← Library · Core concept

Negative Prompting / Exclusionary Instructions

Beyond telling the AI what you *do* want, it's often powerful to tell it what you *don't* want. This is called negative prompting or providing exclusionary instructions. Explicitly stating elements, tones, or formats to avoid can prevent the AI from defaulting to undesirable patterns. For instance, when writing a product description, you might prompt: 'Write a product description for a new ergonomic office chair, but DO NOT use jargon like 'synergistic' or 'paradigm shift', and avoid overly technical specifications.' This guides the AI away from common pitfalls. Before: a product description full of buzzwords. After: a clear, concise, and accessible product description. This is particularly useful in image generation, where 'negative prompts' filter out unwanted elements.

In plain terms

It's like telling a chef not just what ingredients to use, but also 'no cilantro' or 'no spicy peppers' to ensure the dish meets your exact preferences.

Why it matters

Negative prompting hones the AI's output by explicitly removing unwanted elements, leading to cleaner, more targeted results that require less editing and better match your specific vision.

Learn one new AI thing every day.

Daily Deck sends you seven plain-English cards like this every morning. Free.

Start free