> ## Documentation Index
> Fetch the complete documentation index at: https://docs.meetzy.es/llms.txt
> Use this file to discover all available pages before exploring further.
# Actions & Tools
> Configure integrations, call transfers, webhooks, and automated actions for your AI agents
## Overview
The Actions & Tools section is the powerhouse of your AI agent's operational capabilities. Here you configure what your agent can do during and after calls - from transferring conversations to human agents or SIP systems, to making intelligent API calls, and setting up sophisticated callback protocols.
This section transforms your agent from a simple conversationalist into a fully integrated business automation tool that can take real actions and connect with your existing systems.
## Call Transfer
Configure how your agent intelligently transfers calls to human agents, departments, or external phone systems when needed.
### Transfer Configuration
Toggle the "Call Transfer" option to activate the transfer functionality for your agent.
Select between traditional phone numbers or SIP trunk endpoints based on your infrastructure.
Define when and how your agent should initiate transfers using smart prompting.
Validate that transfers work correctly with your phone system before going live.
### Transfer Types
**Traditional Phone Transfer**
Perfect for transferring to mobile phones, landlines, or traditional business numbers.
* **Format**: Use international format (+1234567890)
* **Best for**: Human agents, customer service departments, sales teams
* **Reliability**: High compatibility with all phone systems
* **Cost**: Standard telephony rates apply
**Configuration Example:**
```
Transfer Number: +1-555-123-4567
Department: Sales Team
```
**SIP/VoIP Transfer**
Ideal for enterprise environments with PBX systems, call centers, or VoIP infrastructure.
* **Format**: `sip:extension@gateway_ip:port`
* **Best for**: Call centers, PBX extensions, enterprise VoIP
* **Benefits**: Lower costs, advanced routing, better integration
* **Requirements**: SIP-compatible phone system
**Configuration Examples:**
```
Sales Extension: sip:100@10.0.1.50:5060
Support Queue: sip:support@pbx.company.com:5060
Manager Direct: sip:200@192.168.1.100:5060
```
### Advanced Transfer Features
**Context Preservation**: Comprehensive information transfer to human operators:
* Customer's name, contact information, and call origin
* Complete conversation summary with key discussion points
* Specific questions, requests, or issues that triggered the transfer
* Customer sentiment analysis and engagement level
* Previous interaction history and relationship status
**Transfer Modes**:
* **Warm Transfer**: Agent briefly explains context to human operator before connecting customer
* **Cold Transfer**: Direct transfer without agent introduction for faster handoffs
* **Conference**: Three-way call with agent, customer, and human operator for complex scenarios
**Smart Transfer Routing**:
* Department-specific routing based on conversation content
* Skill-based routing to most qualified available agent
* Priority queuing for VIP customers or urgent issues
* Automatic fallback to voicemail if no agents available
### Transfer Prompt Templates
The transfer prompt is crucial - it teaches your AI agent exactly when to transfer calls. Use these professionally crafted multi-language templates:
```
Se usa para transferir la llamada con una persona en los casos que se indican a continuación:
- El usuario rechaza directamente la propuesta o servicio
- El usuario solicita expresamente hablar con una persona humana
- El usuario muestra desconfianza hacia el asistente virtual
- Se necesita información específica que no está disponible en el sistema
- El usuario requiere autorización o gestión de datos personales sensibles
- Situaciones que requieren negociación o decisiones complejas
- Quejas o reclamaciones que necesitan atención personalizada
- El usuario solicita escalación a un supervisor o gerente
- Casos de facturación complejos o disputas de pagos
- Situaciones médicas o legales que requieren experiencia humana
```
```
Used to transfer the call to a person in the following cases:
- The user directly rejects the proposal or service
- The user expressly requests to speak with a human person
- The user shows distrust towards the virtual assistant
- Specific information is needed that is not available in the system
- The user requires authorization or management of sensitive personal data
- Situations requiring negotiation or complex decisions
- Complaints or claims that need personalized attention
- The user requests escalation to a supervisor or manager
- Complex billing or payment dispute situations
- Medical or legal situations requiring human expertise
```
```
Utilisé pour transférer l'appel à une personne dans les cas suivants:
- L'utilisateur rejette directement la proposition ou le service
- L'utilisateur demande expressément à parler avec une personne humaine
- L'utilisateur montre de la méfiance envers l'assistant virtuel
- Des informations spécifiques sont nécessaires qui ne sont pas disponibles dans le système
- L'utilisateur nécessite une autorisation ou la gestion de données personnelles sensibles
- Situations nécessitant négociation ou décisions complexes
- Plaintes ou réclamations nécessitant une attention personnalisée
- L'utilisateur demande une escalade vers un superviseur ou manager
- Situations de facturation complexes ou litiges de paiement
```
```
Wird verwendet, um den Anruf an eine Person zu übertragen in folgenden Fällen:
- Der Benutzer das Angebot oder den Service direkt ablehnt
- Der Benutzer ausdrücklich darum bittet, mit einer menschlichen Person zu sprechen
- Der Benutzer Misstrauen gegenüber dem virtuellen Assistenten zeigt
- Spezifische Informationen benötigt werden, die im System nicht verfügbar sind
- Der Benutzer eine Autorisierung oder Verwaltung sensibler persönlicher Daten benötigt
- Situationen, die Verhandlungen oder komplexe Entscheidungen erfordern
- Beschwerden oder Ansprüche, die persönliche Aufmerksamkeit benötigen
```
```
Usato per trasferire la chiamata a una persona nei seguenti casi:
- L'utente rifiuta direttamente la proposta o il servizio
- L'utente richiede espressamente di parlare con una persona umana
- L'utente mostra sfiducia verso l'assistente virtuale
- Sono necessarie informazioni specifiche non disponibili nel sistema
- L'utente richiede autorizzazione o gestione di dati personali sensibili
- Situazioni che richiedono negoziazione o decisioni complesse
- Reclami o richieste che necessitano attenzione personalizzata
```
```
Usado para transferir a chamada para uma pessoa nos seguintes casos:
- O usuário rejeita diretamente a proposta ou serviço
- O usuário solicita expressamente falar com uma pessoa humana
- O usuário mostra desconfiança em relação ao assistente virtual
- São necessárias informações específicas que não estão disponíveis no sistema
- O usuário requer autorização ou gestão de dados pessoais sensíveis
- Situações que requerem negociação ou decisões complexas
- Reclamações ou solicitações que precisam de atenção personalizada
```
## Webhook Tools
Create powerful API integrations that allow your agent to interact with external systems during conversations through our sophisticated modal interface.
**New Feature**: Webhook Tools now support advanced parameter mapping, authentication methods, and real-time testing through an intuitive modal interface. You can create custom API integrations that intelligently extract conversation data and trigger external systems.
### Webhook Tool Modal Interface
The webhook configuration uses an advanced modal interface with the following sections:
Configure the basic identity and trigger conditions for your webhook tool.
**Required Fields:**
* **Name**: Unique identifier (e.g., "create\_lead", "check\_inventory")
* **Description**: Clear explanation of when the AI should use this tool
* **Execution Mode**: Choose immediate or deferred execution
Set up the core API connection details.
**URL Configuration:**
* **Base URL**: The complete webhook endpoint URL
* **HTTP Method**: GET, POST, PUT, PATCH, or DELETE
* **Request Timeout**: 5-60 seconds (default: 20)
Configure secure authentication for your API endpoints.
**Authentication Types:**
* Bearer Token authentication
* API Key authentication
* Basic Auth with username/password
* Custom header authentication
Define how conversation data maps to API parameters with intelligent extraction.
**Parameter Types:**
* **Query Parameters**: URL-encoded parameters for GET requests
* **Body Parameters**: JSON payload for POST/PUT/PATCH requests
* **Header Parameters**: Custom HTTP headers
### Advanced Parameter Configuration
Each webhook parameter supports sophisticated data mapping through our modal interface:
| Property | Description | Options | Example |
| --------------------- | -------------------- | --------------------------------------------------- | ---------------------------------------- |
| **Name** | Parameter identifier | Custom string | `customer_name` |
| **Type** | Data validation | string, number, boolean, integer, array, object | `string` |
| **Required** | Mandatory field | true/false | `true` |
| **Description** | AI understanding | Natural language | "Customer's full name from conversation" |
| **Value Source** | How to get value | LLM extraction, static value, conversation metadata | LLM prompt |
| **Extraction Prompt** | AI instruction | Natural language | "Extract the customer's full name" |
**LLM Extraction**
Let the AI intelligently extract information from the conversation:
```
Extraction Prompt: "Extract the customer's email address from the conversation"
Parameter Type: string
Required: true
```
**Static Values**
Use fixed values for consistent data:
```
Static Value: "phone_call"
Parameter: source
Type: string
```
**Conversation Metadata**
Access built-in conversation data:
* Call duration and timestamps
* Customer and agent phone numbers
* Call direction (inbound/outbound)
* Call status and outcome
* Agent ID and configuration
**Supported Parameter Types:**
* **string**: Text data, names, descriptions
* **number**: Numeric values with decimals
* **integer**: Whole numbers only
* **boolean**: true/false values
* **array**: List of values
* **object**: Complex nested data structures
**Type Validation:**
The system automatically validates parameter types and provides clear error messages for mismatched data.
### Webhook Tool Execution Settings
Configure advanced execution behavior through the modal interface:
**Execution Control:**
* **Immediate**: Execute during the active call
* **Deferred**: Execute after the call ends
* **Conditional**: Execute based on conversation outcome
**Agent Behavior Settings:**
* **Disable Interruptions**: Prevent customer from speaking during execution
* **Force Pre-tool Speech**: Require agent announcement before execution
* **Tool Call Sound**: Play typing sound during execution (typing/none)
* **Sound Behavior**: Auto or manual control of sound effects
**Error Handling:**
* **Response Timeout**: Maximum wait time for API response
* **Retry Logic**: Automatic retries on failure
* **Fallback Messages**: What to say if API fails
* **Graceful Degradation**: Continue conversation without API data
### Webhook Integration Examples
**Salesforce Lead Integration**
Configure a webhook tool that automatically creates leads in Salesforce when customers show purchase interest:
```json theme={null}
{
"name": "create_salesforce_lead",
"description": "Create a new lead in Salesforce when customer shows purchase interest",
"url": "https://api.salesforce.com/services/data/v52.0/sobjects/Lead",
"method": "POST",
"headers": {
"Authorization": "Bearer {{salesforce_token}}",
"Content-Type": "application/json"
},
"body_parameters": {
"FirstName": {
"type": "string",
"required": true,
"value_type": "llm_prompt",
"description": "Extract customer's first name from conversation"
},
"LastName": {
"type": "string",
"required": true,
"value_type": "llm_prompt",
"description": "Extract customer's last name from conversation"
},
"Phone": {
"type": "string",
"required": true,
"value_type": "conversation_metadata",
"description": "Customer's phone number"
},
"LeadSource": {
"type": "string",
"value_type": "static",
"static_value": "AI Phone Call"
}
}
}
```
**Product Availability Check**
Create a real-time inventory checking tool that your agent can use during conversations:
```json theme={null}
{
"name": "check_product_availability",
"description": "Check real-time product availability when customer inquires about specific items",
"url": "https://inventory.yourcompany.com/api/check",
"method": "GET",
"query_parameters": {
"product_sku": {
"type": "string",
"required": true,
"value_type": "llm_prompt",
"description": "Extract product SKU or name mentioned by customer"
},
"location": {
"type": "string",
"value_type": "llm_prompt",
"description": "Customer's preferred store location or zip code"
},
"api_key": {
"type": "string",
"value_type": "static",
"static_value": "{{inventory_api_key}}"
}
},
"response_timeout": 10,
"disable_interruptions": false
}
```
**Appointment Scheduling**
Set up automatic appointment booking through your calendar system:
```json theme={null}
{
"name": "book_calendar_appointment",
"description": "Schedule an appointment when customer requests a meeting or consultation",
"url": "https://api.calendly.com/scheduled_events",
"method": "POST",
"headers": {
"Authorization": "Bearer {{calendly_token}}",
"Content-Type": "application/json"
},
"body_parameters": {
"event_type": {
"type": "string",
"value_type": "static",
"static_value": "https://calendly.com/your-company/30-min-consultation"
},
"start_time": {
"type": "string",
"value_type": "llm_prompt",
"description": "Extract preferred meeting time from customer in ISO format"
},
"invitee": {
"type": "object",
"properties": {
"name": {
"type": "string",
"value_type": "llm_prompt",
"description": "Customer's full name"
},
"email": {
"type": "string",
"value_type": "llm_prompt",
"description": "Customer's email address"
}
}
}
}
}
```
### Authentication Configuration
The modal interface supports multiple authentication methods:
**JWT/OAuth 2.0 Authentication**
Most modern APIs use Bearer token authentication for security:
```json theme={null}
{
"Authorization": "Bearer eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzI1NiJ9..."
}
```
**Use Cases:**
* Modern REST APIs (Salesforce, HubSpot, etc.)
* OAuth 2.0 protected endpoints
* JWT-based authentication systems
* Enterprise SaaS platforms
**Simple API Key Authentication**
Traditional API key authentication for simpler integrations:
```json theme={null}
{
"X-API-Key": "sk_live_abcd1234efgh5678ijkl",
"Authorization": "ApiKey sk_live_abcd1234efgh5678ijkl"
}
```
**Use Cases:**
* Third-party service APIs
* Simple authentication requirements
* Legacy system integration
* Custom internal APIs
**Username/Password Authentication**
Basic HTTP authentication for legacy systems:
```json theme={null}
{
"Authorization": "Basic dXNlcm5hbWU6cGFzc3dvcmQ="
}
```
**Use Cases:**
* Legacy systems
* Internal APIs
* Simple HTTP authentication
* Testing environments
### Webhook Testing and Validation
The modal interface includes powerful testing capabilities:
**Real-time Testing:**
* Test API endpoints directly from the configuration modal
* Validate authentication credentials before saving
* Preview request/response data with sample conversation data
* Debug parameter mapping with live extraction
**Validation Features:**
* Automatic URL validation and accessibility checking
* Parameter type validation with clear error messages
* Required field validation with helpful suggestions
* Response format validation for proper integration
## End Call Strategy
Configure intelligent call termination with sophisticated answering machine detection and strategic conversation ending.
### Enhanced Call Termination Logic
Activate the "End Call Strategy" to handle call endings intelligently.
Set up multi-language phrases that indicate answering machines or voicemail systems.
Specify what constitutes a successful call that should end naturally.
Configure responses for unexpected scenarios like long silences or system errors.
### Advanced Answering Machine Detection
Our enhanced detection system recognizes voicemail and answering machines across multiple languages with expanded phrase detection:
**Detection Accuracy**: 97%+ accuracy rate in identifying automated systems
**Languages Supported**: Spanish, English, French, German, Italian, Portuguese
**Response Time**: Detection typically occurs within 2-4 seconds of answering
**False Positive Rate**: Less than 2% with enhanced phrase recognition
### Expanded End Call Strategy Templates
Configure professional call termination for various scenarios using our comprehensive multi-language templates:
```markdown theme={null}
## Finalización de llamada por Detección de Contestador Automático
Si se detecta que el usuario es un contestador automático, finaliza la llamada de inmediato. Aquí tienes ejemplos de mensajes que suelen decir los contestadores automáticos:
**Frases comunes de contestadores:**
- En este momento no podemos atenderle
- Deje su mensaje después de la señal
- El número al que llama...
- Ha llamado al...
- Este es el contestador de...
- Puedes dejar tu mensaje al oir la señal
- Deje su mensaje después de oir la señal
- Gracias por llamar, en estos momentos...
- Por favor, deje su mensaje después del tono
- Lo sentimos, pero en estos momentos...
- Bienvenido al buzón de voz de...
- No podemos atender su llamada ahora mismo
- Por favor, inténtelo de nuevo más tarde
- Ha contactado con el servicio de atención al cliente
- Bienvenido al contestador automático de...
- Su llamada es muy importante para nosotros
- Todos nuestros operadores están ocupados
- Manténgase en línea por favor
## Finalización de Llamada por otros motivos:
También debes colgar las llamadas cuando:
- El usuario se despida de forma clara
- Te despidas tú mismo
- La conversación haya alcanzado su objetivo completamente
- El usuario indique claramente que no está interesado
- Se detecten largos períodos de silencio (más de 10 segundos)
```
```markdown theme={null}
## Call Termination by Answering Machine Detection
If it is detected that the user is an answering machine, terminate the call immediately. Here are examples of messages that answering machines typically say:
**Common answering machine phrases:**
- We cannot attend you at this time
- Leave your message after the signal
- The number you called...
- You have called...
- This is the answering machine of...
- You can leave your message when you hear the signal
- Leave your message after hearing the signal
- Thank you for calling, at this time...
- Please leave your message after the tone
- We're sorry, but at this time...
- Welcome to the voicemail of...
- We cannot take your call right now
- Please try again later
- You have contacted customer service
- Welcome to the answering machine of...
- Your call is very important to us
- All our operators are busy
- Please hold the line
## Call Termination for other reasons:
You should also hang up calls when:
- The user clearly says goodbye
- You say goodbye yourself
- The conversation has completely achieved its objective
- The user clearly indicates they are not interested
- Long periods of silence are detected (more than 10 seconds)
```
```markdown theme={null}
## Finalisation d'appel par Détection de Répondeur Automatique
Si il est détecté que l'utilisateur est un répondeur automatique, finalisez l'appel immédiatement. Voici des exemples de messages que les répondeurs disent généralement :
**Phrases communes de répondeurs:**
- En ce moment nous ne pouvons pas vous répondre
- Laissez votre message après le signal
- Le numéro que vous avez appelé...
- Vous avez appelé le...
- Ceci est le répondeur de...
- Vous pouvez laisser votre message en entendant le signal
- Laissez votre message après avoir entendu le signal
- Merci d'avoir appelé, en ce moment...
- Veuillez laisser votre message après le ton
- Nous sommes désolés, mais en ce moment...
- Bienvenue sur la messagerie vocale de...
- Nous ne pouvons pas prendre votre appel maintenant
- Veuillez réessayer plus tard
- Vous avez contacté le service client
- Bienvenue sur le répondeur automatique de...
- Votre appel est très important pour nous
- Tous nos opérateurs sont occupés
## Finalisation d'Appel pour d'autres raisons :
Vous devez également raccrocher les appels quand :
- L'utilisateur dit clairement au revoir
- Vous dites au revoir vous-même
- La conversation a complètement atteint son objectif
- L'utilisateur indique clairement qu'il n'est pas intéressé
```
```markdown theme={null}
## Anrufbeendigung durch Anrufbeantworter-Erkennung
Wenn erkannt wird, dass der Benutzer ein Anrufbeantworter ist, beenden Sie den Anruf sofort. Hier sind Beispiele für Nachrichten, die Anrufbeantworter normalerweise sagen:
**Häufige Anrufbeantworter-Phrasen:**
- Wir können Sie derzeit nicht erreichen
- Hinterlassen Sie Ihre Nachricht nach dem Signal
- Die Nummer, die Sie angerufen haben...
- Sie haben angerufen...
- Dies ist der Anrufbeantworter von...
- Sie können Ihre Nachricht hinterlassen, wenn Sie das Signal hören
- Hinterlassen Sie Ihre Nachricht nach dem Hören des Signals
- Vielen Dank für Ihren Anruf, derzeit...
- Bitte hinterlassen Sie Ihre Nachricht nach dem Ton
- Es tut uns leid, aber derzeit...
- Willkommen in der Mailbox von...
- Wir können Ihren Anruf jetzt nicht entgegennehmen
- Alle unsere Mitarbeiter sind beschäftigt
## Anrufbeendigung aus anderen Gründen:
Sie sollten auch Anrufe beenden, wenn:
- Der Benutzer sich klar verabschiedet
- Sie sich selbst verabschieden
- Das Gespräch sein Ziel vollständig erreicht hat
```
```markdown theme={null}
## Terminazione Chiamata per Rilevamento Segreteria Telefonica
Se viene rilevato che l'utente è una segreteria telefonica, termina la chiamata immediatamente. Ecco esempi di messaggi che le segreterie telefoniche dicono solitamente:
**Frasi comuni delle segreterie:**
- Al momento non possiamo rispondere
- Lasci il suo messaggio dopo il segnale
- Il numero che ha chiamato...
- Ha chiamato il...
- Questa è la segreteria di...
- Può lasciare il suo messaggio quando sente il segnale
- Lasci il suo messaggio dopo aver sentito il segnale
- Grazie per aver chiamato, al momento...
- Per favore, lasci il suo messaggio dopo il tono
- Ci dispiace, ma al momento...
- Benvenuto nella segreteria di...
- Non possiamo rispondere alla sua chiamata ora
- La sua chiamata è molto importante per noi
- Tutti i nostri operatori sono occupati
## Terminazione Chiamata per altri motivi:
Dovrebbe anche terminare le chiamate quando:
- L'utente si congeda chiaramente
- Si congeda lei stesso
- La conversazione ha completamente raggiunto il suo obiettivo
```
```markdown theme={null}
## Finalização de chamada por Detecção de Secretária Eletrônica
Se for detectado que o usuário é uma secretária eletrônica, finalize a chamada imediatamente. Aqui estão exemplos de mensagens que as secretárias eletrônicas normalmente dizem:
**Frases comuns de secretárias eletrônicas:**
- No momento não podemos atendê-lo
- Deixe sua mensagem após o sinal
- O número que você ligou...
- Você ligou para...
- Esta é a secretária eletrônica de...
- Você pode deixar sua mensagem quando ouvir o sinal
- Deixe sua mensagem após ouvir o sinal
- Obrigado por ligar, neste momento...
- Por favor, deixe sua mensagem após o tom
- Lamentamos, mas neste momento...
- Bem-vindo à caixa postal de...
- Não podemos atender sua chamada agora
- Sua ligação é muito importante para nós
- Todos os nossos operadores estão ocupados
## Finalização de Chamada por outros motivos:
Você também deve encerrar chamadas quando:
- O usuário se despede claramente
- Você se despede
- A conversa atingiu completamente seu objetivo
```
## Email Integration
Configure intelligent email sending capabilities during or after conversations.
### Email Configuration
Toggle the "Send Email" option to activate email functionality.
Define when the agent should send emails using natural language prompts.
Configure dynamic subject lines and email body content.
Set up primary recipients and CC options.
**Email Trigger Examples:**
* Customer requests detailed product information via email
* Follow-up emails after successful calls
* Sending meeting confirmations and calendar invites
* Quote or proposal delivery after phone conversations
**Dynamic Content:**
* Extract customer information from conversation
* Include call summary and next steps
* Personalized product recommendations
* Contact information and appointment details
## SMS Integration
Set up intelligent SMS messaging capabilities for follow-up communications.
### SMS Configuration
Toggle the "Send SMS" option to activate messaging functionality.
Define conversation scenarios that should trigger SMS messages.
Set up dynamic SMS content with conversation data.
Validate SMS functionality with test messages.
**SMS Use Cases:**
* Appointment confirmations and reminders
* Quick follow-up after missed calls
* Delivery of reference numbers or confirmation codes
* Links to online resources or booking pages
**Best Practices:**
* Keep messages concise and actionable
* Include clear opt-out instructions
* Use professional, branded messaging
* Comply with SMS marketing regulations
## Calendar Integration
Configure sophisticated calendar booking with multiple provider support.
### Supported Calendar Providers
**Google Calendar Integration**
Full integration with Google Calendar for availability checking and appointment booking.
**Features:**
* Real-time availability checking
* Automatic event creation
* Meeting invitations and reminders
* Timezone handling
* Conflict detection
**Configuration:**
* Calendar ID for availability checking
* Booking calendar ID for new events
* Working hours and timezone settings
* Default meeting duration
**Microsoft Outlook Integration**
Enterprise-grade integration with Microsoft Outlook and Office 365.
**Features:**
* Exchange Online compatibility
* Meeting room booking
* Teams meeting integration
* Corporate calendar policies
* Multi-tenant support
**Configuration:**
* Outlook calendar access
* Exchange server settings
* Authentication credentials
* Meeting preferences
### Calendar Configuration Options
**Availability Settings:**
* **Multiple Calendar Support**: Check availability across multiple calendars
* **Working Hours**: Define business hours for appointment booking
* **Timezone Management**: Automatic timezone conversion
* **Buffer Times**: Add buffer time between appointments
**Booking Preferences:**
* **Default Duration**: Standard meeting length (15, 30, 60 minutes)
* **Advance Notice**: Minimum time required before booking
* **Maximum Advance**: How far in advance bookings are allowed
* **Blackout Dates**: Exclude specific dates from availability
**Meeting Details:**
* **Dynamic Titles**: Generate meeting titles from conversation context
* **Custom Descriptions**: Include call summary and customer details
* **Attendee Management**: Automatically add customer email
* **Location Handling**: Include meeting location or virtual meeting links
### Calendar Integration Workflow
Set up OAuth 2.0 authentication with Google Calendar or Microsoft Graph API for Outlook integration.
Configure primary and secondary calendars, working hours, and availability preferences.
Create dynamic event templates with conversation data extraction for title, description, and attendees.
Define availability checking logic, conflict resolution, and automatic scheduling preferences.
**Event Data Extraction:**
* Customer name and contact information from conversation
* Meeting purpose and agenda items discussed
* Preferred time slots mentioned by customer
* Special requirements or preparation notes
## Recall Protocol
Set up sophisticated automatic callback systems for comprehensive customer follow-up when initial calls don't achieve their objectives.
### Recall System Architecture
**Smart Scheduling**: Intelligent timing based on customer behavior and business rules
**Success Detection**: Automatic recognition of completed objectives to prevent unnecessary callbacks\
**Compliance Built-in**: Respects Do Not Call lists and regulatory requirements
**Escalation Paths**: Gradually increase intervals and change strategies over time
### Recall Configuration
Activate the recall protocol and set maximum callback attempts.
Specify what constitutes a successful call that doesn't require follow-up.
Set intelligent timing intervals between recall attempts.
Define how callback strategy changes with each attempt.
### Recall Timing Strategies
| Attempt | Timing | Use Case | Success Rate |
| -------------- | ----------------- | ------------------------- | ------------ |
| **1st Recall** | 15-30 minutes | Busy signal, no answer | 35% |
| **2nd Recall** | 2-4 hours | Same day follow-up | 25% |
| **3rd Recall** | Next business day | Professional follow-up | 20% |
| **4th Recall** | 3-5 days later | Persistent but respectful | 15% |
| **5th Recall** | 1-2 weeks later | Final attempt | 10% |
### Success Condition Examples
**Objective Achievement:**
* Customer provided required information (contact details, preferences)
* Meeting or appointment successfully scheduled
* Purchase decision made (positive or negative with clear finality)
* Information successfully delivered (pricing, product details, etc.)
**Explicit Customer Requests:**
* Customer explicitly requested no further contact
* Customer scheduled their own callback time
* Customer was transferred to human agent successfully
* Customer asked to be contacted via different method (email, text)
**Call Completion Scenarios:**
* Full conversation completed with all questions answered
* Customer showed clear lack of interest with polite decline
* Answering machine message successfully delivered
* Technical issues prevented meaningful conversation
### Recall Configuration Options
**Timing Controls:**
* **Business Hours Only**: Restrict callbacks to business hours
* **Time Zone Awareness**: Respect customer's local time zone
* **Day-of-Week Preferences**: Avoid weekends or specific days
* **Holiday Exclusions**: Skip holidays and blackout dates
**Escalation Strategy:**
* **Message Variation**: Change script or approach with each attempt
* **Channel Switching**: Transition to email or SMS after failed calls
* **Human Handoff**: Transfer persistent cases to human agents
* **Compliance Monitoring**: Automatic DNC list checking
**Performance Tracking:**
* **Success Rate Analytics**: Track effectiveness by attempt number
* **Optimal Timing Analysis**: Identify best callback windows
* **Customer Response Patterns**: Learn from customer behavior
* **ROI Measurement**: Calculate cost-effectiveness of recalls
## Caller ID Management
Set up professional caller IDs for outbound calls to improve answer rates and brand recognition.
### Caller ID Configuration
Register your business phone numbers for use as caller IDs through the modal interface.
Complete verification process via SMS or voice call verification.
Choose which number appears for outbound calls by default.
Track answer rates by caller ID to optimize selection.
### Caller ID Best Practices
**Number Selection:**
* Use local area codes when possible (increases answer rates by 20-30%)
* Choose memorable, professional-looking numbers
* Avoid numbers that look like spam (avoid 555, repeated digits)
* Use toll-free numbers for national campaigns
**Verification Process:**
* SMS verification for mobile numbers
* Voice verification for landlines
* Business documentation for toll-free numbers
* Compliance with carrier requirements
**Performance Optimization:**
* A/B test different caller IDs
* Monitor answer rates by time of day
* Adjust caller ID based on campaign type
* Use different numbers for different business units
### Multi-Account Caller ID Management
**Twilio Subaccount Integration:**
* Manage caller IDs across multiple Twilio subaccounts
* Automatic synchronization of verified numbers
* Centralized caller ID performance analytics
* Cross-account number pooling for better coverage
**Phone Number Assignment:**
* Assign specific numbers to specific agents or campaigns
* Automatic rotation for high-volume calling
* Geographic number matching for local presence
* Industry-specific number selection (healthcare, finance, etc.)
## Troubleshooting Common Issues
**Failed Transfers:**
* Check phone number format (use international format)
* Verify SIP URI syntax and network connectivity
* Test transfer destinations manually
* Review carrier compatibility and routing
**Context Loss:**
* Ensure transfer prompts include context instructions
* Verify human agent training on receiving transferred calls
* Check integration between systems
* Review call logging and recording setup
**API Errors:**
* Verify endpoint URL accessibility through modal testing tools
* Check authentication credentials and headers
* Validate request format and required parameters
* Monitor API rate limits and quotas
**Timeout Issues:**
* Reduce response timeout if APIs are slow
* Implement webhook queuing for non-critical operations
* Use asynchronous processing where possible
* Add retry logic with exponential backoff
**Authentication Problems:**
* Refresh OAuth tokens for Google Calendar and Outlook
* Verify permissions and scopes for calendar access
* Check authentication credentials and refresh tokens
* Validate calendar ID format and accessibility
**Booking Failures:**
* Confirm calendar availability checking logic
* Verify timezone handling and conversion
* Check for calendar conflicts and overlaps
* Validate event creation permissions
**Scheduling Problems:**
* Review success criteria configuration for false positives
* Check timing constraints and business hour settings
* Verify DNC list compliance and filtering
* Monitor recall attempt limits and escalation triggers
**Performance Issues:**
* Analyze recall success rates by timing and strategy
* Review customer response patterns and preferences
* Optimize callback intervals based on historical data
* Monitor system load during high-volume recall periods
## Best Practices
### Call Transfer Optimization
1. **Clear Trigger Definition**
* Use multi-language templates for precise trigger conditions
* Define specific, unambiguous scenarios for transfers
* Include escalation paths for different types of issues
* Test transfer logic across different customer personas
2. **Context Preservation**
* Configure comprehensive call context transfer
* Include customer information, conversation summary, and specific needs
* Provide clear reason for transfer to minimize customer frustration
* Train human agents on receiving AI-transferred calls
### Webhook Development
1. **Modal-driven Configuration**
* Leverage the sophisticated modal interface for complex setups
* Use template library for validated starting configurations
* Test API endpoints directly within the interface
* Validate parameter mappings with real conversation data
2. **Security Implementation**
* Always use HTTPS endpoints
* Configure proper authentication through secure header management
* Validate and sanitize all incoming data
* Use rate limiting to prevent abuse
### Calendar Integration Optimization
1. **Multi-Provider Strategy**
* Support both Google Calendar and Outlook for maximum compatibility
* Configure fallback providers for high availability
* Implement cross-platform availability checking
* Maintain consistent booking experience across providers
2. **Smart Scheduling**
* Use intelligent availability detection with buffer times
* Implement automatic conflict resolution and rescheduling
* Configure timezone-aware booking for global customers
* Set up automated reminder and confirmation systems
### Recall Protocol Management
1. **Strategic Planning**
* Define clear success criteria to prevent unnecessary callbacks
* Implement progressive escalation with varied approaches
* Respect customer preferences and compliance requirements
* Monitor and optimize based on performance analytics
2. **Performance Optimization**
* Analyze recall effectiveness by timing and strategy
* A/B test different callback intervals and approaches
* Use customer behavior data to optimize scheduling
* Implement intelligent DNC management and compliance
**Compliance Requirements**: All integrations must comply with applicable regulations including TCPA (US), GDPR (EU), and industry-specific requirements. Always include proper consent mechanisms and opt-out procedures.
## Next Steps
After configuring your Actions & Tools, you can further enhance your agent with:
* **Input Parameters**: Set up dynamic variables for personalized conversations
* **Output Settings**: Configure data extraction and webhook delivery
* **Evaluations**: Define success metrics and conversation quality measures
* **Knowledge Base**: Add contextual information to improve agent responses