VoIP.ms Wiki - User contributions [en]

AI agents

2026-06-15T20:05:00Z

Johann Jimenez:

{| cellspacing="0" style="width: 100%; background: linear-gradient(135deg, #f8fafc 0%, #f1f5f9 100%); border: 1px solid #e2e8f0; border-radius: 8px; padding: 35px; margin-bottom: 25px; box-shadow: 0 1px 3px rgba(0,0,0,0.05);"
|-
| style="text-align: center;" |

<div style="font-size: 2.8em; font-weight: 200; color: #1e293b; margin-bottom: 15px; letter-spacing: -2px;">AI Agents (Beta)</div>

<div style="font-size: 1rem; color: #64748b; margin-bottom: 15px;">
Configure a Voice Agent to better handle your inbound calls.
</div>

<div style="font-size: 0.9rem; color: #94a3b8;">
'''[https://wiki.voip.ms/ 🇨🇦 Français (Bientôt disponible)]'''  •  '''[https://wiki.voip.ms/ 🇲🇽 Español (Próximamente)]'''
</div>

|}

This guide explains how to configure VoIP.ms AI Voice Agent to handle inbound calls within your existing telephony setup.

The AI Voice Agent acts as a virtual first point of contact, capable of answering calls, understanding caller intent, and responding based on the behavior you define during configuration. Proper setup is critical, as the agent's performance is directly influenced by how clearly its instructions, call flows, and routing logic are defined.

'''Important:''' The AI agent does not "learn" your business automatically. It operates based on the rules, prompts, and context you provide — making configuration a key factor in achieving accurate and reliable interactions.

{| cellspacing="0" style="width: 100%; background: linear-gradient(135deg, #fef2f2 0%, #fee2e2 100%); border: 1px solid #fca5a5; border-radius: 8px; padding: 25px; margin: 25px 0; box-shadow: 0 2px 10px rgba(248, 113, 113, 0.1);"
|-
| style="text-align: left;" |
<div style="font-size: 1.1em; font-weight: 500; color: #b91c1c; margin-bottom: 15px;">'''Pricing'''</div>

During the Beta Period, the pricing is '''$10 per agent per month'''. Afterwards, the standard price will be $25 per agent per month. Furthermore, '''per-minute pricing is $0.25/min'''. This includes STT, TTD, and LLM capabilities, so you get full functionality with no hidden costs.

|}

__TOC__

= Getting Started =

{| cellspacing="0" style="width: 100%; background: white; border: 1px solid #e2e8f0; border-radius: 12px; padding: 25px; margin: 20px 0; box-shadow: 0 2px 10px rgba(0,0,0,0.06);"
|-
| style="vertical-align: top;" |

To access the AI Agents feature, navigate to the [https://voip.ms VoIP.ms Customer Portal]and click on '''AI Agents (BETA)''' in the navigation bar.

[[File:AI_Agent_-_Dashboard.png|thumb|none|600px]]

|}

= Creating an Agent =

{| cellspacing="0" style="width: 100%; background: white; border: 1px solid #e2e8f0; border-radius: 12px; padding: 25px; margin: 20px 0; box-shadow: 0 2px 10px rgba(0,0,0,0.06);"
|-
| style="vertical-align: top;" |

Click on '''Create New AI Agent'''.

[[File:IA agents 2.png|thumb|none|600px]]

You will see two options:
* '''Simple Voice Agent''' — A guided, step-by-step setup ideal for most use cases. Covers the essentials: voice, personality, purpose, call routing, and a knowledge base.
* '''Advanced Voice Agent''' — Provides full control over the LLM model, TTS model, MCP servers, webhook tools, and custom parameters for complex integrations.

[[File:IA agents 3.png|thumb|none|600px]]

Choose the option that best fits your needs. The sections below cover both paths in detail.

|}

== Simple Voice Agent ==

The '''Simple Voice Agent''' walks you through setup in a series of focused steps. Complete each step and click '''Next''' to advance.

{| cellspacing="0" style="width: 100%; background: white; border: 1px solid #e2e8f0; border-radius: 12px; padding: 25px; margin: 20px 0; box-shadow: 0 2px 10px rgba(0,0,0,0.06);"
|-
| style="vertical-align: top;" |

=== Step 1: Basic Configuration ===

In this section, you will define the foundational details of your agent:

* '''Agent Name''' — Assign a name to easily identify the agent
* '''Description''' — Provide a brief explanation of the agent's purpose (eg. Support Agent Level 1)
* '''Voice Selection''' — Choose from an extensive list of available voices

[[File:AI_Agent_-_Basic_Configuration.png|thumb|none|600px]]

{| cellspacing="0" style="width: 100%; background: linear-gradient(135deg, #fef2f2 0%, #fee2e2 100%); border: 1px solid #fca5a5; border-radius: 8px; padding: 25px; margin: 25px 0; box-shadow: 0 2px 10px rgba(248, 113, 113, 0.1);"
|-
| style="text-align: left;" |
<div style="font-size: 1.1em; font-weight: 500; color: #b91c1c; margin-bottom: 15px;">'''Note'''</div>

Not all voices currently have preview functionality. This will be expanded in future updates.

|}

Once completed, click '''Next''' to proceed.

|}

{| cellspacing="0" style="width: 100%; background: white; border: 1px solid #e2e8f0; border-radius: 12px; padding: 25px; margin: 20px 0; box-shadow: 0 2px 10px rgba(0,0,0,0.06);"
|-
| style="vertical-align: top;" |

=== Step 2: Personality and Tone ===

This section defines how your agent communicates. Based on your answers, VoIP.ms starts to build a prompt on your behalf in the back-end.

* '''Language''' — Select the primary language for the agent (English, Spanish or French)
* '''Tone and Interaction Style''' — Select how the agent should interact with callers. By default, simply go for Short and Concise.
* '''Agent Personality''' — Use this field to provide additional instructions and context, such as: agent name, company name, behavioral guidelines, or communication style preferences. This input directly influences how the AI behaves during calls.

[[File:AI_Agent_-_Personality_and_Tone.png|thumb|none|600px]]

|}

{| cellspacing="0" style="width: 100%; background: white; border: 1px solid #e2e8f0; border-radius: 12px; padding: 25px; margin: 20px 0; box-shadow: 0 2px 10px rgba(0,0,0,0.06);"
|-
| style="vertical-align: top;" |

=== Step 3: Purpose & Communication ===

Here you need to define what the agent is designed to do and how it interacts at the start of a call:

* '''Purpose of the Agent''' — Select the purpose of the agent anywhere from Troubleshooting Common Issues (Default), to Collect Basic Information.
* '''Greeting Message''' — Define the initial message the agent will deliver when answering a call. This text will be spoken exactly as written, so ensure clarity and professionalism. For instance: Hi, this is Violet with Company X Support. I can help for most issues or connect you with a live engineer. What seems to be happening today?

[[File:AI_Agent_-_Purpose_and_Communication.png|thumb|none|600px]] >>> '''To be changed.'''

|}

{| cellspacing="0" style="width: 100%; background: white; border: 1px solid #e2e8f0; border-radius: 12px; padding: 25px; margin: 20px 0; box-shadow: 0 2px 10px rgba(0,0,0,0.06);"
|-
| style="vertical-align: top;" |

=== Step 4: Call Routing & Transfer Options ===

This section allows you to configure whether the AI agent can transfer calls. If you do not want call transfers, simply click '''Next'''. Otherwise, to '''enable transfers''', click the '''Allow AI agent to transfer calls to specific destinations''' checkbox, then add a '''label''' to describe your transfer scenario(s) (e.g., "Sales Team", "Support Line") or the name of the given person (e.g. "John Doe").

Then, add as many destinations as you wish from:
* [[Sub_Accounts|Internal Extensions]]
* DID Phone numbers
* [[Phone_book|Phonebook speed dial entries]]

[[File:IA agents 11.png|thumb|none|600px]]

|}

{| cellspacing="0" style="width: 100%; background: white; border: 1px solid #e2e8f0; border-radius: 12px; padding: 25px; margin: 20px 0; box-shadow: 0 2px 10px rgba(0,0,0,0.06);"
|-
| style="vertical-align: top;" |

=== Step 5: Knowledgebase ===

In this section, you define the information sources the agent will use to respond to callers. You can add links such as your website, a knowledge base, a FAQ page, or even a Wiki. '''Ensure all links are publicly accessible and readable.'''

'''Optional:''' Enable '''Allow web search for additional information when appropriate''' to supplement responses with live web results.

Once all sections are completed, click '''Create Agent''' to finalize the setup of your Simple Voice Agent.

[[File:IA agents 12.png|thumb|none|600px]]

|}

== Advanced Voice Agent ==

The '''Advanced Voice Agent''' provides full control over your agent's underlying models, integrations ('''coming soon!'''), and behavior. Use this option when you need to select a specific LLM or TTS model, connect external tools via MCP servers or webhooks, or define custom parameters for complex use cases.

{| cellspacing="0" style="width: 100%; background: white; border: 1px solid #e2e8f0; border-radius: 12px; padding: 25px; margin: 20px 0; box-shadow: 0 2px 10px rgba(0,0,0,0.06);"
|-
| style="vertical-align: top;" |

=== General Settings ===

In this section, you define the core configuration of your advanced agent:

* '''Agent Name''' — Assign a name to identify the agent
* '''TTS Model''' — Select the text-to-speech model for voice generation
* '''Voice''' — Choose the voice used during calls. Please note that some voices currently do not have preview functionality. This will be expanded in future updates.
* '''LLM Model''' — Select the language model that powers the agent's reasoning and responses
* '''Background Audio''' — Optionally add background sound during calls
* '''Language''' — Define the primary language of the agent (English, Spanish or French)
* '''Description''' — Provide a brief summary of the agent's purpose

[[File:IA advanced 1.png|thumb|none|600px]]

|}

{| cellspacing="0" style="width: 100%; background: white; border: 1px solid #e2e8f0; border-radius: 12px; padding: 25px; margin: 20px 0; box-shadow: 0 2px 10px rgba(0,0,0,0.06);"
|-
| style="vertical-align: top;" |

=== Call Routing and Transfer ===

This section allows you to configure whether the AI agent can transfer calls. To '''enable transfers''', click the '''Allow AI agent to transfer calls to specific destinations''' checkbox, then add a '''label''' to describe your transfer scenario(s) (e.g., "Sales Team", "Support Line") or the name of the given person (e.g. "John Doe").

Then, add as many destinations as you wish from:
* [[Sub_Accounts|Internal Extensions]]
* Phone numbers (DID)
* [[Phone_book|Phonebook speed dial entries]]

[[File:IA advanced 2.png|thumb|none|600px]]

|}

{| cellspacing="0" style="width: 100%; background: white; border: 1px solid #e2e8f0; border-radius: 12px; padding: 25px; margin: 20px 0; box-shadow: 0 2px 10px rgba(0,0,0,0.06);"
|-
| style="vertical-align: top;" |

=== Knowledge Base ===

In this section, you define the information sources the agent will use to respond to callers. You can add links such as your website, a knowledge base, a FAQ page, or even a Wiki. '''Ensure all links are publicly accessible and readable.'''

'''Optional:''' Enable '''Allow web search for additional information when appropriate''' to supplement responses with live web results.

[[File:AI_Agent_-_Advanced_-_Knowledge_Base.png|thumb|none|600px]]

|}

{| cellspacing="0" style="width: 100%; background: white; border: 1px solid #e2e8f0; border-radius: 12px; padding: 25px; margin: 20px 0; box-shadow: 0 2px 10px rgba(0,0,0,0.06);"
|-
| style="vertical-align: top;" |

== Advanced Tools and Integrations ==

Extensions allow AI Agents to connect with external systems such as CRMs, helpdesks, databases, and internal business applications.

These integrations enable your AI agents to send information, retrieve data, and perform actions. Helping automate workflows and provide more personalized customer interactions.

Extensions are configured from the '''Extensions''' section within the AI Agent configuration page.

There are two types of integrations available:

* Webhooks
* MCP Servers

Each serves a different purpose and can be used independently or together depending on your workflow requirements.

=== Webhooks ===

Webhooks allow your AI Agent to send information to an external system when a specific event occurs during the call lifecycle.

In simple terms:

''"When something happens, send this information to another system."''

Webhooks are commonly used to:

* Create support tickets
* Log call information
* Send call summaries
* Update CRM records
* Trigger internal workflows
* Notify external applications

=== Webhook Configuration ===

The following fields are available when creating or editing a webhook.

{| class="wikitable"
! Field
! Description
! Purpose
|-
| Name
| Internal identifier
| Unique system identifier used by the AI Agent to reference the webhook.
|-
| Friendly Name
| Display name
| Human-readable name displayed within the Portal.
|-
| Description
| Usage description
| Explains the purpose of the webhook and when it should be used. The AI Agent may use this information when determining whether to execute the webhook.
|-
| Trigger Condition
| Execution timing
| Defines when the webhook is triggered.
|-
| HTTP Method
| Request method
| Defines how data is sent to the destination system. Common methods include POST, GET, PUT, PATCH, and DELETE.
|-
| URL
| Destination endpoint
| Web address that receives the webhook request.
|-
| Parameters
| Data fields
| Information sent to the external system.
|}

=== Parameters ===

Parameters define the information that will be sent to the destination system.

For each parameter, you can specify:

* A dynamic value generated by the AI Agent
* A fixed value that is always sent
* A default value used when information is unavailable

=== Dynamic Values ===

If the Value field is left empty, the AI Agent will attempt to populate it using information collected during the conversation.

Examples include:

* Customer name
* Email address
* Phone number
* Call reason
* Issue description

=== Fixed Values ===

A fixed value will always be sent with the request.

Example:

* priority = normal

=== Default Values ===

A default value will only be used if the AI Agent is unable to determine the information from the conversation.

== Example Parameter Configuration ==

{| class="wikitable"
! Parameter
! Value
! Result
|-
| subject
|
| AI generates a subject based on the conversation.
|-
| description
|
| AI generates a call summary.
|-
| customer_email
|
| AI attempts to capture the caller's email address.
|-
| priority
| normal
| Always sends "normal" as the priority value.
|}

[[File:Webhooks.png|thumb|none|600px]]

= MCP Servers =

MCP (Model Context Protocol) Servers allow AI Agents to interact with external systems in real time during a conversation.

Unlike webhooks, which send information in a single direction, MCP Servers establish a live connection that enables the AI Agent to query external tools and retrieve information while speaking with the caller.

In simple terms:

''"Connect the AI Agent to an external system so it can retrieve information and perform actions during the call."''

== Common MCP Use Cases ==

MCP Servers can be used to:

* Retrieve customer information from a CRM
* Check order status
* Verify product availability
* Access account information
* Search internal databases
* Execute business-specific workflows

Because these actions occur during the conversation, the caller can receive immediate responses without requiring manual intervention.

== MCP Server Configuration ==

The following fields are available when configuring an MCP Server.

{| class="wikitable"
! Field
! Description
! Purpose
|-
| Name
| Connection name
| Friendly name used to identify the server connection within the Portal.
|-
| Transport Type
| Connection method
| Defines how the AI Agent communicates with the MCP Server. Supported options include SSE and HTTP.
|-
| URL
| Server endpoint
| Address of the MCP Server provided by the connected platform.
|-
| Auth Headers
| Authentication credentials
| Security information required to access the external system.
|}

== Authentication Headers ==

Authentication Headers are commonly used to grant access to external systems.

Examples include:

{| class="wikitable"
! Header
! Example Value
|-
| Authorization
| Bearer abc123...
|-
| X-API-Key
| your-api-key
|}

These values are typically provided by the technical team responsible for the connected application.

== Additional Notes ==

Some MCP implementations support advanced initialization options that may be configured through the API.

These settings are typically used for custom integrations and advanced deployment scenarios.

[[File:MCPs.png|thumb|none|600px]]

|}

{| cellspacing="0" style="width: 100%; background: white; border: 1px solid #e2e8f0; border-radius: 12px; padding: 25px; margin: 20px 0; box-shadow: 0 2px 10px rgba(0,0,0,0.06);"
|-
| style="vertical-align: top;" |

=== Communication Settings ===

In this final section, you can define how the agent interacts at the start of a call and can also build the entire prompt :

* '''Greeting Message''' — Set the initial message delivered when answering a call
* '''System Prompt''' — Define the core instructions that guide the agent's behavior and responses ([[AI_Prompts|see AI Prompts examples here]])

[[File:IA advanced 5.1.png|thumb|none|600px]]

|}

= Linking Your Agent to a DID =

{| cellspacing="0" style="width: 100%; background: white; border: 1px solid #e2e8f0; border-radius: 12px; padding: 25px; margin: 20px 0; box-shadow: 0 2px 10px rgba(0,0,0,0.06);"
|-
| style="vertical-align: top;" |

Once your agent is created, you need to [[Manage_DID#Edit_a_single_DID_number|assign it]] to a phone number (DID) so it can start answering inbound calls.

# Go to '''DID Numbers''' → '''Manage DIDs''' in the customer portal
# Click '''Edit''' on the DID you want to route to the agent
# In the routing destination section, select '''AI Voice Agent''' from the dropdown
# Choose the specific agent you created from the list
# Click '''Apply'''

Your AI Agent will now answer all inbound calls to that DID!

[[File:AI_Agent_-_Manage_DIDs.png|thumb|none|600px]]

|}

= Servers/ Point of Presence (POP) =

{| cellspacing="0" style="width: 100%; background: white; border: 1px solid #e2e8f0; border-radius: 12px; padding: 25px; margin: 20px 0; box-shadow: 0 2px 10px rgba(0,0,0,0.06);"
|-
| style="vertical-align: top;" |
[[File:Serverspops.png|thumb|none|600px]]

The '''Servers''' section allows you to configure the Point of Presence (POP) used by your AI Voice Agent.

The POP represents the network server location responsible for receiving and processing calls handled by the AI Agent.

This configuration is available when creating or editing an AI Voice Agent in:

* Simple Agent
* Advanced Agent
* Accordion flows

The Servers tab provides a centralized location to define where your AI Agent operates within the network.

== Understanding Point of Presence (POP) ==

A Point of Presence (POP) is the server location associated with your AI Agent.

The selected server determines the infrastructure used when the agent receives and processes calls.

The available server list matches the servers available under your account information.

== Configuration Model Update ==

The Servers tab introduces a new configuration model that separates AI Agent configuration from phone number routing.

{| class="wikitable"
! Previous Model
! New Model
|-
| One AI Agent was tied to one DID
| One AI Agent can be used across multiple DIDs
|-
| The system attempted to synchronize DID and agent assignments when saving routing
| DID routing only stores the selected routing option
|-
| Configuration was associated directly with the phone number
| AI Agent configuration is managed from the Servers tab
|}

== Configuring the Server ==

When configuring an AI Voice Agent, you can select the desired Point of Presence from the available server list.

The selected POP determines where the agent receives and processes incoming calls.

To configure the server:

# Open the AI Voice Agent configuration.
# Navigate to the '''Servers''' section.
# Select the desired Point of Presence.
# Save the configuration.

Once configured, the AI Agent will use the selected server for its call processing operations.

== Multi-DID Support ==

The new configuration model allows a single AI Agent to be assigned to multiple phone numbers.

Each DID can route calls to the same AI Voice Agent while maintaining its own routing configuration.

Example:

{| class="wikitable"
! Phone Number
! Routing Configuration
|-
| DID 315...
| Routes to AI Agent "Reception"
|-
| DID 442...
| Routes to AI Agent "Reception"
|}

The AI Agent configuration is created once, and multiple phone numbers can reference the same agent.

== Benefits ==

The Servers tab improves AI Agent management by allowing:

* Multiple DIDs to use the same AI Agent
* Centralized agent configuration
* Easier server management
* Simplified DID routing
* Greater flexibility when scaling AI call flows

By separating agent configuration from phone number routing, administrators can manage AI Agents more efficiently and support more complex communication environments.

|}

= Frequently Asked Questions =

{| cellspacing="0" style="width: 100%; background: white; border: 1px solid #e2e8f0; border-radius: 12px; padding: 25px; margin: 20px 0; box-shadow: 0 2px 10px rgba(0,0,0,0.06);"
|-
| style="vertical-align: top;" |

'''Q: Can the AI agent handle outbound calls?'''

A: No — AI Agents are designed for inbound calls only. They answer calls made to your DID; they cannot initiate outbound calls.

'''Q: What languages does the agent support?'''

A: English, Spanish, and French.

'''Q: What is the difference between Simple and Advanced?'''

A: The Simple Voice Agent guides you through a fixed set of steps and covers everything most users need: voice, personality, purpose, call routing, and a knowledge base. The Advanced Voice Agent exposes the underlying LLM and TTS model selection, background audio, and (coming soon) MCP servers and webhook tool integrations for more complex use cases.

'''Q: Can I have multiple agents?'''

A: Yes — you can create as many agents as needed and assign each one to a different DID.

'''Q: Can I edit my agent after creating it?'''

A: Yes — from the AI Agents dashboard you can edit, duplicate, or delete any agent at any time.

'''Q: What happens if the agent cannot answer a question?'''

A: The agent will let the caller know it does not have that information. If call transfers are configured, it can route the caller to a human agent instead.

'''Q: Does the agent answer calls 24/7?'''

A: Yes — once assigned to a DID, the agent answers all inbound calls at any hour.

'''Q: Does the AI agent work with my existing DID?'''

A: Yes — any eligible DID can be routed to an AI Agent from '''DID Numbers → Manage DIDs'''.

'''Q: What does "(Beta)" mean?'''

A: The feature is in active development. Some capabilities — such as Advanced Tools and Integrations — are not yet available, and behaviour may change before the general release.

{| cellspacing="0" style="width: 100%; background: linear-gradient(135deg, #fef2f2 0%, #fee2e2 100%); border: 1px solid #fca5a5; border-radius: 8px; padding: 25px; margin: 25px 0; box-shadow: 0 2px 10px rgba(248, 113, 113, 0.1);"
|-
| style="text-align: left;" |

We will keep populating this FAQ as questions come along. '''Thanks in advance for your feedback, support and questions!'''

|}

|}

= Need Help or Got Feedback? =

{| cellspacing="0" style="width: 100%; background: white; border: 1px solid #e2e8f0; border-radius: 12px; padding: 25px; margin: 20px 0; box-shadow: 0 2px 10px rgba(0,0,0,0.06);"
|-
| style="vertical-align: top;" |

<div style="font-size: 1.1em; font-weight: 600; color: #1e293b; margin-bottom: 15px;">Support resources</div>

* '''Email''' — [mailto:support@voip.ms support@voip.ms]

'''When reporting an AI Agent issue, include:'''
* The name of the agent and the DID it is assigned to
* The date and time of the call, including the UniqueID found in the CDR
* A description of the behaviour observed vs. what was expected

|}

[[Category:Guides]]

File:Serverspops.png

2026-06-15T20:04:29Z

Johann Jimenez:

AI agents

2026-06-09T15:02:27Z

Johann Jimenez:

{| cellspacing="0" style="width: 100%; background: linear-gradient(135deg, #f8fafc 0%, #f1f5f9 100%); border: 1px solid #e2e8f0; border-radius: 8px; padding: 35px; margin-bottom: 25px; box-shadow: 0 1px 3px rgba(0,0,0,0.05);"
|-
| style="text-align: center;" |

<div style="font-size: 2.8em; font-weight: 200; color: #1e293b; margin-bottom: 15px; letter-spacing: -2px;">AI Agents (Beta)</div>

<div style="font-size: 1rem; color: #64748b; margin-bottom: 15px;">
Configure a Voice Agent to better handle your inbound calls.
</div>

<div style="font-size: 0.9rem; color: #94a3b8;">
'''[https://wiki.voip.ms/ 🇨🇦 Français (Bientôt disponible)]'''  •  '''[https://wiki.voip.ms/ 🇲🇽 Español (Próximamente)]'''
</div>

|}

This guide explains how to configure VoIP.ms AI Voice Agent to handle inbound calls within your existing telephony setup.

The AI Voice Agent acts as a virtual first point of contact, capable of answering calls, understanding caller intent, and responding based on the behavior you define during configuration. Proper setup is critical, as the agent's performance is directly influenced by how clearly its instructions, call flows, and routing logic are defined.

'''Important:''' The AI agent does not "learn" your business automatically. It operates based on the rules, prompts, and context you provide — making configuration a key factor in achieving accurate and reliable interactions.

{| cellspacing="0" style="width: 100%; background: linear-gradient(135deg, #fef2f2 0%, #fee2e2 100%); border: 1px solid #fca5a5; border-radius: 8px; padding: 25px; margin: 25px 0; box-shadow: 0 2px 10px rgba(248, 113, 113, 0.1);"
|-
| style="text-align: left;" |
<div style="font-size: 1.1em; font-weight: 500; color: #b91c1c; margin-bottom: 15px;">'''Pricing'''</div>

During the Beta Period, the pricing is '''$10 per agent per month'''. Afterwards, the standard price will be $25 per agent per month. Furthermore, '''per-minute pricing is $0.25/min'''. This includes STT, TTD, and LLM capabilities, so you get full functionality with no hidden costs.

|}

__TOC__

= Getting Started =

{| cellspacing="0" style="width: 100%; background: white; border: 1px solid #e2e8f0; border-radius: 12px; padding: 25px; margin: 20px 0; box-shadow: 0 2px 10px rgba(0,0,0,0.06);"
|-
| style="vertical-align: top;" |

To access the AI Agents feature, navigate to the [https://voip.ms VoIP.ms Customer Portal]and click on '''AI Agents (BETA)''' in the navigation bar.

[[File:AI_Agent_-_Dashboard.png|thumb|none|600px]]

|}

= Creating an Agent =

{| cellspacing="0" style="width: 100%; background: white; border: 1px solid #e2e8f0; border-radius: 12px; padding: 25px; margin: 20px 0; box-shadow: 0 2px 10px rgba(0,0,0,0.06);"
|-
| style="vertical-align: top;" |

Click on '''Create New AI Agent'''.

[[File:IA agents 2.png|thumb|none|600px]]

You will see two options:
* '''Simple Voice Agent''' — A guided, step-by-step setup ideal for most use cases. Covers the essentials: voice, personality, purpose, call routing, and a knowledge base.
* '''Advanced Voice Agent''' — Provides full control over the LLM model, TTS model, MCP servers, webhook tools, and custom parameters for complex integrations.

[[File:IA agents 3.png|thumb|none|600px]]

Choose the option that best fits your needs. The sections below cover both paths in detail.

|}

== Simple Voice Agent ==

The '''Simple Voice Agent''' walks you through setup in a series of focused steps. Complete each step and click '''Next''' to advance.

{| cellspacing="0" style="width: 100%; background: white; border: 1px solid #e2e8f0; border-radius: 12px; padding: 25px; margin: 20px 0; box-shadow: 0 2px 10px rgba(0,0,0,0.06);"
|-
| style="vertical-align: top;" |

=== Step 1: Basic Configuration ===

In this section, you will define the foundational details of your agent:

* '''Agent Name''' — Assign a name to easily identify the agent
* '''Description''' — Provide a brief explanation of the agent's purpose (eg. Support Agent Level 1)
* '''Voice Selection''' — Choose from an extensive list of available voices

[[File:AI_Agent_-_Basic_Configuration.png|thumb|none|600px]]

{| cellspacing="0" style="width: 100%; background: linear-gradient(135deg, #fef2f2 0%, #fee2e2 100%); border: 1px solid #fca5a5; border-radius: 8px; padding: 25px; margin: 25px 0; box-shadow: 0 2px 10px rgba(248, 113, 113, 0.1);"
|-
| style="text-align: left;" |
<div style="font-size: 1.1em; font-weight: 500; color: #b91c1c; margin-bottom: 15px;">'''Note'''</div>

Not all voices currently have preview functionality. This will be expanded in future updates.

|}

Once completed, click '''Next''' to proceed.

|}

{| cellspacing="0" style="width: 100%; background: white; border: 1px solid #e2e8f0; border-radius: 12px; padding: 25px; margin: 20px 0; box-shadow: 0 2px 10px rgba(0,0,0,0.06);"
|-
| style="vertical-align: top;" |

=== Step 2: Personality and Tone ===

This section defines how your agent communicates. Based on your answers, VoIP.ms starts to build a prompt on your behalf in the back-end.

* '''Language''' — Select the primary language for the agent (English, Spanish or French)
* '''Tone and Interaction Style''' — Select how the agent should interact with callers. By default, simply go for Short and Concise.
* '''Agent Personality''' — Use this field to provide additional instructions and context, such as: agent name, company name, behavioral guidelines, or communication style preferences. This input directly influences how the AI behaves during calls.

[[File:AI_Agent_-_Personality_and_Tone.png|thumb|none|600px]]

|}

{| cellspacing="0" style="width: 100%; background: white; border: 1px solid #e2e8f0; border-radius: 12px; padding: 25px; margin: 20px 0; box-shadow: 0 2px 10px rgba(0,0,0,0.06);"
|-
| style="vertical-align: top;" |

=== Step 3: Purpose & Communication ===

Here you need to define what the agent is designed to do and how it interacts at the start of a call:

* '''Purpose of the Agent''' — Select the purpose of the agent anywhere from Troubleshooting Common Issues (Default), to Collect Basic Information.
* '''Greeting Message''' — Define the initial message the agent will deliver when answering a call. This text will be spoken exactly as written, so ensure clarity and professionalism. For instance: Hi, this is Violet with Company X Support. I can help for most issues or connect you with a live engineer. What seems to be happening today?

[[File:AI_Agent_-_Purpose_and_Communication.png|thumb|none|600px]] >>> '''To be changed.'''

|}

{| cellspacing="0" style="width: 100%; background: white; border: 1px solid #e2e8f0; border-radius: 12px; padding: 25px; margin: 20px 0; box-shadow: 0 2px 10px rgba(0,0,0,0.06);"
|-
| style="vertical-align: top;" |

=== Step 4: Call Routing & Transfer Options ===

This section allows you to configure whether the AI agent can transfer calls. If you do not want call transfers, simply click '''Next'''. Otherwise, to '''enable transfers''', click the '''Allow AI agent to transfer calls to specific destinations''' checkbox, then add a '''label''' to describe your transfer scenario(s) (e.g., "Sales Team", "Support Line") or the name of the given person (e.g. "John Doe").

Then, add as many destinations as you wish from:
* [[Sub_Accounts|Internal Extensions]]
* DID Phone numbers
* [[Phone_book|Phonebook speed dial entries]]

[[File:IA agents 11.png|thumb|none|600px]]

|}

{| cellspacing="0" style="width: 100%; background: white; border: 1px solid #e2e8f0; border-radius: 12px; padding: 25px; margin: 20px 0; box-shadow: 0 2px 10px rgba(0,0,0,0.06);"
|-
| style="vertical-align: top;" |

=== Step 5: Knowledgebase ===

In this section, you define the information sources the agent will use to respond to callers. You can add links such as your website, a knowledge base, a FAQ page, or even a Wiki. '''Ensure all links are publicly accessible and readable.'''

'''Optional:''' Enable '''Allow web search for additional information when appropriate''' to supplement responses with live web results.

Once all sections are completed, click '''Create Agent''' to finalize the setup of your Simple Voice Agent.

[[File:IA agents 12.png|thumb|none|600px]]

|}

== Advanced Voice Agent ==

The '''Advanced Voice Agent''' provides full control over your agent's underlying models, integrations ('''coming soon!'''), and behavior. Use this option when you need to select a specific LLM or TTS model, connect external tools via MCP servers or webhooks, or define custom parameters for complex use cases.

{| cellspacing="0" style="width: 100%; background: white; border: 1px solid #e2e8f0; border-radius: 12px; padding: 25px; margin: 20px 0; box-shadow: 0 2px 10px rgba(0,0,0,0.06);"
|-
| style="vertical-align: top;" |

=== General Settings ===

In this section, you define the core configuration of your advanced agent:

* '''Agent Name''' — Assign a name to identify the agent
* '''TTS Model''' — Select the text-to-speech model for voice generation
* '''Voice''' — Choose the voice used during calls. Please note that some voices currently do not have preview functionality. This will be expanded in future updates.
* '''LLM Model''' — Select the language model that powers the agent's reasoning and responses
* '''Background Audio''' — Optionally add background sound during calls
* '''Language''' — Define the primary language of the agent (English, Spanish or French)
* '''Description''' — Provide a brief summary of the agent's purpose

[[File:IA advanced 1.png|thumb|none|600px]]

|}

{| cellspacing="0" style="width: 100%; background: white; border: 1px solid #e2e8f0; border-radius: 12px; padding: 25px; margin: 20px 0; box-shadow: 0 2px 10px rgba(0,0,0,0.06);"
|-
| style="vertical-align: top;" |

=== Call Routing and Transfer ===

This section allows you to configure whether the AI agent can transfer calls. To '''enable transfers''', click the '''Allow AI agent to transfer calls to specific destinations''' checkbox, then add a '''label''' to describe your transfer scenario(s) (e.g., "Sales Team", "Support Line") or the name of the given person (e.g. "John Doe").

Then, add as many destinations as you wish from:
* [[Sub_Accounts|Internal Extensions]]
* Phone numbers (DID)
* [[Phone_book|Phonebook speed dial entries]]

[[File:IA advanced 2.png|thumb|none|600px]]

|}

{| cellspacing="0" style="width: 100%; background: white; border: 1px solid #e2e8f0; border-radius: 12px; padding: 25px; margin: 20px 0; box-shadow: 0 2px 10px rgba(0,0,0,0.06);"
|-
| style="vertical-align: top;" |

=== Knowledge Base ===

In this section, you define the information sources the agent will use to respond to callers. You can add links such as your website, a knowledge base, a FAQ page, or even a Wiki. '''Ensure all links are publicly accessible and readable.'''

'''Optional:''' Enable '''Allow web search for additional information when appropriate''' to supplement responses with live web results.

[[File:AI_Agent_-_Advanced_-_Knowledge_Base.png|thumb|none|600px]]

|}

{| cellspacing="0" style="width: 100%; background: white; border: 1px solid #e2e8f0; border-radius: 12px; padding: 25px; margin: 20px 0; box-shadow: 0 2px 10px rgba(0,0,0,0.06);"
|-
| style="vertical-align: top;" |

== Advanced Tools and Integrations ==

Extensions allow AI Agents to connect with external systems such as CRMs, helpdesks, databases, and internal business applications.

These integrations enable your AI agents to send information, retrieve data, and perform actions. Helping automate workflows and provide more personalized customer interactions.

Extensions are configured from the '''Extensions''' section within the AI Agent configuration page.

There are two types of integrations available:

* Webhooks
* MCP Servers

Each serves a different purpose and can be used independently or together depending on your workflow requirements.

=== Webhooks ===

Webhooks allow your AI Agent to send information to an external system when a specific event occurs during the call lifecycle.

In simple terms:

''"When something happens, send this information to another system."''

Webhooks are commonly used to:

* Create support tickets
* Log call information
* Send call summaries
* Update CRM records
* Trigger internal workflows
* Notify external applications

=== Webhook Configuration ===

The following fields are available when creating or editing a webhook.

{| class="wikitable"
! Field
! Description
! Purpose
|-
| Name
| Internal identifier
| Unique system identifier used by the AI Agent to reference the webhook.
|-
| Friendly Name
| Display name
| Human-readable name displayed within the Portal.
|-
| Description
| Usage description
| Explains the purpose of the webhook and when it should be used. The AI Agent may use this information when determining whether to execute the webhook.
|-
| Trigger Condition
| Execution timing
| Defines when the webhook is triggered.
|-
| HTTP Method
| Request method
| Defines how data is sent to the destination system. Common methods include POST, GET, PUT, PATCH, and DELETE.
|-
| URL
| Destination endpoint
| Web address that receives the webhook request.
|-
| Parameters
| Data fields
| Information sent to the external system.
|}

=== Parameters ===

Parameters define the information that will be sent to the destination system.

For each parameter, you can specify:

* A dynamic value generated by the AI Agent
* A fixed value that is always sent
* A default value used when information is unavailable

=== Dynamic Values ===

If the Value field is left empty, the AI Agent will attempt to populate it using information collected during the conversation.

Examples include:

* Customer name
* Email address
* Phone number
* Call reason
* Issue description

=== Fixed Values ===

A fixed value will always be sent with the request.

Example:

* priority = normal

=== Default Values ===

A default value will only be used if the AI Agent is unable to determine the information from the conversation.

== Example Parameter Configuration ==

{| class="wikitable"
! Parameter
! Value
! Result
|-
| subject
|
| AI generates a subject based on the conversation.
|-
| description
|
| AI generates a call summary.
|-
| customer_email
|
| AI attempts to capture the caller's email address.
|-
| priority
| normal
| Always sends "normal" as the priority value.
|}

[[File:Webhooks.png|thumb|none|600px]]

== MCP Servers ==

MCP (Model Context Protocol) Servers allow AI Agents to interact with external systems in real time during a conversation.

Unlike webhooks, which send information in a single direction, MCP Servers establish a live connection that enables the AI Agent to query external tools and retrieve information while speaking with the caller.

In simple terms:

''"Connect the AI Agent to an external system so it can retrieve information and perform actions during the call."''

== Common MCP Use Cases ==

MCP Servers can be used to:

* Retrieve customer information from a CRM
* Check order status
* Verify product availability
* Access account information
* Search internal databases
* Execute business-specific workflows

Because these actions occur during the conversation, the caller can receive immediate responses without requiring manual intervention.

== MCP Server Configuration ==

The following fields are available when configuring an MCP Server.

{| class="wikitable"
! Field
! Description
! Purpose
|-
| Name
| Connection name
| Friendly name used to identify the server connection within the Portal.
|-
| Transport Type
| Connection method
| Defines how the AI Agent communicates with the MCP Server. Supported options include SSE and HTTP.
|-
| URL
| Server endpoint
| Address of the MCP Server provided by the connected platform.
|-
| Auth Headers
| Authentication credentials
| Security information required to access the external system.
|}

== Authentication Headers ==

Authentication Headers are commonly used to grant access to external systems.

Examples include:

{| class="wikitable"
! Header
! Example Value
|-
| Authorization
| Bearer abc123...
|-
| X-API-Key
| your-api-key
|}

These values are typically provided by the technical team responsible for the connected application.

== Additional Notes ==

Some MCP implementations support advanced initialization options that may be configured through the API.

These settings are typically used for custom integrations and advanced deployment scenarios.

[[File:MCPs.png|thumb|none|600px]]

|}

{| cellspacing="0" style="width: 100%; background: white; border: 1px solid #e2e8f0; border-radius: 12px; padding: 25px; margin: 20px 0; box-shadow: 0 2px 10px rgba(0,0,0,0.06);"
|-
| style="vertical-align: top;" |

=== Communication Settings ===

In this final section, you can define how the agent interacts at the start of a call and can also build the entire prompt :

* '''Greeting Message''' — Set the initial message delivered when answering a call
* '''System Prompt''' — Define the core instructions that guide the agent's behavior and responses ([[AI_Prompts|see AI Prompts examples here]])

[[File:IA advanced 5.1.png|thumb|none|600px]]

|}

= Linking Your Agent to a DID =

{| cellspacing="0" style="width: 100%; background: white; border: 1px solid #e2e8f0; border-radius: 12px; padding: 25px; margin: 20px 0; box-shadow: 0 2px 10px rgba(0,0,0,0.06);"
|-
| style="vertical-align: top;" |

Once your agent is created, you need to [[Manage_DID#Edit_a_single_DID_number|assign it]] to a phone number (DID) so it can start answering inbound calls.

# Go to '''DID Numbers''' → '''Manage DIDs''' in the customer portal
# Click '''Edit''' on the DID you want to route to the agent
# In the routing destination section, select '''AI Voice Agent''' from the dropdown
# Choose the specific agent you created from the list
# Click '''Apply'''

Your AI Agent will now answer all inbound calls to that DID!

[[File:AI_Agent_-_Manage_DIDs.png|thumb|none|600px]]

|}

= Frequently Asked Questions =

{| cellspacing="0" style="width: 100%; background: white; border: 1px solid #e2e8f0; border-radius: 12px; padding: 25px; margin: 20px 0; box-shadow: 0 2px 10px rgba(0,0,0,0.06);"
|-
| style="vertical-align: top;" |

'''Q: Can the AI agent handle outbound calls?'''

A: No — AI Agents are designed for inbound calls only. They answer calls made to your DID; they cannot initiate outbound calls.

'''Q: What languages does the agent support?'''

A: English, Spanish, and French.

'''Q: What is the difference between Simple and Advanced?'''

A: The Simple Voice Agent guides you through a fixed set of steps and covers everything most users need: voice, personality, purpose, call routing, and a knowledge base. The Advanced Voice Agent exposes the underlying LLM and TTS model selection, background audio, and (coming soon) MCP servers and webhook tool integrations for more complex use cases.

'''Q: Can I have multiple agents?'''

A: Yes — you can create as many agents as needed and assign each one to a different DID.

'''Q: Can I edit my agent after creating it?'''

A: Yes — from the AI Agents dashboard you can edit, duplicate, or delete any agent at any time.

'''Q: What happens if the agent cannot answer a question?'''

A: The agent will let the caller know it does not have that information. If call transfers are configured, it can route the caller to a human agent instead.

'''Q: Does the agent answer calls 24/7?'''

A: Yes — once assigned to a DID, the agent answers all inbound calls at any hour.

'''Q: Does the AI agent work with my existing DID?'''

A: Yes — any eligible DID can be routed to an AI Agent from '''DID Numbers → Manage DIDs'''.

'''Q: What does "(Beta)" mean?'''

A: The feature is in active development. Some capabilities — such as Advanced Tools and Integrations — are not yet available, and behaviour may change before the general release.

{| cellspacing="0" style="width: 100%; background: linear-gradient(135deg, #fef2f2 0%, #fee2e2 100%); border: 1px solid #fca5a5; border-radius: 8px; padding: 25px; margin: 25px 0; box-shadow: 0 2px 10px rgba(248, 113, 113, 0.1);"
|-
| style="text-align: left;" |

We will keep populating this FAQ as questions come along. '''Thanks in advance for your feedback, support and questions!'''

|}

|}

= Need Help or Got Feedback? =

{| cellspacing="0" style="width: 100%; background: white; border: 1px solid #e2e8f0; border-radius: 12px; padding: 25px; margin: 20px 0; box-shadow: 0 2px 10px rgba(0,0,0,0.06);"
|-
| style="vertical-align: top;" |

<div style="font-size: 1.1em; font-weight: 600; color: #1e293b; margin-bottom: 15px;">Support resources</div>

* '''Email''' — [mailto:support@voip.ms support@voip.ms]

'''When reporting an AI Agent issue, include:'''
* The name of the agent and the DID it is assigned to
* The date and time of the call, including the UniqueID found in the CDR
* A description of the behaviour observed vs. what was expected

|}

[[Category:Guides]]

AI agents

2026-06-09T15:00:48Z

Johann Jimenez:

{| cellspacing="0" style="width: 100%; background: linear-gradient(135deg, #f8fafc 0%, #f1f5f9 100%); border: 1px solid #e2e8f0; border-radius: 8px; padding: 35px; margin-bottom: 25px; box-shadow: 0 1px 3px rgba(0,0,0,0.05);"
|-
| style="text-align: center;" |

<div style="font-size: 2.8em; font-weight: 200; color: #1e293b; margin-bottom: 15px; letter-spacing: -2px;">AI Agents (Beta)</div>

<div style="font-size: 1rem; color: #64748b; margin-bottom: 15px;">
Configure a Voice Agent to better handle your inbound calls.
</div>

<div style="font-size: 0.9rem; color: #94a3b8;">
'''[https://wiki.voip.ms/ 🇨🇦 Français (Bientôt disponible)]'''  •  '''[https://wiki.voip.ms/ 🇲🇽 Español (Próximamente)]'''
</div>

|}

This guide explains how to configure VoIP.ms AI Voice Agent to handle inbound calls within your existing telephony setup.

The AI Voice Agent acts as a virtual first point of contact, capable of answering calls, understanding caller intent, and responding based on the behavior you define during configuration. Proper setup is critical, as the agent's performance is directly influenced by how clearly its instructions, call flows, and routing logic are defined.

'''Important:''' The AI agent does not "learn" your business automatically. It operates based on the rules, prompts, and context you provide — making configuration a key factor in achieving accurate and reliable interactions.

{| cellspacing="0" style="width: 100%; background: linear-gradient(135deg, #fef2f2 0%, #fee2e2 100%); border: 1px solid #fca5a5; border-radius: 8px; padding: 25px; margin: 25px 0; box-shadow: 0 2px 10px rgba(248, 113, 113, 0.1);"
|-
| style="text-align: left;" |
<div style="font-size: 1.1em; font-weight: 500; color: #b91c1c; margin-bottom: 15px;">'''Pricing'''</div>

During the Beta Period, the pricing is '''$10 per agent per month'''. Afterwards, the standard price will be $25 per agent per month. Furthermore, '''per-minute pricing is $0.25/min'''. This includes STT, TTD, and LLM capabilities, so you get full functionality with no hidden costs.

|}

__TOC__

= Getting Started =

{| cellspacing="0" style="width: 100%; background: white; border: 1px solid #e2e8f0; border-radius: 12px; padding: 25px; margin: 20px 0; box-shadow: 0 2px 10px rgba(0,0,0,0.06);"
|-
| style="vertical-align: top;" |

To access the AI Agents feature, navigate to the [https://voip.ms VoIP.ms Customer Portal]and click on '''AI Agents (BETA)''' in the navigation bar.

[[File:AI_Agent_-_Dashboard.png|thumb|none|600px]]

|}

= Creating an Agent =

{| cellspacing="0" style="width: 100%; background: white; border: 1px solid #e2e8f0; border-radius: 12px; padding: 25px; margin: 20px 0; box-shadow: 0 2px 10px rgba(0,0,0,0.06);"
|-
| style="vertical-align: top;" |

Click on '''Create New AI Agent'''.

[[File:IA agents 2.png|thumb|none|600px]]

You will see two options:
* '''Simple Voice Agent''' — A guided, step-by-step setup ideal for most use cases. Covers the essentials: voice, personality, purpose, call routing, and a knowledge base.
* '''Advanced Voice Agent''' — Provides full control over the LLM model, TTS model, MCP servers, webhook tools, and custom parameters for complex integrations.

[[File:IA agents 3.png|thumb|none|600px]]

Choose the option that best fits your needs. The sections below cover both paths in detail.

|}

== Simple Voice Agent ==

The '''Simple Voice Agent''' walks you through setup in a series of focused steps. Complete each step and click '''Next''' to advance.

{| cellspacing="0" style="width: 100%; background: white; border: 1px solid #e2e8f0; border-radius: 12px; padding: 25px; margin: 20px 0; box-shadow: 0 2px 10px rgba(0,0,0,0.06);"
|-
| style="vertical-align: top;" |

=== Step 1: Basic Configuration ===

In this section, you will define the foundational details of your agent:

* '''Agent Name''' — Assign a name to easily identify the agent
* '''Description''' — Provide a brief explanation of the agent's purpose (eg. Support Agent Level 1)
* '''Voice Selection''' — Choose from an extensive list of available voices

[[File:AI_Agent_-_Basic_Configuration.png|thumb|none|600px]]

{| cellspacing="0" style="width: 100%; background: linear-gradient(135deg, #fef2f2 0%, #fee2e2 100%); border: 1px solid #fca5a5; border-radius: 8px; padding: 25px; margin: 25px 0; box-shadow: 0 2px 10px rgba(248, 113, 113, 0.1);"
|-
| style="text-align: left;" |
<div style="font-size: 1.1em; font-weight: 500; color: #b91c1c; margin-bottom: 15px;">'''Note'''</div>

Not all voices currently have preview functionality. This will be expanded in future updates.

|}

Once completed, click '''Next''' to proceed.

|}

{| cellspacing="0" style="width: 100%; background: white; border: 1px solid #e2e8f0; border-radius: 12px; padding: 25px; margin: 20px 0; box-shadow: 0 2px 10px rgba(0,0,0,0.06);"
|-
| style="vertical-align: top;" |

=== Step 2: Personality and Tone ===

This section defines how your agent communicates. Based on your answers, VoIP.ms starts to build a prompt on your behalf in the back-end.

* '''Language''' — Select the primary language for the agent (English, Spanish or French)
* '''Tone and Interaction Style''' — Select how the agent should interact with callers. By default, simply go for Short and Concise.
* '''Agent Personality''' — Use this field to provide additional instructions and context, such as: agent name, company name, behavioral guidelines, or communication style preferences. This input directly influences how the AI behaves during calls.

[[File:AI_Agent_-_Personality_and_Tone.png|thumb|none|600px]]

|}

{| cellspacing="0" style="width: 100%; background: white; border: 1px solid #e2e8f0; border-radius: 12px; padding: 25px; margin: 20px 0; box-shadow: 0 2px 10px rgba(0,0,0,0.06);"
|-
| style="vertical-align: top;" |

=== Step 3: Purpose & Communication ===

Here you need to define what the agent is designed to do and how it interacts at the start of a call:

* '''Purpose of the Agent''' — Select the purpose of the agent anywhere from Troubleshooting Common Issues (Default), to Collect Basic Information.
* '''Greeting Message''' — Define the initial message the agent will deliver when answering a call. This text will be spoken exactly as written, so ensure clarity and professionalism. For instance: Hi, this is Violet with Company X Support. I can help for most issues or connect you with a live engineer. What seems to be happening today?

[[File:AI_Agent_-_Purpose_and_Communication.png|thumb|none|600px]] >>> '''To be changed.'''

|}

{| cellspacing="0" style="width: 100%; background: white; border: 1px solid #e2e8f0; border-radius: 12px; padding: 25px; margin: 20px 0; box-shadow: 0 2px 10px rgba(0,0,0,0.06);"
|-
| style="vertical-align: top;" |

=== Step 4: Call Routing & Transfer Options ===

This section allows you to configure whether the AI agent can transfer calls. If you do not want call transfers, simply click '''Next'''. Otherwise, to '''enable transfers''', click the '''Allow AI agent to transfer calls to specific destinations''' checkbox, then add a '''label''' to describe your transfer scenario(s) (e.g., "Sales Team", "Support Line") or the name of the given person (e.g. "John Doe").

Then, add as many destinations as you wish from:
* [[Sub_Accounts|Internal Extensions]]
* DID Phone numbers
* [[Phone_book|Phonebook speed dial entries]]

[[File:IA agents 11.png|thumb|none|600px]]

|}

{| cellspacing="0" style="width: 100%; background: white; border: 1px solid #e2e8f0; border-radius: 12px; padding: 25px; margin: 20px 0; box-shadow: 0 2px 10px rgba(0,0,0,0.06);"
|-
| style="vertical-align: top;" |

=== Step 5: Knowledgebase ===

In this section, you define the information sources the agent will use to respond to callers. You can add links such as your website, a knowledge base, a FAQ page, or even a Wiki. '''Ensure all links are publicly accessible and readable.'''

'''Optional:''' Enable '''Allow web search for additional information when appropriate''' to supplement responses with live web results.

Once all sections are completed, click '''Create Agent''' to finalize the setup of your Simple Voice Agent.

[[File:IA agents 12.png|thumb|none|600px]]

|}

== Advanced Voice Agent ==

The '''Advanced Voice Agent''' provides full control over your agent's underlying models, integrations ('''coming soon!'''), and behavior. Use this option when you need to select a specific LLM or TTS model, connect external tools via MCP servers or webhooks, or define custom parameters for complex use cases.

{| cellspacing="0" style="width: 100%; background: white; border: 1px solid #e2e8f0; border-radius: 12px; padding: 25px; margin: 20px 0; box-shadow: 0 2px 10px rgba(0,0,0,0.06);"
|-
| style="vertical-align: top;" |

=== General Settings ===

In this section, you define the core configuration of your advanced agent:

* '''Agent Name''' — Assign a name to identify the agent
* '''TTS Model''' — Select the text-to-speech model for voice generation
* '''Voice''' — Choose the voice used during calls. Please note that some voices currently do not have preview functionality. This will be expanded in future updates.
* '''LLM Model''' — Select the language model that powers the agent's reasoning and responses
* '''Background Audio''' — Optionally add background sound during calls
* '''Language''' — Define the primary language of the agent (English, Spanish or French)
* '''Description''' — Provide a brief summary of the agent's purpose

[[File:IA advanced 1.png|thumb|none|600px]]

|}

{| cellspacing="0" style="width: 100%; background: white; border: 1px solid #e2e8f0; border-radius: 12px; padding: 25px; margin: 20px 0; box-shadow: 0 2px 10px rgba(0,0,0,0.06);"
|-
| style="vertical-align: top;" |

=== Call Routing and Transfer ===

This section allows you to configure whether the AI agent can transfer calls. To '''enable transfers''', click the '''Allow AI agent to transfer calls to specific destinations''' checkbox, then add a '''label''' to describe your transfer scenario(s) (e.g., "Sales Team", "Support Line") or the name of the given person (e.g. "John Doe").

Then, add as many destinations as you wish from:
* [[Sub_Accounts|Internal Extensions]]
* Phone numbers (DID)
* [[Phone_book|Phonebook speed dial entries]]

[[File:IA advanced 2.png|thumb|none|600px]]

|}

{| cellspacing="0" style="width: 100%; background: white; border: 1px solid #e2e8f0; border-radius: 12px; padding: 25px; margin: 20px 0; box-shadow: 0 2px 10px rgba(0,0,0,0.06);"
|-
| style="vertical-align: top;" |

=== Knowledge Base ===

In this section, you define the information sources the agent will use to respond to callers. You can add links such as your website, a knowledge base, a FAQ page, or even a Wiki. '''Ensure all links are publicly accessible and readable.'''

'''Optional:''' Enable '''Allow web search for additional information when appropriate''' to supplement responses with live web results.

[[File:AI_Agent_-_Advanced_-_Knowledge_Base.png|thumb|none|600px]]

|}

{| cellspacing="0" style="width: 100%; background: white; border: 1px solid #e2e8f0; border-radius: 12px; padding: 25px; margin: 20px 0; box-shadow: 0 2px 10px rgba(0,0,0,0.06);"
|-
| style="vertical-align: top;" |

== Advanced Tools and Integrations ==

Extensions allow AI Agents to connect with external systems such as CRMs, helpdesks, databases, and internal business applications.

These integrations enable your AI agents to send information, retrieve data, and perform actions outside of Telzino, helping automate workflows and provide more personalized customer interactions.

Extensions are configured from the '''Extensions''' section within the AI Agent configuration page.

There are two types of integrations available:

* Webhooks
* MCP Servers

Each serves a different purpose and can be used independently or together depending on your workflow requirements.

=== Webhooks ===

Webhooks allow your AI Agent to send information to an external system when a specific event occurs during the call lifecycle.

In simple terms:

''"When something happens, send this information to another system."''

Webhooks are commonly used to:

* Create support tickets
* Log call information
* Send call summaries
* Update CRM records
* Trigger internal workflows
* Notify external applications

=== Webhook Configuration ===

The following fields are available when creating or editing a webhook.

{| class="wikitable"
! Field
! Description
! Purpose
|-
| Name
| Internal identifier
| Unique system identifier used by the AI Agent to reference the webhook.
|-
| Friendly Name
| Display name
| Human-readable name displayed within the Portal.
|-
| Description
| Usage description
| Explains the purpose of the webhook and when it should be used. The AI Agent may use this information when determining whether to execute the webhook.
|-
| Trigger Condition
| Execution timing
| Defines when the webhook is triggered.
|-
| HTTP Method
| Request method
| Defines how data is sent to the destination system. Common methods include POST, GET, PUT, PATCH, and DELETE.
|-
| URL
| Destination endpoint
| Web address that receives the webhook request.
|-
| Parameters
| Data fields
| Information sent to the external system.
|}

=== Parameters ===

Parameters define the information that will be sent to the destination system.

For each parameter, you can specify:

* A dynamic value generated by the AI Agent
* A fixed value that is always sent
* A default value used when information is unavailable

=== Dynamic Values ===

If the Value field is left empty, the AI Agent will attempt to populate it using information collected during the conversation.

Examples include:

* Customer name
* Email address
* Phone number
* Call reason
* Issue description

=== Fixed Values ===

A fixed value will always be sent with the request.

Example:

* priority = normal

=== Default Values ===

A default value will only be used if the AI Agent is unable to determine the information from the conversation.

== Example Parameter Configuration ==

{| class="wikitable"
! Parameter
! Value
! Result
|-
| subject
|
| AI generates a subject based on the conversation.
|-
| description
|
| AI generates a call summary.
|-
| customer_email
|
| AI attempts to capture the caller's email address.
|-
| priority
| normal
| Always sends "normal" as the priority value.
|}

[[File:Webhooks.png|thumb|none|600px]]

= MCP Servers =

MCP (Model Context Protocol) Servers allow AI Agents to interact with external systems in real time during a conversation.

Unlike webhooks, which send information in a single direction, MCP Servers establish a live connection that enables the AI Agent to query external tools and retrieve information while speaking with the caller.

In simple terms:

''"Connect the AI Agent to an external system so it can retrieve information and perform actions during the call."''

== Common MCP Use Cases ==

MCP Servers can be used to:

* Retrieve customer information from a CRM
* Check order status
* Verify product availability
* Access account information
* Search internal databases
* Execute business-specific workflows

Because these actions occur during the conversation, the caller can receive immediate responses without requiring manual intervention.

== MCP Server Configuration ==

The following fields are available when configuring an MCP Server.

{| class="wikitable"
! Field
! Description
! Purpose
|-
| Name
| Connection name
| Friendly name used to identify the server connection within the Portal.
|-
| Transport Type
| Connection method
| Defines how the AI Agent communicates with the MCP Server. Supported options include SSE and HTTP.
|-
| URL
| Server endpoint
| Address of the MCP Server provided by the connected platform.
|-
| Auth Headers
| Authentication credentials
| Security information required to access the external system.
|}

== Authentication Headers ==

Authentication Headers are commonly used to grant access to external systems.

Examples include:

{| class="wikitable"
! Header
! Example Value
|-
| Authorization
| Bearer abc123...
|-
| X-API-Key
| your-api-key
|}

These values are typically provided by the technical team responsible for the connected application.

== Additional Notes ==

Some MCP implementations support advanced initialization options that may be configured through the API.

These settings are typically used for custom integrations and advanced deployment scenarios.

[[File:MCPs.png|thumb|none|600px]]

|}

{| cellspacing="0" style="width: 100%; background: white; border: 1px solid #e2e8f0; border-radius: 12px; padding: 25px; margin: 20px 0; box-shadow: 0 2px 10px rgba(0,0,0,0.06);"
|-
| style="vertical-align: top;" |

=== Communication Settings ===

In this final section, you can define how the agent interacts at the start of a call and can also build the entire prompt :

* '''Greeting Message''' — Set the initial message delivered when answering a call
* '''System Prompt''' — Define the core instructions that guide the agent's behavior and responses ([[AI_Prompts|see AI Prompts examples here]])

[[File:IA advanced 5.1.png|thumb|none|600px]]

|}

= Linking Your Agent to a DID =

{| cellspacing="0" style="width: 100%; background: white; border: 1px solid #e2e8f0; border-radius: 12px; padding: 25px; margin: 20px 0; box-shadow: 0 2px 10px rgba(0,0,0,0.06);"
|-
| style="vertical-align: top;" |

Once your agent is created, you need to [[Manage_DID#Edit_a_single_DID_number|assign it]] to a phone number (DID) so it can start answering inbound calls.

# Go to '''DID Numbers''' → '''Manage DIDs''' in the customer portal
# Click '''Edit''' on the DID you want to route to the agent
# In the routing destination section, select '''AI Voice Agent''' from the dropdown
# Choose the specific agent you created from the list
# Click '''Apply'''

Your AI Agent will now answer all inbound calls to that DID!

[[File:AI_Agent_-_Manage_DIDs.png|thumb|none|600px]]

|}

= Frequently Asked Questions =

{| cellspacing="0" style="width: 100%; background: white; border: 1px solid #e2e8f0; border-radius: 12px; padding: 25px; margin: 20px 0; box-shadow: 0 2px 10px rgba(0,0,0,0.06);"
|-
| style="vertical-align: top;" |

'''Q: Can the AI agent handle outbound calls?'''

A: No — AI Agents are designed for inbound calls only. They answer calls made to your DID; they cannot initiate outbound calls.

'''Q: What languages does the agent support?'''

A: English, Spanish, and French.

'''Q: What is the difference between Simple and Advanced?'''

A: The Simple Voice Agent guides you through a fixed set of steps and covers everything most users need: voice, personality, purpose, call routing, and a knowledge base. The Advanced Voice Agent exposes the underlying LLM and TTS model selection, background audio, and (coming soon) MCP servers and webhook tool integrations for more complex use cases.

'''Q: Can I have multiple agents?'''

A: Yes — you can create as many agents as needed and assign each one to a different DID.

'''Q: Can I edit my agent after creating it?'''

A: Yes — from the AI Agents dashboard you can edit, duplicate, or delete any agent at any time.

'''Q: What happens if the agent cannot answer a question?'''

A: The agent will let the caller know it does not have that information. If call transfers are configured, it can route the caller to a human agent instead.

'''Q: Does the agent answer calls 24/7?'''

A: Yes — once assigned to a DID, the agent answers all inbound calls at any hour.

'''Q: Does the AI agent work with my existing DID?'''

A: Yes — any eligible DID can be routed to an AI Agent from '''DID Numbers → Manage DIDs'''.

'''Q: What does "(Beta)" mean?'''

A: The feature is in active development. Some capabilities — such as Advanced Tools and Integrations — are not yet available, and behaviour may change before the general release.

{| cellspacing="0" style="width: 100%; background: linear-gradient(135deg, #fef2f2 0%, #fee2e2 100%); border: 1px solid #fca5a5; border-radius: 8px; padding: 25px; margin: 25px 0; box-shadow: 0 2px 10px rgba(248, 113, 113, 0.1);"
|-
| style="text-align: left;" |

We will keep populating this FAQ as questions come along. '''Thanks in advance for your feedback, support and questions!'''

|}

|}

= Need Help or Got Feedback? =

{| cellspacing="0" style="width: 100%; background: white; border: 1px solid #e2e8f0; border-radius: 12px; padding: 25px; margin: 20px 0; box-shadow: 0 2px 10px rgba(0,0,0,0.06);"
|-
| style="vertical-align: top;" |

<div style="font-size: 1.1em; font-weight: 600; color: #1e293b; margin-bottom: 15px;">Support resources</div>

* '''Email''' — [mailto:support@voip.ms support@voip.ms]

'''When reporting an AI Agent issue, include:'''
* The name of the agent and the DID it is assigned to
* The date and time of the call, including the UniqueID found in the CDR
* A description of the behaviour observed vs. what was expected

|}

[[Category:Guides]]

File:MCPs.png

2026-06-09T15:00:31Z

Johann Jimenez:

File:Webhooks.png

2026-06-09T14:59:30Z

Johann Jimenez:

AI Agent Report

2026-05-20T19:55:34Z

Johann Jimenez:

Reporte de Agentes de IA

2026-05-20T19:55:16Z

Johann Jimenez: Created page with "{| cellspacing="0" style="width: 100%; background: linear-gradient(135deg, #f8fafc 0%, #f1f5f9 100%); border: 1px solid #e2e8f0; border-radius: 8px; padding: 35px; margin-bottom:..."

AI Agent Report

2026-05-15T22:26:55Z

Johann Jimenez:

File:Agentsreports5.png

2026-05-15T22:25:48Z

Johann Jimenez:

File:Agentsreports4.png

2026-05-15T22:23:57Z

Johann Jimenez:

File:Agentsreports3.png

2026-05-15T22:23:45Z

Johann Jimenez:

File:Agentsreports2.png

2026-05-15T22:23:33Z

Johann Jimenez:

File:Agentsreports1.png

2026-05-15T22:18:35Z

Johann Jimenez:

AI Agent Report

2026-05-15T21:58:21Z

Agentes de IA

2026-04-24T16:45:10Z

Johann Jimenez:

{| class="wikitable"
|+
|-
! Article en Français !! Article on English
|-
| [https://wiki.voip.ms/article/Identification_de_l%27appelant Français] ||
[https://wiki.voip.ms/article/AI_agents English]
|}

Esta guía explica cómo configurar su Agente de Voz con IA para gestionar llamadas entrantes dentro de su configuración de telefonía existente.
El Agente de Voz con IA actúa como un primer punto de contacto virtual, capaz de contestar llamadas, comprender la intención del usuario y responder en función del comportamiento que usted defina durante la configuración. Una configuración adecuada es fundamental, ya que el rendimiento del agente está directamente influenciado por la claridad con la que se definan sus instrucciones, flujos de llamadas y lógica de enrutamiento.
Es importante tener en cuenta que el agente de IA no “aprende” su negocio automáticamente. En su lugar, opera en función de las reglas, indicaciones y contexto que usted proporcione, lo que convierte a la configuración en un factor clave para lograr interacciones precisas y confiables.

__TOC__

= Configuración Inicial =

Para comenzar a configurar su Agente de Voz con IA, diríjase al portal del cliente.

Vaya a la barra de navegación y haga clic en '''AI Agents (BETA)'''

[[File:IA agents 1.png|thumb|none|600px]]

Haga clic en '''Create New AI Agent'''

[[File:IA agents 2.png|thumb|none|600px]]

Verá dos opciones:
* Agente de Voz Simple
* Agente de Voz Avanzado

[[File:IA agents 3.png|thumb|none|600px]]

Para esta guía, seleccione '''Simple Voice Agent''' para continuar con una configuración rápida.

= Configuración Básica =

En esta sección, definirá los detalles fundamentales de su agente:

* 1 Nombre del Agente: Asigne un nombre para identificar fácilmente al agente
* 2 Descripción: Proporcione una breve explicación del propósito del agente
* 3 Selección de Voz: Elija entre una amplia lista de voces disponibles

[[File:IA agents 4.png|thumb|none|600px]]

Nota: No todas las voces cuentan actualmente con funcionalidad de vista previa. Esto se ampliará en futuras actualizaciones.

Una vez completado, haga clic en Next para continuar.

= Personalidad y Tono =

Esta sección define cómo se comunica su agente.

Idioma: Seleccione el idioma del agente
Opciones disponibles: Español, Inglés, Francés

[[File:IA agents 5.png|thumb|none|600px]]

Tono y Estilo de Interacción:
Predeterminado: Corto y conciso
Alternativas: Conversacional, Eficiente, Servicial

[[File:IA agents 6.png|thumb|none|600px]]

Personalidad del Agente (Campo de Prompt):
Utilice este campo para proporcionar instrucciones y contexto adicional, como:
* Nombre del agente
* Nombre de la empresa
* Lineamientos de comportamiento
* Preferencias de estilo de comunicación

Esta información influye directamente en cómo la IA se comporta durante las llamadas.

[[File:IA agents 7.png|thumb|none|600px]]

= Propósito y Comunicación =

Aquí define qué está diseñado para hacer el agente y cómo interactúa al inicio de una llamada.

Propósito del Agente:
* Soporte
* Ventas
* Enrutamiento de llamadas
* Otros casos de uso

[[File:IA agents 8.png|thumb|none|600px]]

Capacidades:
* Actuar como recepcionista
* Recopilar información básica del llamante
* Responder preguntas frecuentes

[[File:IA agents 9.png|thumb|none|600px]]

Mensaje de Bienvenida:
Defina el mensaje inicial que el agente reproducirá al contestar una llamada.
Este texto se reproducirá exactamente como está escrito, por lo que debe asegurar claridad y profesionalismo.

= Opciones de Enrutamiento y Transferencia de Llamadas =

Esta sección le permite configurar si el agente de IA puede transferir llamadas.

[[File:IA agents 10.png|thumb|none|600px]]

Si no desea transferencias de llamadas, simplemente haga clic en Next.

'''Para habilitar transferencias:'''
Active Permitir que el agente de IA transfiera llamadas a destinos específicos

[[File:IA agents 11.png|thumb|none|600px]]

Defina los destinos de transferencia:
* Extensiones
* Números telefónicos
* Entradas de marcación rápida del directorio (si están disponibles)

'''Etiquetado:'''
Agregue una etiqueta para describir el escenario de transferencia (por ejemplo, “Equipo de Ventas”, “Línea de Soporte”).

'''Números Telefónicos Personalizados:'''
Ingrese el número completo incluyendo el código de país y de área
Haga clic en + Add para incluir múltiples destinos de transferencia según sea necesario

= Base de Conocimiento =

En esta sección, define las fuentes de información que el agente utilizará para responder a los llamantes.

Agregue enlaces a:

* Sitios web
* Bases de conocimiento
* Páginas de preguntas frecuentes (FAQ)
* Wikis

'''Asegúrese de que todos los enlaces sean accesibles públicamente y se puedan leer.'''

Puede agregar múltiples enlaces para ampliar la cobertura de conocimiento del agente.

'''Opcional:'''
Habilite Allow web search for additional information when appropriate para complementar las respuestas con información adicional cuando sea necesario

Una vez que todas las secciones estén completadas, haga clic en Create Agent para finalizar la configuración de su Agente de Voz Simple.

[[File:IA agents 12.png|thumb|none|600px]]

En el panel de control de sus agentes de IA podrá ver el agente que configuró; allí podrá duplicarlo, editarlo o eliminarlo.

[[File:IA agents 13.png|thumb|none|600px]]

File:IA Advanced 4.png

2026-04-23T22:24:49Z

Johann Jimenez: uploaded a new version of "File:IA Advanced 4.png"

File:IA Advanced 3.png

2026-04-23T22:24:39Z

Johann Jimenez: uploaded a new version of "File:IA Advanced 3.png"

File:IA advanced 5.1.png

2026-04-23T22:24:10Z

Johann Jimenez:

File:IA advanced 5.png

2026-04-23T22:21:20Z

Johann Jimenez:

File:IA Advanced 4.png

2026-04-23T22:21:11Z

Johann Jimenez:

File:IA Advanced 3.png

2026-04-23T22:21:01Z

Johann Jimenez:

File:IA advanced 2.png

2026-04-23T22:20:53Z

Johann Jimenez:

File:IA advanced 1.png

2026-04-23T22:19:11Z

Johann Jimenez:

File:IA agents 13.png

2026-04-23T17:02:36Z

Johann Jimenez:

File:IA agents 12.png

2026-04-23T17:00:31Z

Johann Jimenez:

File:IA agents 11.png

2026-04-23T16:57:03Z

Johann Jimenez:

File:IA agents 10.png

2026-04-23T16:56:48Z

Johann Jimenez:

File:IA agents 9.png

2026-04-23T16:52:58Z

Johann Jimenez:

File:IA agents 8.png

2026-04-23T16:52:45Z

Johann Jimenez:

File:IA agents 7.png

2026-04-23T16:50:45Z

Johann Jimenez:

File:IA agents 6.png

2026-04-23T16:50:30Z

Johann Jimenez:

File:IA agents 5.png

2026-04-23T16:50:20Z

Johann Jimenez:

File:IA agents 4.png

2026-04-23T16:48:15Z

Johann Jimenez:

File:IA agents 3.png

2026-04-23T16:42:03Z

Johann Jimenez:

File:IA agents 2.png

2026-04-23T16:40:52Z

Johann Jimenez:

File:IA agents 1.png

2026-04-23T16:30:47Z

Johann Jimenez: