Back to guide/Education & Learning

Constraint Setting

Explicit DO and DO NOT lists are the easiest way to control AI output. 'Do not use jargon' is more effective than 'write simply'. The 'ask me rather than assume' instruction prevents the AI from making wrong guesses.

prompt-engineering-beginnerstaskdo_1do_2
Edit View
Prompt
{{task}}

Constraints:
- DO: {{do_1}}, {{do_2}}
- DO NOT: {{dont_1}}, {{dont_2}}
- Audience: {{audience}}
- Maximum length: {{max_length}}

If you're unsure about something, ask me a clarifying question rather than making assumptions.

Variables to customize

{{task}}{{do_1}}{{do_2}}{{dont_1}}{{dont_2}}{{audience}}{{max_length}}

Why this prompt works

Explicit DO and DO NOT lists are the easiest way to control AI output. 'Do not use jargon' is more effective than 'write simply'. The 'ask me rather than assume' instruction prevents the AI from making wrong guesses.

Save this prompt to your library

Organize, version, and access your best prompts across ChatGPT, Claude, and Cursor.

Related prompts

Sentiment Analysis

Requesting confidence and key phrases forces the model to justify its classification rather than guessing. The structured output format works zero-shot because sentiment analysis is well-understood by LLMs.

Key Information Extraction

Listing the exact fields to extract removes guesswork. The 'Not specified' instruction prevents hallucination when information is missing -- a common failure mode without this guardrail.

Question Answering with Source

Grounding the answer in source material and instructing the model to refuse when information is missing dramatically reduces hallucination -- the biggest risk in zero-shot Q&A.

Math Word Problem Reasoning

Explicit numbered steps force the model to decompose the problem rather than guessing. The verification step catches arithmetic errors before the final answer.