitate the pattern through in context learning, with no weight updates.

Memory aid

Sign in for the mnemonic that makes this stick. See Pro pricing.

Easy to grasp

Imagine asking a new intern to label customer feedback. If you just say 'label these,' they will probably invent their own categories. So you show them three already-labeled examples first: this one is positive, this one is negative, this one is neutral. Now they know what shape your labels take and can copy the pattern on the next ten. Few shot prompting is the same trick with a language model. You drop in two to eight worked examples right before the actual question, and the model imitates the demonstrated pattern. The model is not being trained or retrained; it is just reading the examples in the same prompt and matching the shape. The training all happened earlier; this is on the fly imitation.

Key concepts

Few shot prompting In context learning Zero shot prompting

Detailed answer & concept explanation

~6 min read

Everything you need to truly understand this topic: intuition, mechanics, step by step explanation, code, formulas, and worked example. Click to expand.

Everything you need to truly understand this topic: intuition, mechanics, step by step explanation, code, formulas, and worked example.

Sign in for 5 free unlocks/day or go Pro for unlimited. See Pro pricing.

Quick scan · 2–4 min

Everything important, quickly.

3 min: define few shot, explain in context learning, name placement and diversity rules, and show how prompt caching changes the cost story.

Real-world examples

Real products, models, and research that use this idea.

Cursor and GitHub Copilot Chat assemble dynamic few shot examples from the user's own repository before each completion, so the model imitates the project's actual coding style.
Claude Opus 4.7 documentation recommends 3-5 examples for most classification tasks, with prompt caching turned on so the prefix is paid for only once per session.
OpenAI's structured output guides show few shot prompts that lock the model into a custom JSON schema by demonstrating the exact format two or three times.
LangChain's FewShotPromptTemplate and SemanticSimilarityExampleSelector let teams pull the most relevant examples from a training pool by embedding similarity to the current query.

Interviewer follow-ups

What an interviewer would ask next. Try answering before peeking at the approach.

QHow would you pick which few shot examples to include for a given task?

Sign in or go Pro to see the approach for this follow-up.

QWhy does the order of few shot examples sometimes matter for accuracy?

Sign in or go Pro to see the approach for this follow-up.

QWhen should you stop adding few shot examples and fine tune instead?

Sign in or go Pro to see the approach for this follow-up.

Don't say this

Red flags and common mistakes that signal junior thinking. Click to expand.

Most common mistake

Believing the model is being fine tuned by your few shot examples. Nothing is updating in the weights; the model is doing in context pattern matching for that one call and forgets the examples on the next request.

Sign in or go Pro to see all red flags and common mistakes. See Pro pricing.

60-second cheat sheet

The night-before-the-interview bullets. Scan these on the way to the call.

Sign in for 5 unlocks/day or go Pro for unlimited revision sheets. See Pro pricing.

References

Primary sources. Skim if you want the original framing.