— Techniques
Few-Shot Prompting
Showing the AI 2-5 examples of the desired output before asking for a new one.
What is Few-Shot Prompting?
Few-shot prompting means including 2-5 worked examples in your prompt before asking the LLM to do a new task. The model picks up the pattern from the examples and applies it. Especially useful for output-formatting tasks where you want consistent structure (JSON schemas, specific tones, custom layouts).
— Related
Terms connected to Few-Shot Prompting
Techniques
Prompt Engineering
The craft of designing inputs to LLMs to get reliable, high-quality outputs.
Open →Techniques
Chain-of-Thought (CoT)
A prompting technique where you ask the AI to think step-by-step before answering.
Open →Techniques
Zero-Shot Prompting
Asking the AI to do a task with no examples, just instructions.
Open →— Apply this
From definitions to deployed projects.
Knowing what a term means is step one. ONROL's AI Generalist track gets you shipping projects that use it.
Reserve Free Masterclass