TABLE OF CONTENTS

The AI Agent Responses section lets you customize your AI Agent’s tone, messaging, and supported languages to reflect your brand voice and create more engaging customer interactions. For details on the complete AI Agent setup, see Create an AI Agent using the AI Agent Studio.


Set up conversation behaviour

To configure AI Agent behaviour:

  1. Log in to your account.
  2. From the left navigation pane, click AI Agent Studio.
  3. Select your AI Agent > Build >Configurations > Conversation behaviour.
  4. You can configure the following:
    • Send introductory message
    • Send fallback message
    • Collect feedback
    • Collect details

You can use the default pre-configured messages or customize them to ensure they align with your brand voice and enhance customer engagement.


Send an introductory message 

The Introductory message is the customer's first interaction with your AI Agent. Personalizing this message can set the right tone and increase engagement.

  1. On the AI Agent's Configurations section > Conversation behaviour tab, click Send introductory message.
  2. Use rich text formatting, links, and emojis to make the greeting more inviting. Placeholders can also personalize the message by automatically pulling fields, such as the customer’s name, email, or phone number.
    Example:
    • Basic greeting: "Hi there! How can I help you?"
    • Personalized greeting: "Hello [Customer Name]! How can I assist you today?"
  3. Click Review translations to verify and edit the auto-translated message, used across all supported languages to ensure the correct tone, accuracy, and clarity. Click Manage languages link to add or remove supported languages.
  4.  You can also choose to collect user details such as name, email address etc.
  5. Once done, click Save.

Send fallback message

When the AI Agent cannot respond to a customer’s query, a fallback message is displayed. This message helps manage customer expectations and keeps the conversation ongoing, even when the AI Agent doesn’t have an answer.

You can customize this message to be clear and supportive.

  1. On the AI Agent's Configurations section > Conversation behaviour tab, click Send fallback message.
  2. Enter the message.

    Example: "Sorry, I couldn’t find an answer to that. Let me connect you to someone who can help!"

    You can also select Transfer conversation to agent to automatically hand over the chat to agents.

  3. Click Review translations to verify and edit the auto-translated message, used across all supported languages to ensure the correct tone, accuracy, and clarity.

  4. Click Save.


Collect feedback

Collecting feedback from your customers helps you continuously improve the accuracy and overall experience of your AI Agent. You can customize the feedback prompt using rich text, links, and emojis to make it more engaging and consistent with your brand voice.

How is feedback collected?

If feedback collection is enabled:

  • It is triggered when responses are provided through Knowledge Sources or Workflows.
  • For Workflows, feedback is collected after the entire Workflow is completed. However, if the final block in the Workflow transfers the conversation to an agent, feedback will not be sent.

To configure the feedback message:

  1. On the AI Agent's Configurations section > Conversation behaviour tab > Collect feedback > toggle on Always ask for feedback.
  2. Set the feedback message (e.g.: Was this helpful?)
  3. Select the AI agent's response: resolve, transfer to a human agent, or do nothing, based on the feedback.
  4. Add the positive (Yes) and negative (No) text messages for the customer to choose from.
  5. Click Save.
Note: For Workflows, feedback is collected after the entire Workflow is completed.

Collect user details

Collect essential customer information, such as name, email, or location, to personalize conversations and make agent handoffs smoother. You can collect up to five custom properties.

User details are collected as part of the AI Agent’s introductory greeting, and before transferring to a human agent. This will be triggered in the following scenarios:

  • When queries are unanswered
  • When the user explicitly requests an agent
  • When negative feedback is received
  • When a user’s query falls under sensitive topics
Notes: 
1. Collecting unique properties like Email and Phone number from visitors might have a security impact.
2. When workflows retrieve sensitive data (orders, refunds, account info):
    1. If user properties are pre-filled through the widget script, the AI Agent         automatically uses them and skips additional prompts.
    2. If not, the admin must ensure the workflow explicitly collects:
            Order ID
            Email or another unique identifier
            Validate both before responding
For best results, configure the widget to pass verified user properties.


To collect user details:

  1. On the AI Agents Configurations section > Conversation behaviour tab > select Collect user details.
  2. On the Collect user details pane, specify the following:
    1. Collect the user details during the Introduction as part of the AI Agent’s initial greeting (this is auto-filled).
    2. Add Propertiesthat the AI Agent should collect:
      1. Choose from available text, paragraph, or number fields.
      2. Add description to provide additional context, if needed.
      3. You can mark the fields as Required. Properties that are not marked as Required can be skipped if the customer denies them or requests other information.
  3. Click Save. A toggle will appear next to Collect user details to indicate the feature is active.
  4. Click Sync fields to automatically refresh contact fields when properties are added or removed.

Manage and remove fields

  1. To stop collecting user details, turn off the Collect user details toggle. 
  2. To remove any property, click on the minus icon and click Save


Note: If a selected property is deleted from your contact fields, you will see the following error next to that field:

“This property was removed from contact fields or ticket properties. Select a different property or remove it to proceed.”

To resolve this, either choose a new property or delete the invalid one from your configuration.

Supported languages

By default, the AI Agent understands queries in all languages and responds in the following manner:

  1. If the user's query is in one of the added languages in the supported languages section: The AI Agent will reply in the language of the query.
  2. If the user query is outside the added languages in the supported languages section: The AI Agent will respond in the primary language with a language disclaimer: “Apologies! I am trained to answer in <added languages>”


The supported languages include the following -

AmharicAssameseBengaliBosnianBulgarian
CatalanChineseChinese (Traditional)CroatianCzech
DanishDutchEnglishEstonianFilipino
FinnishFrenchGermanGreekGujarati
HebrewHindiHungarianIcelandicIndonesian
ItalianJapaneseKannadaKazakhKhmer
KoreanKurdishLatvianLithuanianMalay
MalayalamMarathiNepaliNorwegianOdia
PolishPortuguese (BR)Portuguese (Portugal)PunjabiRomanian
RussianSerbianSinhaleseSlovakSlovenian
SomaliSpanishSpanish (Latin America)SwahiliSwedish
TamilTeluguThaiTurkishUkrainian
UrduVietnameseWelsh