Sign in
Skip to solution
easyAI Engineering

What is the difference between zero-shot, one-shot and few-shot prompting?

192 views
01

Understand the problem

How in-context examples steer a model without any training.

few-shotzero-shotin-context-learningprompting
02

Attempt it yourself

Sketch your approach before reading the solution — that's what interviews test.

Nudge consolestandby

Stuck? Beam a request up — the console returns a conceptual nudge that guides your logic without spoiling the implementation.

03

Study the solution

Zero-shot gives only an instruction; one-shot/few-shot include example input-output pairs in the prompt so the model infers the pattern (in-context learning). Few-shot examples are the highest-leverage tool for format compliance and edge-case handling: pick diverse, correct examples and keep their format identical to t

Solution ready — 2 min read

Classified // press E to declassify

04

Read the code

Few-shot with hard negatives for a classifier
const prompt = [
  "Classify the ticket as: bug | feature_request | question.",
  "",
  'Ticket: "App crashes when I tap export" → bug',
  'Ticket: "Export to CSV would be great" → feature_request',
  // hard negative: sounds like a bug, is actually a question
  'Ticket: "Is export supposed to include archived items?" → question',
  "",
  "Ticket: " + JSON.stringify(ticketText) + " →",
].join("\n");
05

Join the discussion

Discussion (0)

Sign in to join the discussion.

No responses yet. Be the first to share what you think.

Transmission complete // awaiting log

KEEP THE
STREAK ALIVE.

Dossier 11 of 80 decoded in the AI Engineering track. One more won't hurt.

Back to track