The AI Agent Responses section allows you to tailor your Freddy AI Agent's communication style by customizing various responses and managing supported languages. This helps ensure the AI Agent aligns with your brand's voice while enhancing customer engagement. 

You can configure how AI Agents interact with customers by customising various AI Agent responses and supported languages, based on the following scenarios:

1. To send an introductory greeting
2. To collect customer feedback
3. To transfer conversation to agent
4. To send a failure message

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

1. To send an introductory greeting - The Introductory greeting is the customer's first interaction with your AI Agent. Personalizing this message can set the right tone and increase engagement. You can use rich text formatting, links, and emojis to make the greeting more inviting. Placeholders can also personalize the message by automatically pulling fields like 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?"

Once you've crafted your greeting, click Save to apply it.

2. To collect customer feedback- Gathering feedback from customers is essential to improving the AI Agent’s performance. You can customize the feedback prompt using rich text, links, and emojis.
   To configure feedback message:
   1. Set the feedback message (e.g.: Was this helpful?)
   2. Select the AI agent's action: resolve or do nothing, based on the response.
   3. Add the positive (Yes) and negative (No) text messages for the customer to choose from.
   4. Click Save.
      
3. To transfer conversation to agent - In situations where users request to speak with an agent, either without a prior conversation or during an ongoing discussion, this functionality enables the AI Agent to transfer the interaction to a human agent smoothly.
   Enable this feature, set the message for the customer when transferring the conversation to an Agent, and click Save.

4. To send a failure Message - In cases where the AI Agent cannot respond to a user’s query, a failure message is triggered. This failure/fallback message helps manage customer expectations and maintains engagement even when the AI Agent doesn’t have an answer.
   Customize this message to be clear and supportive. Select the checkbox Transfer conversation to agent to hand off the discussion to a support representative for further assistance, and click Save.
   Example: "Sorry, I couldn’t find an answer to that. Let me connect you to someone who can help!"
   
   

Supported languages

You can configure the AI Agent to respond in multiple languages by adding the language in the Supported languages section. 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 -