Chapter 9 of Anthropic's interactive prompt engineering tutorial includes this complex legal services prompt that demonstrates retrieval over research with citation formatting, pre
A prompt chaining pipeline that first pulls verbatim relevant quotes from a long document, then uses those quotes to generate a grounded answer to your question. Use it when you ne
From the Anthropic cookbook's building moderation filter.ipynb . A production style moderation prompt that uses explicit ALLOW/BLOCK guidelines, a <thinking scratchpad, and an <out
RAG system prompt from the embeddings QA recipe. The closing sentence is what stops hallucinations on questions outside the retrieved articles. Paired role message: You answer ques
Writes a movie review covering plot, themes, acting, direction, and cinematography, with a personal emotional read. Source: https://github.com/f/awesome chatgpt prompts
Researches both sides of a topic, presents arguments for each, refutes opposing points, and draws conclusions backed by evidence. Source: https://github.com/f/awesome chatgpt promp
Explores philosophical questions, conducts theoretical research, and proposes ethical frameworks. Source: https://github.com/f/awesome chatgpt prompts
Two prompt chain for grounded QA. Prompt 1 pulls verbatim quotes; prompt 2 turns those quotes into the final answer. Forcing extraction first cuts hallucination dramatically. Promp
Guides you on enriching LLM prompts with database schemas, sample data, and table relationships to improve generated SQL quality. Use this when Claude is producing inaccurate or in
Microsoft's recommended structure for break the task down prompts. Uppercase section headers, delimiters and an explicit SEARCH "query" affordance make the output trivially parseab
Named entity recognition prompt that locks the model to a single, closed label set. Pinning the categories is what makes the output safe to feed into a downstream parser. User turn
