学ぶ

目標から推論モデル向けのプロンプトまで、強いプロンプトの要素を学ぶ8つの短いレッスンです。各レッスンには解説付きの例と、あなたのプロンプトと同じルーブリックで採点される演習があります。

このレッスンはまだお使いの言語に対応していないため、別の言語（English）で表示しています。

1. 1目標と成功基準6分

   Say what success looks like

   State the outcome you want and how you will judge it, so the model aims at something you can check.

2. 2コンテキストと入力6分

   Give the model what it cannot know

   Supply the facts, material and situation the task depends on, clearly separated from your instructions.

3. 3対象読者と用途6分

   Write for someone

   Say who will read the output and what they will do with it, so the level, emphasis and tone follow.

4. 4制約と範囲6分Pro

   Draw the boundaries

   Set the scope, the must and must-not, the sources and what to do when unsure, and say which rule wins when they clash.

5. 5タスクの指示6分Pro

   Say what to do, in order

   Turn a tangle of requests into clear, ordered steps, with the reason for the order, a stopping point and a plan for a step that fails.

6. 6出力の仕様6分Pro

   Agree the shape of the answer

   Specify the format, structure, length, language and tone of the result, and use a schema when a program will read it.

7. 7例と参考資料6分Pro

   Show as well as tell

   When words cannot pin down the format or judgement you want, give a few varied, delimited examples, including a hard case.

8. 8モデル適合性と健全性7分Pro

   Prompting reasoning models in 2026

   Current models reason for themselves: set the effort instead of asking for step-by-step thinking, write calmly, put long material first, explain why, and use structured outputs instead of prefill.