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).
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 it’s ability to be truly dynamic and responsive to the conversation.
Example Configuration
A very interesting use case of the Receptionist Inbound Agent, especially for businesses looking to implement Voice AI for their clients or prospects, is the demo “roleplay” Agent.
In this setup, the Receptionist Agent not only acts as the first point of contact—answering questions about the business—but is also designed to roleplay with the caller. It pretends to be an employee of the caller’s business so that the caller can experience firsthand what it would be like to have this technology working within their own company.
To enable this scenario, you can configure your Agent with the following prompts:
Information to gather
Ask the caller:
- Their name
- The name of their company
- What services they offer
- How long they’ve been in business
- What kind of situation they would like to roleplay
It’s important to collect all of this information, but do it in a casual, conversational way. Avoid going through the list mechanically—treat it like a natural conversation.
Key Information
Andrew’s Automations is a full-service AI consultancy that provides AI solutions to small and medium-sized businesses. Core offerings include setting up inbound and outbound AI calling agents for customer support, multilingual support, sales, call transfers and escalations, appointment booking, and re-engaging old leads.
Primary Goal
The Agent’s goal is to:
- Collect all the details listed above.
- Confirm the caller’s name and company name before starting the roleplay.
- Begin the conversation as a representative of Andrew’s Automations, then switch personas to act as a representative of the caller’s business.
- Conduct a live, interactive roleplay based on the caller’s chosen scenario.
- Let the caller experience the Agent in action by carrying on a natural conversation (without stating roles or dialogue turns explicitly).
- Conclude the roleplay by saying: “That concludes this roleplay.”
- Then switch back to being Andrew’s receptionist and ask the caller how they felt about the experience.
- If appropriate, guide the caller toward booking a meeting with Andrew.
This use case is a powerful way to show potential clients the real-world value of AI call handling.
3. Assigning Actions to the Receptionist AI
A Receptionist Inbound Agent is more than just a virtual assistant—it can also take real-time actions to streamline business workflows.
- Click “Manage Actions” to configure:
- Real-Time Appointment Scheduling:
- Enables the AI to book meetings directly into a connected Calendar.
- Example: If a caller inquires about scheduling a consultation, the AI can check availability and book a meeting directly into the chosen calendar
- Real-Time Appointment Scheduling:
- Call Transfers:
- The AI can route calls to human representatives or even other Inbound agents.
- Users can configure:
- Phone numbers to transfer to.
- Conditions for transferring (e.g., sales inquiries → sales team).
- Pre-transfer messaging (e.g., “Let me connect you to our sales team. One moment, please.”).
- Representative Notifications
- The AI can send email summaries of calls, including:
- Caller details (name, phone number).
- A summary of the conversation.
- A full transcript of the call.
- Call sentiment analysis.
- A link to the call recording.
How to Edit an Existing Receptionist AI
-
Navigate to the Active Agents list on the Home screen.
-
Click directly on the agent you wish to edit (or click the 3 dots in the corner)
-
Modify any of the training inputs (greeting, key information, primary goal, etc.).
-
Adjust actions such as booking, transfers, or notifications.
-
Save the changes and test the Inbound Agent using the “Save & Test” feature.
Notes & Additional Considerations
- Phone-based Receptionist Agents require a valid phone number to function.
- One phone number cannot be assigned to multiple inbound agents.
- AI agents can function across both phone and web for a unified experience.
- Outbound campaign phone numbers can be used for inbound agents, allowing call-backs to be handled by AI.
- Test mode does not support live actions (e.g., booking, transfers, notifications).
FAQs & Troubleshooting
General Questions
Troubleshooting
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 and submit a Ticket or contact our team directly at hello@thinkrr.ai.