Receptionist

The Receptionist role is ideal for businesses looking to automate their inbound call handling, ensuring that customers receive immediate and around-the-clock responses and guidance. Roles set a framework for call interactions that the Inbound Agent can follow, and provide a variety of predefined input boxes for the user to configure, allowing the AI to be trained on specific company details and goals.

Details

A Receptionist Inbound Agent is capable of:

• Greeting callers professionally with a custom welcome message.
• Understanding inquiries and responding based on business-specific knowledge.
• Executing defined actions, such as call transfers, meeting bookings, or email notifications.
• Capturing caller details for future follow-up.

The goal of the Receptionist Inbound Agent is to act as an efficient, always-available first point of contact, improving customer experience and streamlining business operations.

Configuring the Receptionist Role

1. Selecting the Receptionist Role

• If it’s your very first time in AVA, you will be prompted to create an Outbound Project, or an Inbound Agent.

Otherwise, navigate to the Home screen in AVA.

• Click “Add New Agent” in the Active Agents section.
• Choose whether the agent should be:
  • Tied to a phone number
  • Deployed to the web
  • Both

Then, you will be able to configure the following:

• Agent Role - Select the character and function of the Agent (e.g. Receptionist).
• Agent Name - Enter a custom name for the Agent.
• Language & Ethnicity - Choose the language and voice characteristics (Agents will stick to the predefined language and will not switch languages during a conversation)
• Phone Number - Select an ****available phone number (Inbound Agents cannot share a phone number).
• Voice Selection - Preview and choose a voice.

2. Defining the Receptionist’s Behavior

Once the Receptionist role is selected, you will need to train the Inbound Agent to properly represent your business. The following input fields determine how the agent will interact with callers:

• How will the agent greet callers? - How the Receptionist answers calls or starts interactions (e.g., “Hello! Thanks for calling [Company Name]”).
• Introduction text (optional) - Optional text where the Agent introduces itself and its function (e.g., “I’m an AI receptionist working for [Representative Name]. How can I help you?”).
• Representative name - Name of the business representative the AI is assisting. This could be name of the CEO, or the Sales Manager, for example.
• Representative title - Job title of the representative (e.g. Sales Manager).
• Company name - The company the Agent is working on behalf of.
• Information to gather - What details the Agent should collect from the caller during the interaction (e.g., name, preferred email, preferred phone number, inquiry type).
• Key information - Business-specific data that the Agent should know (e.g., pricing, services, policies).
• Primary goal - The main purpose of the Agent (e.g., answering FAQs, booking appointments, forwarding calls).

If you need assistance filling in these training fields, you can use the built-in AI Copilot.
AI Copilot lets you describe your receptionist in plain language and will auto-populate a draft configuration for you.

• Click “AI-Copilot agent builder” to open the builder interface and explain your goals or agree to suggested options.

  

• Click “Perfect, let’s create the agent” once you’re satisfied. The assistant will automatically populate the customizable fields shown above, giving you a solid starting point you can refine.

  

We recommend not overthinking the instructions. Train your agent the way you would train an intern; not by defining an exact script that you want the Agent to follow, but by providing guidelines, points, and considerations that you want it to follow.

Remember, this is Generative AI, so trying to tell it what to say word-for-word suppresses its ability to be truly dynamic and responsive to the conversation.

Optional: Configure the Web Widget

If your Receptionist Agent is also or only deployed to the web, you can customize its appearance and placement using the Web Agent tab.

1. Web Widget Style

   • Select Primary Color – Set the base color of your widget to match your website branding.
   • Theme Selection – Choose between:
     • Light Theme
     • Dark Theme
   • Idle Image – Choose a preset icon that appears when the agent is idle.
   • Speaking Image – Choose a preset icon to display while the agent is speaking.
   • Speaking Animation Toggle – Enable or disable animation that plays when the agent talks.

   
2. Advanced Settings

   • Select Embedded or Overlay placement.
   • Choose justification: Left, Center, or Right.
   • Enable text features (Overlay only) with max 16/23 characters.

   
3. Website Setup

   • Enter the domain(s) where your Web Agent will be allowed to appear.
   • Include both www. and non-www versions if applicable.

   

Once saved, AVA will generate a code snippet you can embed in your site. Testing both Embedded and Overlay modes is recommended.

Optional: Add a Knowledge Pack

A Knowledge Pack allows your agent to access and reference structured company information during conversations. It can be used across both inbound and outbound projects.

Depending on your plan, you can create one or more Knowledge Packs and attach them to specific agents as needed.

Supported plans:

• Business Professional: 1 Pack
• Business Growth: 2 Packs
• Agency Lite: 1 Pack
• Agency Unlimited: 2 Packs

Steps to Add a Knowledge Pack:

1. In your inbound agent configuration screen, scroll down and click “Knowledge Packs.”

   

2. Click “Create New Knowledge Pack” to launch the builder.

   

3. Choose one or both of the following sources:

   • Upload files in .csv, .xlsx, .pdf, .txt, or .docx format
     • Up to 50MB per file; total upload limit of 500MB
   • Enter URLs to let AVA scan web pages for reference content
   

4. Once created, you can edit, delete, or refresh your pack from the right-hand menu.

   • To disable access temporarily, simply turn off the pack instead of deleting it.
   • You can re-enable the same pack at any time without losing the content.
   

🚫 Note: Sub-accounts cannot access Knowledge Packs created by an agency’s main account.

3. Assigning Actions to the Receptionist AI

Once your agent’s behavior and optional modules are configured, scroll to the section titled “What actions can the agent take?”

Each action appears as a toggle switch:

• Turning a toggle on opens a configuration sidebar.

• Once configured, the setup will be retained, even if later turned off.

• Re-enabling the toggle restores the saved configuration instantly.

  

1. Real-Time Appointment Scheduling

   • Lets the agent book meetings into connected calendars.
   • You must select a GHL calendar.
   • Optional: Add conditional logic for when booking should occur.
   • Works only in phone-based and web-based agents (not test calls).

   
2. Call Transfer

   • Enter the phone number to transfer to.
   • Define when the transfer should occur.
   • Add a message to be spoken before the transfer (e.g., “Let me connect you to someone…”).
   • Multiple call transfers can be set up with unique hours and conditions. If two conditions are true at once, the system prioritizes the first configuration in the list.

   

   • You can configure business/availability hours to prevent disruptive off-hour transfers (e.g., 3 AM).
     Outside configured hours, the agent will offer alternatives such as taking a message or sending an email.

   

   • Select the days of the week and customize the hours for each day. After customizing one day, use Copy All to apply the same hours across all days, if you wish.

   

   • Transfers only work in phone-based agents.
3. Notify The Rep

   • Enter up to 10 email addresses.
   • Each email includes:
     • Caller details
     • Summary + transcript
     • Call sentiment
     • Recording link (unless the call was transferred)
   • These are internal-only notifications.

   

---

FAQs & Troubleshooting

General Questions

Can I have multiple Receptionist AI Agents?

Yes, you can create multiple agents for different departments or use cases.

Can I customize the AI’s responses?

Yes, you can train the AI using the Key Information section to ensure it knows relevant business details.

Can I have a receptionist for both phone and web?

Yes, you can deploy the same AI for phone calls and website interactions.

Configuration

Where do I configure the widget if I’m using a web-based Receptionist?

The Web Widget is configured under the Web Agent tab in the agent setup. You can customize colors, size, placement, and domain targeting.

How do I add a Knowledge Pack to my receptionist agent?

Scroll to the Knowledge Packs section in the agent configuration. You can upload files or paste URLs, then toggle the pack on for the agent.

Can I use placeholders like {{client_firstname}}?

Yes. You can use dynamic placeholders in fields like greeting or key information to personalize responses.

Usage and Results

Can I test the agent before going live?

Yes. Use the Save & Test feature to run simulations. Note: actions like bookings and transfers require live phone or web calls.

Do Web Widget interactions support transfers?

No. Call Transfers only work for phone-based agents.

Will notifications be sent from my white-labeled domain?

Yes, if you’ve set up your custom email domain in the White Label > Email settings. Otherwise, emails will default to @thinkrr.ai.

---

For additional questions or guidance, try using our Virtual Support Agent! Available 24/7 to help resolve most issues quickly at thinkrr.ai/support.

If you still need assistance, visit our support site at help.thinkrr.ai or contact our team directly at [e-mail].