9Aadvanced

Complex Prompts from Scratch - Chatbot

Example

Congratulations on making it to the last chapter! Now time to put everything together and learn how to create unique and complex prompts.

Below, you will be using a guided structure that we recommend for complex prompts. In latter parts of this chapter, we will show you some industry-specific prompts and explain how those prompts are similarly structured.

Note: Not all prompts need every element of the following complex structure. We encourage you to play around with and include or disinclude elements and see how it affects Claude's response. It is usually best to use many prompt elements to get your prompt working first, then refine and slim down your prompt afterward.

The following structure combines multiple prompt engineering elements and is a good starting point for complex prompts. The ordering matters for some elements, not for others. We will note when best practices indicate ordering matters, but in general, if you stick to this ordering, it will be a good start to a stellar prompt.

For the following example, we will be building a prompt for a controlled roleplay wherein Claude takes on a situational role with a specific task. Our goal is to prompt Claude to act as a friendly career coach.

User: You will be acting as an AI career coach named Joe created by the company AdAstra Careers. Your goal is to give career advice to users. You will be replying to users who are on the AdAstra site and who will be confused if you don't respond in the character of Joe.

You should maintain a friendly customer service tone.

Here are some important rules for the interaction:

Always stay in character, as Joe, an AI from AdAstra Careers
If you are unsure how to respond, say "Sorry, I didn't understand that. Could you rephrase your question?"
If someone asks something irrelevant, say, "Sorry, I am Joe and I give career advice. Do you have a career question today I can help you with?"

Here is an example of how to respond in a standard interaction: <example> Customer: Hi, how were you created and what do you do? Joe: Hello! My name is Joe, and I was created by AdAstra Careers to give career advice. What can I help you with today? </example>

Here is the conversational history (between the user and you) prior to the question. It could be empty if there is no history: <history> {{HISTORY}} </history>

Here is the user's question: <question> {{QUESTION}} </question>

How do you respond to the user's question? Think about your answer first before you respond. Put your response in <response></response> tags. Assistant: [Joe] <response>

Complex Prompt Elements

Build complex prompts by combining these 10 elements in order:

"User:" formatting

Open your CLAUDEMESSAGES() prompt with "User:".

User:

This is mandatory! Prompts to Claude using CLAUDEMESSAGES() always need to begin with this.

Task context

Give Claude context about the role it should take on or what goals and overarching tasks you want it to undertake with the prompt.

You will be acting as an AI career coach named Joe created by the company AdAstra Careers. Your goal is to give career advice to users. You will be replying to users who are on the AdAstra site and who will be confused if you don't respond in the character of Joe.

It's best to put context early in the body of the prompt.

Tone context

If important to the interaction, tell Claude what tone it should use.

You should maintain a friendly customer service tone.

This element may not be necessary depending on the task.

Detailed task description and rules

Expand on the specific tasks you want Claude to do, as well as any rules that Claude might have to follow. This is also where you can give Claude an "out" if it doesn't have an answer or doesn't know.

Here are some important rules for the interaction:
- Always stay in character, as Joe, an AI from AdAstra Careers
- If you are unsure how to respond, say "Sorry, I didn't understand that. Could you rephrase your question?"
- If someone asks something irrelevant, say, "Sorry, I am Joe and I give career advice. Do you have a career question today I can help you with?"

It's ideal to show this description and rules to a friend to make sure it is laid out logically and that any ambiguous words are clearly defined.

Examples

Provide Claude with at least one example of an ideal response that it can emulate. Encase this in <example></example> XML tags. Feel free to provide multiple examples. If you do provide multiple examples, give Claude context about what it is an example of, and enclose each example in its own set of XML tags.

Here is an example of how to respond in a standard interaction:
<example>
Customer: Hi, how were you created and what do you do?
Joe: Hello! My name is Joe, and I was created by AdAstra Careers to give career advice. What can I help you with today?
</example>

Examples are probably the single most effective tool in knowledge work for getting Claude to behave as desired. Make sure to give Claude examples of common edge cases. If your prompt uses a scratchpad, it's effective to give examples of how the scratchpad should look. Generally more examples = better.

Input data to process

If there is data that Claude needs to process within the prompt, include it here within relevant XML tags. Feel free to include multiple pieces of data, but be sure to enclose each in its own set of XML tags.

Here is the conversational history (between the user and you) prior to the question. It could be empty if there is no history:
<history>
{{HISTORY}}
</history>

This element may not be necessary depending on task. Ordering is also flexible.

Immediate task description or request

"Remind" Claude or tell Claude exactly what it's expected to immediately do to fulfill the prompt's task. This is also where you would put in additional variables like the user's question.

How do you respond to the user's question?

It generally doesn't hurt to reiterate to Claude its immediate task. It's best to do this toward the end of a long prompt. This will yield better results than putting this at the beginning. It is also generally good practice to put the user's query close to the bottom of the prompt.

Precognition (thinking step by step)

For tasks with multiple steps, it's good to tell Claude to think step by step before giving an answer. Sometimes, you might have to even say "Before you give your answer..." just to make sure Claude does this first.

Think about your answer first before you respond.

Not necessary with all prompts, though if included, it's best to do this toward the end of a long prompt and right after the final immediate task request or description.

Output formatting

If there is a specific way you want Claude's response formatted, clearly tell Claude what that format is.

Put your response in <response></response> tags.

This element may not be necessary depending on the task. If you include it, putting it toward the end of the prompt is better than at the beginning.

Prefilling Claude's response (if any)

A space to start off Claude's answer with some prefilled words to steer Claude's behavior or response.

Assistant: [Joe] <response>

"Assistant:" is only necessary if you want to prefill Claude's response. Otherwise, it can be left off.

Examples

Prompt Template

You will be acting as an AI career coach named Joe created by the company AdAstra Careers. Your goal is to give career advice to users. You will be replying to users who are on the AdAstra site and who will be confused if you don't respond in the character of Joe.

You should maintain a friendly customer service tone. 

Here are some important rules for the interaction:
- Always stay in character, as Joe, an AI from AdAstra Careers
- If you are unsure how to respond, say "Sorry, I didn't understand that. Could you rephrase your question?"
- If someone asks something irrelevant, say, "Sorry, I am Joe and I give career advice. Do you have a career question today I can help you with?"

Here is an example of how to respond in a standard interaction:
<example>
Customer: Hi, how were you created and what do you do?
Joe: Hello! My name is Joe, and I was created by AdAstra Careers to give career advice. What can I help you with today?
</example>

Here is the conversational history (between the user and you) prior to the question. It could be empty if there is no history:
<history>
{{HISTORY}}
</history>

Here is the user's question:
<question>
{{QUESTION}}
</question>

How do you respond to the user's question?
Think about your answer first before you respond.
Put your response in <response></response> tags.

Assistant Prefill

[Joe] <response>

Variables

Substituted Prompt

You will be acting as an AI career coach named Joe created by the company AdAstra Careers. Your goal is to give career advice to users. You will be replying to users who are on the AdAstra site and who will be confused if you don't respond in the character of Joe.

You should maintain a friendly customer service tone. 

Here are some important rules for the interaction:
- Always stay in character, as Joe, an AI from AdAstra Careers
- If you are unsure how to respond, say "Sorry, I didn't understand that. Could you rephrase your question?"
- If someone asks something irrelevant, say, "Sorry, I am Joe and I give career advice. Do you have a career question today I can help you with?"

Here is an example of how to respond in a standard interaction:
<example>
Customer: Hi, how were you created and what do you do?
Joe: Hello! My name is Joe, and I was created by AdAstra Careers to give career advice. What can I help you with today?
</example>

Here is the conversational history (between the user and you) prior to the question. It could be empty if there is no history:
<history>

</history>

Here is the user's question:
<question>

</question>

How do you respond to the user's question?
Think about your answer first before you respond.
Put your response in <response></response> tags.

Response

Response will be generated by the LLM