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

# Prompt & Tools

> Configure your assistant's knowledge base, tools, variables, and system prompt to define its capabilities and behavior.

Configure the objective of the assistant and the tools it can use during calls.

## Knowledge Base

Give information to the assistant to use as a knowledge base when responding to customers. From website contents, documents, etc.

### Knowledge Base Selection

> [accordion] Choose Knowledge Base
>
> Select a knowledge base store containing relevant information for the assistant to use.
>
> **Requirements:**
>
> * Must be created in your [Knowledge Bases](https://docs.receptonic.com/conversation-design/knowledge-bases.md) section first
>
> * Shows status (Active, Processing, etc.) and description
>
> * Only your own knowledge bases are available
>
> > [!TIP]
> >
> > Create knowledge bases from website content, PDFs, or custom documents to give your assistant domain-specific information. For comprehensive setup guide including content types, processing status, website scraping, and troubleshooting, see the complete [Knowledge Base Guide](https://docs.receptonic.com/conversation-design/knowledge-bases.md).

> [accordion] Knowledge Base Mode
>
> Choose how the AI will use the knowledge base.
>
> > [card] Function Call
> >
> > **Recommended for most cases**
> >
> > Uses a function call to search for information in the knowledgebase, only when needed. More accurate and efficient.
>
> > [card] Prompt Injection
> >
> > **For simple use cases**
> >
> > Performs a search after every customer speech. More accurate but can be slower without filler audios.
>
> > [!NOTE]
> >
> > **Mode availability:** Speech-to-Speech and Dualplex modes only support Function Call mode.

## Custom Mid-Call Tools

Create and assign your own custom tools that AI can use **mid-call** with the customer.

> [card] Create Custom Tools
>
> Build tools tailored to your specific business needs: API integrations, database queries, custom workflows, and external service calls.
>
> **Quick action:** Direct link to tool creation page.

> [card] Assign to Assistant
>
> Select which custom tools this assistant can use with multiple selection, search by name/description, and real-time assignment.
>
> **Scope:** Only your own tools are available.

> [!TIP]
>
> Read the [Custom Tools documentation](https://docs.receptonic.com/ai-assistants/custom-tools.md) for detailed guides on creating and configuring custom tools.

## Default Tools

Choose built-in tools that AI can use **mid-call** with the customer.

> [accordion] Multi Call Transfer
>
> Route calls to multiple destination phone numbers like different people or departments according to your flow.
>
> **Use cases:**
>
> * Escalation to human agents
> * Department routing
> * Specialist handoffs
>
> **Configuration options:**
>
> * **Standard mode:** Use regular phone numbers (e.g., +1234567890)
> * **Advanced mode:** Use SIP URI format for SIP providers (e.g., sip:+1234567890\@sip-server)
>
> **For SIP integrations:**
>
> * Set transfer to "Advanced" mode
>
> * Use SIP URI format: `sip:number@sip-server`
>
> * Verify your SIP provider supports SIP REFER
>
> * Test with different URI formats if transfers fail
>
> > [!NOTE]
> >
> > **Prompt instruction:** Include in your system prompt something like "call the transfer function when the user requests to speak with someone else" to ensure the AI uses this tool appropriately.
>
> > [!TIP]
> >
> > If transfers aren't working, see our [SIP Integration troubleshooting guide](https://docs.receptonic.com/troubleshooting/sip-integration.md#transfer-phone-call-not-working) for detailed solutions.

> [accordion] End Call
>
> Ends the call when the conversation is complete.
>
> **Use cases:**
>
> * Natural conversation conclusion
>
> * Objective achieved
>
> * Customer satisfaction confirmed
>
> > [!NOTE]
> >
> > **Prompt instruction:** If the AI doesn't call the end call function automatically, include in your system prompt "call the hang\_up function to close the call" when the conversation should end.

> [accordion] DTMF Input
>
> Easily send keypad inputs during outbound calls, enabling smooth navigation through IVR menus and automated workflows. The AI navigates using keypad buttons when calling and responding to prompts.
>
> **Use cases:**
>
> * Navigate phone menus
>
> * Enter extension numbers
>
> * Input security codes
>
> * IVR system navigation
>
> > [!NOTE]
> >
> > **Prompt instruction:** Include in your system prompt instructions about when to use DTMF input, such as "use the send\_dtmf tool to navigate phone menus when needed to reach the right person."
>
> For detailed information about DTMF capabilities, see [Tools & Functions](https://docs.receptonic.com/ai-assistants/tools-and-functions.md#4-dtmf-input).

> [accordion] Appointment Scheduling
>
> Real-time booking scheduling integration with multiple calendar platforms.
>
> **Available integrations:**
>
> * **Cal.com:** Full setup guide available at [Cal.com Scheduling](https://docs.receptonic.com/ai-assistants/cal-com-scheduling.md)
> * **GoHighLevel:** Complete integration guide at [GoHighLevel Scheduling](https://docs.receptonic.com/ai-assistants/gohighlevel-scheduling.md)
> * **Calendly:** Full setup guide available at [Calendly Scheduling](https://docs.receptonic.com/ai-assistants/calendly-scheduling.md)
>
> **Use cases:**
>
> * Book appointments with calendars
> * Check real-time availability
> * Send automatic confirmation details
> * Sync with existing calendar systems
>
> **Setup:**
>
> 1. Select your calendar provider (Cal.com, GoHighLevel, or Calendly)
>
> 2. Authenticate with your calendar account
>
> 3. Choose the event type/calendar to use for bookings
>
> 4. The AI will automatically check availability and book appointments
>
> > [!NOTE]
> >
> > Available when calendar integration is enabled in your platform settings.

## Call Variables

Define variables that can be passed **before** making the call and used in the prompt **like {variable_name}**.

### Variable Configuration

> [accordion] Variable Definition
>
> Create call variables to pass information to your assistant before the call starts.
>
> **Setup process:**
>
> * Define variable names and default values
> * Pass values when creating calls/leads or importing clients
> * Variables available immediately in prompts and during calls
> * Use for personalization and context
>
> **Configuration:**
>
> * **Variable name:** The identifier (e.g., `customer_name`)
> * **Default value:** Used when not passed (e.g., "John")

> [accordion] Variable Usage
>
> How to use call variables in your assistant:
>
> **In system prompts:**
>
> * Reference variables with `{variable_name}` syntax
> * Personalize conversations dynamically
> * Provide context-specific information
>
> **Examples:**
>
> * `{customer_name}` for personalization ("Hello {customer_name}")
> * `{email}` for calendar integrations
> * `{account_type}` for tailored responses
> * `{company}` for business context

> [accordion] Data Sources
>
> Ways to populate call variables:
>
> **Manual entry:**
>
> * When creating individual calls
> * Through campaign lead creation
>
> **Import methods:**
>
> * CSV import with variable columns
> * API integration with client data
> * Direct CRM synchronization
>
> **Automation platform integrations:**
>
> * **GoHighLevel (GHL):** Automatically pull contact data and custom fields
> * **Google Sheets:** Import leads with variables from spreadsheet columns
> * **Connect with 250+ popular tools** and platforms using our no-code platform
> * **Any other platform** through webhooks for custom integrations
>
> **Platform integration:**
>
> * Automatically populated from client profiles
> * Connected to existing customer databases
> * No-code automation workflows

> [!NOTE]
>
> Call variables are essential for personalizing AI conversations. They allow the AI to use specific customer information during calls, making interactions more relevant and effective.

## Call Flow Configuration

### Who Speaks First?

Control whether your assistant or the customer initiates the conversation.

> [card] AI Assistant
>
> **Default behavior:** Assistant starts the conversation
>
> The AI will immediately greet the caller and begin the conversation flow as soon as the call connects.
>
> **Best for:** Most outbound scenarios, sales calls, appointment reminders

> [card] Customer
>
> **Wait for customer:** Assistant listens first
>
> If you choose "Customer", the AI will wait for the customer to speak first before responding.
>
> **Best for:** Inbound support calls, reception scenarios, reactive assistance

### Initial Message

Configure the first thing your assistant says when the call begins.

> [accordion] Initial Message Text
>
> Write the opening message your assistant will speak at the start of each call.
>
> **Best practices:**
>
> * Keep it concise and friendly
> * Introduce your company/purpose clearly
> * Set expectations for the conversation
> * Use variables for personalization (e.g., `{customer_name}`)
>
> **Example:** "Hi {customer_name}, this is Sarah from ABC Company. I'm calling to follow up on your recent inquiry about our services. Do you have a moment to chat?"

> [accordion] Initial Audio File
>
> **Optional:** Upload a custom audio file instead of text-to-speech
>
> **Requirements:**
>
> * MP3 or WAV format
> * Clear, high-quality recording
> * Professional voice and tone
> * Matches your assistant's voice if using voice cloning
>
> **Benefits:**
>
> * Perfect pronunciation and delivery
>
> * Consistent brand voice
>
> * Professional first impression
>
> * No text-to-speech latency for opening
>
> > [!TIP]
> >
> > This works best if the AI voice is cloned using the same voice used in the initial audio.

> [!NOTE]
>
> See our [Initial Message guide](https://docs.receptonic.com/ai-assistants/initial-message.md) for detailed best practices and examples.

## System Prompt

Define the assistant's personality, objectives, and behavior guidelines.

### Editing Tools

Choose the editing experience that works best for you:

> [card] [AI Prompt Editor](https://docs.receptonic.com/ai-assistants/ai-prompt-editor.md)
>
> **Chat-based editing with AI assistance**
>
> Describe changes in plain language and let AI suggest intelligent modifications. Review and accept/reject each change individually.
>
> **Best for:** Quick iterations, improving existing prompts, text-focused editing

> [card] [Flow Builder](https://docs.receptonic.com/ai-assistants/flow-builder.md)
>
> **Visual drag-and-drop editor**
>
> Design conversation flows by connecting nodes on a canvas. Create branching logic and multi-path decision trees visually.
>
> **Best for:** Complex call flows, structured scripts, visual thinkers

> [!NOTE]
>
> Both tools store the prompt in the same field - switching between them is possible but may require adjustments.

### Prompt Configuration

> [card] Custom Prompt
>
> Write your own system prompt from scratch
>
> * Full control over assistant behavior
> * Tailored to specific use cases
> * Markdown formatting supported

> [card] Template Library
>
> Start with pre-built templates
>
> * Multiple languages available
> * Different conversation types
> * Proven effective prompts

### Best Practices

> [accordion] Be Specific
>
> Clearly define the assistant's role, objectives, and constraints.
>
> **Include:**
>
> * Who the assistant represents
> * What they're trying to achieve
> * What they should/shouldn't do

> [accordion] Set Boundaries
>
> Define what topics and actions are off-limits.
>
> **Consider:**
>
> * Data privacy requirements
> * Legal compliance
> * Brand guidelines

> [accordion] Use Examples
>
> Provide sample conversations to guide behavior.
>
> **Examples help with:**
>
> * Tone and style
> * Response length
> * Handling objections

> [!TIP]
>
> See our [System Prompt guide](https://docs.receptonic.com/ai-assistants/system-prompt.md) for detailed best practices and examples.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.