Skip to main content
The Agent Tab controls your agent’s welcome message, prompts, and conversation behavior. Add multiple languages, set a primary, and write a dedicated prompt for each.
Agent Tab showing welcome message, language tabs with English as primary alongside Dutch and Hindi, prompt editor with token count, language switching instructions, advanced settings, and prompt variables for testing

Agent Tab with welcome message, multilingual prompt editor, language switching instructions, and hangup configuration

​
Agent Welcome Message

The first thing callers hear when they connect.
Agent Welcome Message input with sample greeting and hint showing variable_name syntax in curly braces

Welcome message field with variable syntax hint

Keep It Short

Brief greetings work best. Long announcements feel robotic.

Use Variables

Personalize with {variable_name}, e.g. {customer_name}.

​
Canvas

Each language gets its own prompt. Select a language tab and write the prompt for that language. The agent activates the matching prompt when speaking in that language during a call.
Canvas with English marked as Primary, Hindi and Dutch language tabs, prompt editor showing Personality and Identity sections, token counter at 14111, and hint text for variable and module syntax

Prompt editor with English as primary, Hindi and Dutch as secondary tabs, personality prompt for Vidya, token counter, and variable syntax hints

​
Managing Languages

Languages are synced between the Agent Tab and Audio Tab. Adding or removing a language in either tab updates both. Each language can also have its own STT and TTS providers configured in the Audio Tab.
1

Add a Language

Click + Add Language to create a new language tab.
2

Set the Primary

Click the crown icon next to any language to make it primary. The primary language is what the agent starts every conversation in, marked with (Primary) in the tab.
3

Write Per-Language Prompts

Select each language tab and write its prompt.
4

Remove a Language

Click the x on a tab to remove it from both tabs.
Tooltip showing Make Hindi primary when clicking the crown icon next to Hindi

Crown icon tooltip to set a language as primary

​
Prompt Structure

The editor shows a token count in the bottom-right to help you stay within LLM limits.

​
Variable Syntax

Variables with { }

Select existing variables or create new ones by typing a name. Values are passed via API or CSV at call time.

Modules and Functions with @

Select existing prompt modules, custom functions, or variables. Cannot create new items.

​
Browse Modules

Click the Browse Modules button in the top-right of the prompt section to open the full modules library. Browse by category (Collection, Optional, Flow, Sector, Universal), preview what each module does, and insert it directly into your prompt. See the Prompting Guide for the full list of available modules.

​
Language Switching Instructions

A single shared field that applies to all languages. Describes when the agent should switch languages mid-call.
Write these once. They apply across all languages automatically.

​
Per-Language Advanced Settings

Each language tab has its own expandable Advanced Settings section.
Language Switching Instructions field, Advanced Settings for English expanded with Agent Name placeholder AI Assistant and Handoff Message reading Let me connect you with agent_name who speaks language

Advanced Settings for English showing Agent Name, Handoff Message with variables, Language Switching Instructions, and prompt variable testing

​
Prompt Variables for Testing

When you use {variable_name} in your prompt, those variables automatically appear as input fields in the testing section. Fill in test values to preview how the prompt behaves before going live.
Prompt variables for testing section showing Asia Kolkata UTC plus 05 30 timezone selector and auto-detected variable fields for referrer_name, referee_name, city, and user_number

Prompt variables auto-detected from the prompt, shown as editable input fields alongside the timezone selector

The Timezone selector (e.g., Asia/Kolkata UTC+05:30) is a separate field that sets the timezone context for test calls.

Per-Language Scope

Settings are independent. Hindi’s Agent Name and Handoff Message do not affect English.

Natural Handoffs

Always set a Handoff Message per language. Without it, transitions feel abrupt.

​
Hangup Using Prompt

Let your agent decide when to end calls based on conversation context instead of silence detection or timeouts.
Hangup using a prompt toggle enabled with conversation completion conditions and closing lines in English and Hindi

Hangup toggle enabled with multilingual closing conditions in English and Hindi

1

Enable the Toggle

Turn on Hangup using a prompt.
2

Define Completion Conditions

Write conditions for when a conversation is complete. For multilingual agents, include closing lines in each language.
Without this, calls end only on silence detection or timeouts.

​
Next Steps

LLM Tab

Configure the language model and knowledge bases

Audio Tab

Set up voice, transcription, and languages

Prompting Guide

Best practices for writing prompts

Using Variables

Dynamic personalization with context