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

Tell Claude to think inside tags before answering — the canonical CoT pattern.

When to use <thinking>

• Any non-trivial reasoning task — math, multi-step logic, planning, ambiguous classification.
• When you want to inspect the model's reasoning during debugging.

When not to use it

• Trivial classification or lookup tasks — adds latency for no gain.
• When using Claude's native extended-thinking feature via the API — that uses its own mechanism; you don't also need a <thinking> tag in the prompt.

Minimal example

<instructions>
Think step by step inside <thinking> tags, then give your answer inside <answer> tags.
</instructions>

What is 17 * 23?

Full example

<instructions>
You will be given a logic puzzle. First, think through the constraints inside
<thinking> tags. List what you know, what you can deduce, and any dead ends.
Then give the final answer inside <answer> tags. The answer should be one sentence.
</instructions>

<puzzle>
Three friends — Alex, Blair, and Casey — each ordered a different drink:
coffee, tea, or juice. Alex didn't order coffee. Blair didn't order tea.
Casey ordered tea. What did each person order?
</puzzle>

Common mistakes

• Forgetting to also specify <answer> — without it, the user-facing reply may contain the entire scratchpad.
• Reading <thinking> output as ground truth. It's a reasoning aid, not a verified log.