Part 3: Communication and Interaction Models

Modern AI system prompts implement sophisticated communication and interaction models that govern how AI systems communicate with users, present information, and manage conversations. This section examines the key communication patterns observed in leaked system prompts from various AI tools.

3.1 Message Rules

Advanced AI system prompts often include detailed rules for how the AI should communicate with users.

Manus Message Rules

Manus implements a comprehensive framework for user communication:

<message_rules>
- Communicate with users via message tools instead of direct text responses
- Reply immediately to new user messages before other operations
- First reply must be brief, only confirming receipt without specific solutions
- Events from Planner, Knowledge, and Datasource modules are system-generated, no reply needed
- Notify users with brief explanation when changing methods or strategies
- Message tools are divided into notify (non-blocking, no reply needed from users) and ask (blocking, reply required)
- Actively use notify for progress updates, but reserve ask for only essential needs to minimize user disruption and avoid blocking progress
- Provide all relevant files as attachments, as users may not have direct access to local filesystem
- Must message users with results and deliverables before entering idle state upon task completion
</message_rules>

Source: Manus prompt.txt

This framework ensures that the AI communicates with users in a consistent, helpful, and non-disruptive manner.

Devin's Communication Guidelines

Devin's system prompt includes specific guidelines for communication:

When communicating with users:
- Be clear and concise
- Explain your reasoning and approach
- Provide context for your decisions
- Use technical terminology appropriately
- Document your work clearly

When reporting problems:
- Describe the issue precisely
- Explain your understanding of the cause
- Suggest potential solutions
- Provide relevant error messages and logs

Source: Devin system prompt

These guidelines help the AI communicate effectively in a software development context, where clear explanations and documentation are essential.

3.2 Interaction Models

AI system prompts implement different interaction models that define how the AI engages with users.

Manus Ask vs. Notify Model

Manus implements a sophisticated interaction model that distinguishes between different types of communication:

<function>{"description": "Send a message to user.\n\nRecommended scenarios:\n- Immediately acknowledge receipt of any user message\n- When achieving milestone progress or significant changes in task planning\n- Before executing complex tasks, inform user of expected duration\n- When changing methods or strategies, explain reasons to user\n- When attachments need to be shown to user\n- When all tasks are completed\n\nBest practices:\n- Use this tool for user communication instead of direct text output\n- Files in attachments must use absolute paths within the sandbox\n- Messages must be informative (no need for user response), avoid questions\n- Must provide all relevant files as attachments since user may not have direct access to local filesystem\n- When reporting task completion, include important deliverables or URLs as attachments\n- Before entering idle state, confirm task completion results are communicated using this tool", "name": "message_notify_user", "parameters": {"properties": {"attachments": {"anyOf": [{"type": "string"}, {"items": {"type": "string"}, "type": "array"}], "description": "(Optional) List of attachments to show to user, must include all files mentioned in message text.\nCan be absolute path of single file or URL, e.g., \"/home/example/report.pdf\" or \"http://example.com/webpage\".\nCan also be list of multiple absolute file paths or URLs, e.g., [\"/home/example/part_1.md\", \"/home/example/part_2.md\"].\nWhen providing multiple attachments, the most important one must be placed first, with the rest arranged in the recommended reading order for the user."}, "text": {"description": "Message text to display to user. e.g. \"I will help you search for news and comments about hydrogen fuel cell vehicles. This may take a few minutes.\"", "type": "string"}}, "required": ["text"], "type": "object"}}

Source: Manus tools.json - message_notify_user function

<function>{"description": "Ask user a question and wait for response.\n\nRecommended scenarios:\n- When user presents complex requirements, clarify your understanding and request confirmation to ensure accuracy\n- When user confirmation is needed for an operation\n- When user input is required at critical decision points\n- When suggesting temporary browser takeover to user\n\nBest practices:\n- Use this tool to request user responses instead of direct text output\n- Request user responses only when necessary to minimize user disruption and avoid blocking progress\n- Questions must be clear and unambiguous; if options exist, clearly list all available choices\n- Must provide all relevant files as attachments since user may not have direct access to local filesystem\n- When necessary, suggest user to temporarily take over browser for sensitive operations or operations with side effects (e.g., account login, payment completion)\n- When suggesting takeover, also indicate that the user can choose to provide necessary information via messages", "name": "message_ask_user", "parameters": {"properties": {"attachments": {"anyOf": [{"type": "string"}, {"items": {"type": "string"}, "type": "array"}], "description": "(Optional) List of question-related files or reference materials, must include all files mentioned in message text.\nCan be absolute path of single file or URL, e.g., \"/home/example/report.pdf\" or \"http://example.com/webpage\".\nCan also be list of multiple absolute file paths or URLs, e.g., [\"/home/example/part_1.md\", \"/home/example/part_2.md\"].\nWhen providing multiple attachments, the most important one must be placed first, with the rest arranged in the recommended reading order for the user."}, "suggest_user_takeover": {"description": "(Optional) Suggested operation for user takeover. Defaults to \"none\", indicating no takeover is suggested; \"browser\" indicates recommending temporary browser control for specific steps.", "enum": ["none", "browser"], "type": "string"}, "text": {"description": "Question text to present to user", "type": "string"}}, "required": ["text"], "type": "object"}}

Source: Manus tools.json - message_ask_user function

This model distinguishes between notifications (which don't require a response) and questions (which do), which helps minimize unnecessary interruptions while ensuring that the AI gets the information it needs.

Cursor's Context-Aware Responses

Cursor implements a context-aware interaction model that adapts based on the user's input:

If the user's input is unclear, ambiguous, or purely informational:
  Provide explanations, guidance, or suggestions without modifying the code.
  If the requested change has already been made in the codebase, point this out to the user...
Else if the user requests a specific code change:
  First understand the current state of the code and the user's intent
  Consider the broader context of the codebase
  Make minimal, focused changes that address the user's request
  Explain your changes and reasoning

Source: Cursor system prompt

This model enables the AI to provide appropriate responses based on the nature of the user's input, which is particularly important in a code editing context.

3.3 Information Presentation

AI system prompts often include guidelines for how information should be presented to users.

Manus Writing Rules

Manus includes detailed rules for content creation:

<writing_rules>
- Write content in continuous paragraphs using varied sentence lengths for engaging prose; avoid list formatting
- Use prose and paragraphs by default; only employ lists when explicitly requested by users
- All writing must be highly detailed with a minimum length of several thousand words, unless user explicitly specifies length or format requirements
- When writing based on references, actively cite original text with sources and provide a reference list with URLs at the end
- For lengthy documents, first save each section as separate draft files, then append them sequentially to create the final document
- During final compilation, no content should be reduced or summarized; the final length must exceed the sum of all individual draft files
</writing_rules>

Source: Manus prompt.txt

These rules ensure that the AI creates high-quality, detailed content that meets user expectations.

Lovable's Presentation Guidelines

Lovable includes specific guidelines for presenting information to users:

When presenting information to users:
- Use clear, concise language
- Organize information logically
- Highlight important points
- Use appropriate formatting for different types of content
- Provide context and explanations for technical concepts

When presenting code:
- Use syntax highlighting
- Include comments to explain complex logic
- Organize code logically
- Follow best practices for the relevant programming language
- Ensure code is readable and maintainable

Source: Lovable system prompt

These guidelines help the AI present information in a way that is clear, organized, and easy to understand.

3.4 Conversation Management

Advanced AI system prompts include frameworks for managing conversations over time.

Manus Event Stream Processing

Manus uses event stream processing to maintain conversation context:

<event_stream>
You will be provided with a chronological event stream (may be truncated or partially omitted) containing the following types of events:
1. Message: Messages input by actual users
2. Action: Tool use (function calling) actions
3. Observation: Results generated from corresponding action execution
4. Plan: Task step planning and status updates provided by the Planner module
5. Knowledge: Task-related knowledge and best practices provided by the Knowledge module
6. Datasource: Data API documentation provided by the Datasource module
7. Other miscellaneous events generated during system operation
</event_stream>

Source: Manus prompt.txt

This framework enables the AI to maintain a coherent understanding of the conversation history, which is essential for providing contextually appropriate responses.

3.5 Communication Patterns

AI system prompts implement different communication patterns that define how the AI structures its responses.

Lovable's Custom Markup

Lovable uses a custom markup language to structure its responses:

Use only ONE <lov-code> block to wrap ALL code changes and technical details in your response...
Use <lov-write> for creating or updating files...
Use <lov-rename> for renaming files...
Use <lov-delete> for removing files...

Source: Lovable system prompt

This markup language provides a clear structure for the AI's responses, making it easier for users to understand and implement the AI's suggestions.

Manus Function Calling

Manus uses a function-based communication pattern:

<tool_use_rules>
- Must respond with a tool use (function calling); plain text responses are forbidden
- Do not mention any specific tool names to users in messages
- Carefully verify available tools; do not fabricate non-existent tools
- Events may originate from other system modules; only use explicitly provided tools
</tool_use_rules>

Source: Manus prompt.txt

This pattern ensures that the AI's responses are structured and actionable, which is particularly important for complex tasks that involve multiple steps.

3.6 Communication Implications

The communication and interaction models observed in modern AI system prompts have significant implications for AI system design:

User Experience: Clear communication guidelines ensure a consistent and positive user experience
Task Efficiency: Appropriate interaction models minimize unnecessary interruptions and maximize task efficiency
Information Quality: Guidelines for information presentation ensure that users receive high-quality, well-organized information
Conversation Coherence: Frameworks for conversation management ensure that the AI maintains context and provides coherent responses
Response Structure: Communication patterns ensure that the AI's responses are structured and actionable

By implementing these communication and interaction models, AI system designers can create more effective, user-friendly AI assistants.

Key Takeaways

Modern AI system prompts implement sophisticated communication and interaction models
Message rules provide guidelines for how the AI should communicate with users
Interaction models define how the AI engages with users and manages conversations
Information presentation guidelines ensure that users receive high-quality, well-organized information
Conversation management frameworks help the AI maintain context and provide coherent responses
Communication patterns ensure that the AI's responses are structured and actionable

In the next section, we'll explore how AI system prompts implement domain specialization to tailor AI behavior for specific use cases.