> ## Documentation Index
> Fetch the complete documentation index at: https://docs.convocore.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Formatting your Prompts

Proper formatting of prompts is crucial for effective communication with AI models. Here are some tips and tricks on using the formatting languages of the GPT models in `markdown` and the anthropic models in `xml`.

## Key Concepts

<CardGroup cols={2}>
  <Card title="Emphasis" icon="bold">
    Highlight important information using various text styling techniques.
  </Card>

  <Card title="Structure" icon="layer-group">
    Organize your prompt with headings, lists, and nested elements.
  </Card>
</CardGroup>

## Formatting Techniques

Here is everything you need to craft effective prompts in markdown and xml formatting:

<Tabs>
  <Tab title="Markdown">
    <Accordion title="Basic Formatting" icon="text-size">
      ```markdown theme={null}
      *Italic text* for mild emphasis
      **Bold text** for strong emphasis
      ***Bold and italic*** for extra strong emphasis
      `Code-style text` for technical terms or commands
      ```
    </Accordion>

    <Accordion title="Headings and Structure" icon="heading">
      ```markdown theme={null}
      # Main Prompt Title
      ## Section 1: Context
      ### Background Information
      ### Current Situation
      ## Section 2: Task Description
      ```
    </Accordion>

    <Accordion title="Lists and Steps" icon="list">
      ```markdown theme={null}
      1. First step
      2. Second step
      3. Third step
      - Bullet point 1
      - Bullet point 2
      - Sub-point A
      - Sub-point B
      ```
    </Accordion>

    <Accordion title="Code Blocks" icon="code">
      ````markdown theme={null}
      ```python
      def example_function():
          return "This is an example"
      ````

      ````
      ```json
      {
        "key": "value",
        "array": [1, 2, 3]
      }

      ````
    </Accordion>
  </Tab>

  <Tab title="XML">
    <Accordion title="Basic Structure" icon="sitemap">
      ```xml theme={null}
       <prompt>
         <context>This is the context</context>
         <instruction>This is the main instruction</instruction>
         <important>This is crucial information</important>
         <example>This is an example</example>
       </prompt>
      ```
    </Accordion>

    <Accordion title="Roles and Dialogue" icon="comments">
      ```xml theme={null}
      <conversation>
        <human>What's the weather like today?</human>
        <assistant>I don't have real-time weather data. Please check a reliable weather website or app for your location.</assistant>
      </conversation>
      ```
    </Accordion>

    <Accordion title="Nested Structures" icon="network-wired">
      ```xml theme={null}
      <prompt>
        <context>
          <background>Relevant background information goes here.</background>
          <current_situation>Description of the current scenario.</current_situation>
        </context>
        <task>
          <primary_objective>Main goal of the task</primary_objective>
          <secondary_objectives>
            <objective1>First secondary objective</objective1>
            <objective2>Second secondary objective</objective2>
          </secondary_objectives>
        </task>
      </prompt>
      ```
    </Accordion>

    <Accordion title="Attributes and CDATA" icon="code">
      ```xml theme={null}
      <instruction type="main" priority="high" tone="professional">
        Craft a response addressing the user's concern.
      </instruction>
      <example_code>
      <![CDATA[
      def complex_function(x, y):
          return x * y + (x / y) if y != 0 else "Error: Division by zero"
      ]]>
      </example_code>
      ```
    </Accordion>
  </Tab>
</Tabs>

#

<Warning>
  Always test your formatted prompts to ensure they produce the desired results with your specific AI model.
</Warning>

#

<Card title="Advanced Formatting Tips" icon="lightbulb">
  <Steps>
    <Step title="Combine Formats">
      For complex prompts, consider using a combination of Markdown and XML techniques to leverage the strengths of both formats.
    </Step>

    <Step title="Model-Specific Formatting">
      Some AI models have specific formatting preferences:

      * GPT models typically work well with Markdown
      * Anthropic models are designed to interpret XML
        Always consult the model's documentation for best results.
    </Step>

    <Step title="Test and Iterate">
      Experiment with different formatting styles and structures. Test your prompts with the target AI model and refine based on the results.
    </Step>
  </Steps>
</Card>

#

By mastering these formatting techniques and utilizing appropriate structures, you can create highly effective prompts that clearly communicate your intentions to AI models, resulting in more accurate and useful responses.

Now that you know the proper formatting, read our comprehensive guide on how to write your [system prompt](/agent-creation/system-prompt/step-1-define-the-tone-and-objective).