### Answer The best practices for prompt writing in Retell AI involve using sectional prompts and understanding how global prompts work in Conversation Flow agents [(1) ]() [(2) ]() . ## Best Practice: Use Sectional Prompts Break large prompts into focused sections for better organization and LLM comprehension [(1) ]() . This structured approach offers several benefits : - **Reusability**: Sections can be adapted across different agents - **Maintainability**: Easy to update specific behaviors without affecting others - **Clarity**: LLMs process structured information more accurately ### Recommended Prompt Structure

///## Identity
You are a friendly AI assistant for [Company Name].
Your role is to [specific purpose].
You have expertise in [relevant domains].

///## Style Guardrails
Be concise: Keep responses under 2 sentences unless explaining complex topics.
Be conversational: Use natural language, contractions, and acknowledge what the caller says.
Be empathetic: Show understanding for the caller's situation.

///## Response Guidelines
Return dates in spoken form: Say "January fifteenth" not "1/15".
Ask one question at a time: Avoid overwhelming the caller with multiple questions.
Confirm understanding: Paraphrase important information back to the caller.

///## Task Instructions
[Specific steps the agent should follow]

///## Objection Handling
If the caller says they're not interested: "I understand. Is there anything specific..."
If the caller is frustrated: "I hear your frustration, let me help resolve this..."

## Global Prompt in Conversation Flow For Conversation Flow agents, the global prompt is used in every node of the conversation flow [(2) ]() . You can set it when creating a conversation flow : - The global prompt provides consistent context across all nodes - It's separate from node-specific instructions - Example:

"You are a helpful customer service agent."

## Tool Calling Instructions For Single/Multi Prompt Agents, always specify exact conditions for tool usage and reference tools by their exact names [(1) ]() . Define clear triggers with specific words/phrases that should trigger tool calls .

​ To learn more, see the sources I considered: [[1] Prompt Engineering Guide](https://docs.retellai.com/build/prompt-engineering-guide) [[2] Create Conversation Flow](https://docs.retellai.com/api-references/create-conversation-flow) ​

Feel free to tag @AI Evy with additional questions. I also appreciate feedback, it helps me improve.

### Answer For effective prompt writing in Retell AI, use sectional prompts to organize your instructions clearly [(1) ]() . Break large prompts into focused sections like Identity, Style Guardrails, Response Guidelines, Task Instructions, and Objection Handling . Recommended Prompt Structure:

///## Identity
You are a friendly AI assistant for [Company Name].
Your role is to [specific purpose].
You have expertise in [relevant domains].
///## Style Guardrails
Be concise: Keep responses under 2 sentences unless explaining complex topics.
Be conversational: Use natural language, contractions, and acknowledge what the caller says.
Be empathetic: Show understanding for the caller's situation.
///## Response Guidelines

Return dates in spoken form: Say "January fifteenth" not "1/15".
Ask one question at a time: Avoid overwhelming the caller with multiple questions.
Confirm understanding: Paraphrase important information back to the caller.
///## Task Instructions
[Specific steps the agent should follow]
///## Objection Handling
If the caller says they're not interested: "I understand. Is there anything specific..."
If the caller is frustrated: "I hear your frustration, let me help resolve this..."

For Global Prompts (used in Conversation Flow agents) , the global prompt is applied across every node in the conversation flow [(2) ]() . You can set it when creating or updating your conversation flow . Key Benefits of Sectional Prompts: [(1) ]() - **Reusability**: Sections can be adapted across different agents - **Maintainability**: Easy to update specific behaviors without affecting others - **Clarity**: LLMs process structured information more accurately For complex tasks, consider using Conversation Flow agents instead of cramming everything into a single prompt .

​ To learn more, see the sources I considered: [[1] Prompt Engineering Guide](https://docs.retellai.com/build/prompt-engineering-guide) [[2] List Conversation Flows](https://docs.retellai.com/api-references/list-conversation-flows) ​

Feel free to tag @AI Evy with additional questions. I also appreciate feedback, it helps me improve.

### Answer I don't have specific information in the available sources about bulk-editing multiple agents or managing changes across 80 location-based agents simultaneously. However, I'd recommend checking out these potentially useful sources that might help with agent management: - [Prompt Engineering Guide]() - [Single/Multi Prompt Agent Overview]() Would you like me to try to provide a general answer about potential approaches for managing multiple agents, or would you prefer to reach out to Retell AI support for specific guidance on bulk operations? You can also visit: - [Documentation]() - [Hire certified Retell partner]()

message has been deleted

Feel free to tag @AI Evy with additional questions. I also appreciate feedback, it helps me improve.