<instructions> — when and how to use it in Claude prompts

The most important tag. Wraps the system-level instructions you want Claude to follow throughout the conversation.

When to use <instructions>

• Defining the model's task, persona, constraints, or response format.
• Placing system-prompt-like content inside a user message when the API system field isn't enough.

When not to use it

• Don't use it to wrap the user's actual question — use a separate tag like <question> or just unwrapped prose for that.
• Don't restate the same instructions multiple times inside one prompt — Claude follows the first <instructions> block; redundancy invites contradiction.

Minimal example

<instructions>
Summarize the article below in 3 bullet points.
</instructions>

Full example

<instructions>
You are a technical writer. Read the article inside <article> and produce:
- A 1-sentence TL;DR
- 3 bullet points of key takeaways
- 1 open question the article does not answer

Use Markdown. Do not invent facts. If the article doesn't mention something, say so.
</instructions>

<article>
{{ user_provided_article }}
</article>

Common mistakes

• Putting the question inside <instructions>. Claude may treat the question text as an instruction to follow rather than a query to answer.
• Nesting other content tags inside <instructions>. Keep instructions flat; let context, examples, and documents be siblings.