Why let Claude think?

Imagine being woken up and immediately asked to answer a series of complicated questions. You’d probably perform better if given some time to think through your answers first, right? The same applies to Claude!

Allowing Claude to reason through a problem before responding can lead to more accurate and intelligent outputs, particularly for multifaceted or challenging queries. By explicitly instructing Claude to think step-by-step, you encourage a more methodical and thorough approach to problem-solving.

Furthermore, examining Claude’s thought process can be invaluable for troubleshooting and identifying areas where your prompt instructions may be unclear or easily misinterpreted.

It’s important to note that thinking cannot happen without output! Claude must output its thinking in order to actually “think.”


How to prompt for thinking step-by-step

The simplest way to encourage thinking step-by-step is to include the phrase “Think step by step” in your prompt. For example:

RoleContent
UserAre both the directors of Jaws and Casino Royale from the same country? Think step by step.

Claude will then break down its thought process before providing a final answer:

RoleContent
Assistant (Claude’s response)To determine if the directors of the movies “Jaws” and “Casino Royale” are from the same country, let’s break it down into steps:

Step 1: Identify the director of the movie “Jaws.”
The director of “Jaws” is Steven Spielberg.

Step 2: Identify the country of origin for Steven Spielberg.
Steven Spielberg was born in Cincinnati, Ohio, United States.

Step 3: Identify the director of the movie “Casino Royale.”
The director of the 2006 movie “Casino Royale” is Martin Campbell.

Step 4: Identify the country of origin for Martin Campbell.
Martin Campbell was born in Hastings, New Zealand.

Step 5: Compare the countries of origin for both directors.
Steven Spielberg is from the United States, while Martin Campbell is from New Zealand.

Therefore, the directors of “Jaws” and “Casino Royale” are not from the same country.

For more complex queries, you can guide Claude’s thinking by specifying the steps it should take. Here’s an example:

RoleContent
UserUse the following clues to answer the multiple-choice question below, using this procedure:
1. Go through the clues one by one and consider whether each is potentially relevant
2. Combine the relevant clues to reason out the answer to the question
3. Map the answer to one of the multiple choice options: (a), (b), or (c)

Clues:
1. Miss Scarlett was the only person in the lounge.
2. The person with the pipe was in the kitchen.
3. Colonel Mustard was the only person in the observatory.
4. Professor Plum was not in the library nor the billiard room.
5. The person with the candlestick was in the observatory.

Question: Was Colonel Mustard in the observatory with the candlestick?
(a) Yes; Colonel Mustard was in the observatory with the candlestick
(b) No; Colonel Mustard was not in the observatory with the candlestick
(c) Unknown; there is not enough information to determine whether Colonel Mustard was in the observatory with the candlestick

By outlining a clear thinking process, you help Claude focus its reasoning on the most relevant information and ensure it thinks through all the necessary factors to perform well at its given task.


Capturing Claude’s thought process

To make it easier to separate Claude’s step-by-step reasoning from its final response, consider using XML tags like <thinking> and <answer>. You can instruct Claude to place its thought process inside <thinking> tags and its ultimate answer within <answer> tags.

Here’s an example prompt with this method:

RoleContent
User[Rest of prompt] Before answering the question, please think about it step-by-step within <thinking></thinking> tags. Then, provide your final answer within <answer></answer> tags.

You can even prefill the <thinking> tag in the Assistant role to guide Claude as to where to begin:

RoleContent
Assistant (prefill)<thinking>

Claude will then complete its thought process within the tags and provide its final answer:

RoleContent
Assistant (Claude’s response)[Reasoning through the problem step-by-step]
</thinking>

<answer>[Final answer]</answer>

Using tags makes it simple to extract just the final answer within <answer></answer> tags during post-processing if desired.


Some considerations

While encouraging step-by-step thinking can greatly enhance Claude’s responses, keep these points in mind:

  • Thinking cannot occur unless Claude is allowed to output its thought process. There’s no way to have Claude think privately and only return the final answer.
  • Prompting for step-by-step reasoning will increase the length of Claude’s outputs, which can impact latency. Consider this tradeoff when deciding whether to use this technique.

Additional resources

  • Prompt engineering techniques: Explore other strategies for optimizing your prompts and enhancing Claude’s performance.
  • Anthropic Cookbook: Browse a collection of Jupyter notebooks featuring copy-able code snippets that demonstrate highly effective and advanced techniques, integrations, and implementations using Claude.
  • Prompt library: Get inspired by a curated selection of prompts for various tasks and use cases.