The Persona feature allows you to craft a clear and structured identity for your Freddy AI Agent. By providing detailed information about your business and customizing the AI’s tone and behavior, you help ensure the AI responds more accurately, efficiently, and in alignment with your brand.

Importance of Defining a Persona

A well-defined Persona enables your AI Agent to:

• Understand your business context and industry terminology

• Deliver accurate, relevant, and brand-aligned responses

• Reduce unnecessary fallbacks and avoidable agent handoffs

• Filter out spam or irrelevant customer queries

Without this configuration, your AI Agent may provide vague or off-topic answers or escalate queries it could otherwise resolve, leading to a poor customer experience and increased agent workload.

Configure Your AI Agent’s Persona

The Persona tab is a guided, multi-section interface that combines customization, business details, and response instructions. To access and set up the Persona tab:

1. As an Admin, navigate to Freddy AI Agent > Configure.
2. Click on the Persona tab after completing the setup of Knowledge Sources, API Actions, and AI Agent Responses.

Set the AI Agent Name

1. Enter a name for your AI Agent under the AI Agent Name field.
2. Choose a name that reflects your brand identity. This name will appear in conversations and be visible to end users.

Assign an Avatar

1. Choose from a library of avatars.
2. Or upload a custom image using the upload icon. The avatar is visible in chat interfaces and adds a personal touch to the AI.

Add Business Details

Under Provide the AI Agent with details about your business section, including:

• A short description of your company
• The industry you operate in
• The products or services you offer
• Any terminology or phrasing common in your domain

Use the Write with AI option to help draft or rephrase your input. You can also auto-generate this content from your existing Knowledge Sources to save time and maintain consistency.

Note: Use simple, jargon-free language so the AI understands your business better and provides more contextual answers.

Configure Instructions 

Instructions help create consistent and accurate responses, ensuring the Freddy AI Agent follows your business processes and communication guidelines.

In the Add Instructions section, describe how the AI Agent should behave and respond to customer queries. This includes:

• Tone of voice (e.g., friendly, professional, empathetic)
• Behavior (e.g., prioritize quick resolution, escalate billing issues)
• Response strategy (e.g., link to articles, avoid handoffs for out-of-scope questions)

With enhanced capabilities, the AI Agent can now recognize and filter semantically unclear or out-of-scope queries—such as irrelevant general knowledge questions (“Who is the President of India?”) or spam from social platforms—without defaulting to fallback or agent handoff. Instead, it will respond with an appropriate message indicating that the query is outside its scope, helping reduce noise in agent queues and prioritizing genuine customer inquiries.

Write Effective Instructions

To help you create clear and effective instructions for the bot, we provide a Writing Tips section. 

Examples of Good Instructions

Use the following examples as a reference to craft clear, brand-aligned, and compliant instructions for your Freddy AI Agent:

1. Style & Formatting Guidance
   These instructions help ensure consistency in tone and response length.
   • Keep responses concise and relevant, ideally under 300 words.
     Example: “Respond with short and direct answers; avoid unnecessary elaboration.”
   • Acknowledge customer concerns before presenting solutions.
     Example: “Start responses by acknowledging the customer’s issue in a polite and professional tone.”
   • Use a formal and respectful tone for all customer interactions.
     Example: “Maintain a professional tone across all responses; avoid slang or overly casual language.”
     
     
2. Terminology & Brand Language
   Define how business-specific terms or roles should be referenced.
   • Use internal terms familiar to your customers.
     Example: “Refer to delivery personnel as ‘Captains’ instead of ‘agents’ or ‘executives’.”
   • Treat synonymous terms interchangeably based on your business vocabulary.
     Example: “Use ‘recipient’ and ‘customer’ interchangeably—they both refer to the end user.”

What Not to Include in Instructions

1. Do not include complete responses
   Instructions should not contain actual reply content, links, or customer-facing actions.
   Avoid instructions like: “If a customer wants to cancel their account, share the cancellation form link: https://example.com/form”
   Such responses are considered critical and should be added in the QnA section, not in the Instructions. Including them here can overcomplicate your instructions and reduce the effectiveness of the AI agent.
   
   
2. Avoid using Instructions for Business Hours Handling
   Instead of including time-based instructions like: “Outside these hours, ask the customer to leave their email address.”
   Use the Business Hours feature to configure after-hours behavior.
   
   
3. Do not define Agent Handoff Behavior depending on user properties

   Instructions such as: “If the customer’s plan is not 'Premium', then don’t transfer chat to humans”.

   If you need customized agent handoff rules, please contact the Support Team to explore implementation options.
   
   

4. Do not define Agent Handoff Behavior on Negative feedback or Fallback

   Instructions for handling fallback or feedback are: “Before triggering agent handoff due to fallback, take confirmation from the user if they would like to speak with an Agent before transferring the chat.” These settings can be configured in Preset Messages.