Rather than only telling an AI what you want, you also explicitly tell it what you don't want—exclude certain tones, avoid specific topics, skip particular formatting—which often produces better results than positive instructions alone. This mirrors how humans clarify requests: not just 'write something funny' but 'write something funny, but not mean-spirited.'
Negative prompting means explicitly telling AI what you do not want in a response, such as avoiding jargon, skipping disclaimers, or omitting bullet points, so the output matches your actual needs.
Most people only describe what they want, but defining what to exclude is equally powerful and dramatically reduces the number of revision rounds required to get a usable result.
Peri can explain this concept, give practical examples, help you decide whether it applies to your situation, or recommend a journey if appropriate.
Explore related journeys or tell Peri what you're working through.