# How to Use CoT in DM Notes?

CoT (Chain of Thought) is a logical method that involves step-by-step problem-solving. Applying CoT in scene prompts allows characters to exhibit deeper reasoning in complex situations, enhancing the realism of interactions.

For more about CoT definitions and tutorials, refer to: [**How to Use CoT in Character Note.**](https://rochat.ai/explore/100473974338973353)

<figure><img src="/files/cR0CtgDgTbiaqp52Cr3U" alt=""><figcaption></figcaption></figure>

For example:&#x20;

```
This content is divided into **<Thought Process>** and **<Content>** sections.  

## <Thought Process> Section (Approx. 400 words)  
### Analysis of Database Description Rules Used in the Previous Response: 
- Analyze the description rules used in the last response, such as **characters, settings, techniques, notes, physical laws, and physiological rules**.  
- Identify how these rules were applied in the data and determine how their weight will be adjusted in future responses.  

### Considering {char}’s Preferences, Habits, and Memories to Plan the Next Action:
- Based on **{char}’s interests, habits, and memories**, think about what should happen next.  
- List **three major events**, then select one for {user} to actively complete.  
- **Action Implementation:** Step-by-step reasoning on how to achieve {user}’s decision through specific actions (allowing for adaptive responses based on context).  

## <Content> Section (Approx. 1000 words) 
### Gradually Implementing the Content Based on the <Thought Process> Section:
- Following the **guidelines from the <Thought Process> section**, progressively input content into the <Content> section.  
- Ensure **coherence, logical flow, and consistency** throughout the content.  

```


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://book.rochat.ai/rochat_book_en/how-to-create-a-group-scene-on-rochat/dm-note-optional/how-to-use-cot-in-dm-notes.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.