Prompts tagged "xml" in the PromptCraft library.
把指令、資料、規則、schema 用 XML 標籤包起來餵給 AI，結構化抽取任務實測比 Markdown 標題少約 28% 出錯。
Five quantifiable techniques from an AI engineer's hundreds of hours testing across GPT-4, Claude, and Gemini: CoT scaffolding, persona + goal + anti-goal, XML being 28% more accurate than markdown, negative examples outperforming positive ones, and prompt chaining beating the mega-prompt.