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:
For example:
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.
