Skip to main content

​
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 thinkrr, you will be prompted to create an Outbound Project, or an Inbound Agent.
Otherwise, navigate to the Home screen in thinkrr.
  • 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
When creating a new inbound agent, configuration is organized into three tabs: Agent Settings, Call Settings, and Voice Settings.
  • Agent Settings
    • Agent Role – Select Receptionist to determine the agent’s function and tone.
    • Agent Name – Customize how the agent refers to itself during calls. If left blank, it will use its default name.
    • Train Agent from Website – Paste a public company URL and thinkrr will use your website content to pre-configure the training fields in the next step.
    • Phone Number – Assign an available number (Inbound Agents cannot share phone numbers).
    • Language – Agents can only speak their specifically assigned language. The selected language determines which voices are available.
    • Ethnicity – Optional voice style filter to help narrow down accent and delivery options.
    • Agent Voice – Use the Listen button to preview and select a voice.
  • Call Settings
    • Include History – Option to let the agent remember past conversations (phone agent only).
    • Noise Isolation Mode – Filters out background voices.
    • Maximum Call Duration – Caps call time (set in minutes).
    • End Call After Silence – Ends calls automatically after a set period of silence.
    • Background Sound – Add ambient noise (e.g., Coffee Shop).
    • Background Volume Slider – Appears if background sound is enabled.
  • Voice Settings
    • Loudness Level (volume) – Adjust how loud or soft your agent talks.
    • Responsiveness – Decide how quickly your agent replies.
      • Less responsive: Gives users more time to think or speak without interruption.
      • More responsive: Makes for fast-paced chats or real-time assistance.
    • Interruption Sensitivity – Controls how easily you can cut off the agent mid-sentence.
      • High sensitivity: Easy to interrupt at any time.
      • Low sensitivity: Agent will usually finish speaking before listening again.

​
2. Defining the Receptionist’s Behavior

Once the Receptionist role is selected and your initial settings are configured, you will need to train the Inbound Agent to properly represent your business. If you need to revisit or update these settings later, click the Settings button at the top of the agent’s page. This reopens the same three tabs—Agent Settings, Call Settings, and Voice Settings—allowing you to make adjustments at any time. Choose the model tier. At the top of the Agent Configuration screen, you’ll see:
  • Estimated credits per minute: An estimate of how many credits the agent consumes for each minute of calling, based on how it is configured. Click it to open What’s Driving This Estimate, which breaks the estimate down into Agent Model, Voice, Agent Training, and Actions. Actual consumption depends on what happens during each call.
  • Available credits: Your current credit balance.
  • Using: The model tier this agent runs on. Click Manage to change it.
Click Manage to open Select Agent Model Tier and choose Basic, which is reliable and efficient for shorter, linear conversations, or Premium, which offers deeper reasoning built for longer, more complex conversations. Agent calls consume subscription credits first, then purchased credits. For details, see Credit Pricing. 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.
  • Representative name – Name of the business representative the AI is assisting.
  • Representative title – Job title of the representative.
  • 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.
  • Key information – Business-specific data that the Agent should know.
  • Primary goal – The main purpose of the Agent.
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, but by providing guidelines and considerations you want it to follow.
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

  • Theme Selection – Choose between:
    • Light
    • Dark
  • Edit Idle – Select the visual displayed when the widget is idle.
  • Edit Speaking – Select the visual displayed while the agent is speaking.
  • You can:
    • Choose from available agent faces
    • Select from built-in icons
    • Upload a custom image (PNG format - 64 by 64 pixels recommended) for either Idle or Speaking state
2

Widget Size

  • Choose the display size of the widget:
    • Small
    • Medium
    • Large
3

Web Widget Experience

  • Placement Type
    • Overlay – Displays on top of your website content.
    • Embedded – Integrated directly into your page layout.
  • Justification
    • Left
    • Center
    • Right
  • You can reset the configuration at any time using Reset to default settings.
4

After Call Experience

  • Toggle this setting to display an AI-generated recap in the web widget after a conversation ends.
  • When enabled, users will see a short summary of what was discussed once the call is completed.
5

On Which Websites Will the Agent Be Published?

  • Enter the domain(s) where your Web Agent should appear.
  • Include both www. and non-www versions if applicable.
Once saved, thinkrr will generate a code snippet you can embed in your site. Testing both Embedded and Overlay modes is recommended.
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. Each Knowledge Pack uses one slot.Supported plans:
  • Agency Lite: 1 Knowledge Pack slot
  • Agency Unlimited: 2 Knowledge Pack slots
Additional slots can be unlocked from the Knowledge Packs page in the left-hand sidebar.

​
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 .md, .csv, .tsv, .xlsx, .xls, .pdf, .txt, or .docx format
      • Up to 25 files per Knowledge Pack, 50MB per file
    • Enter URLs to let thinkrr 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, let’s move to the Actions tab. 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.
4

Smart Actions

  • Allows your agent to automate CRM follow-up actions after completing a call.
  • Smart Actions require an active GoHighLevel CRM connection before they can be enabled.
  • Once turned on, you can choose which actions should run when the agent finishes a conversation.
  • Actions to trigger
    • Add Tags
      • Automatically apply one or more CRM tags to any contact who interacts with this inbound agent.
      • Tags must already exist inside GoHighLevel before they can be selected.
    • Trigger Workflow
      • Automatically start one or more published GoHighLevel workflows after the call ends.
      • Workflows must be configured and published inside GoHighLevel before they appear in the selection list.
⚠️ Important If you trigger workflows using Smart Actions, do not use Inbound Agent Call or AI Voice Studio Smart Trigger as the workflow trigger in GoHighLevel. Otherwise, the workflow may run twice.
5

Send Reports

  • Sends report emails summarizing the calls handled by that agent.
  • Choose Daily, Weekly, or Monthly reports.
  • Add up to 10 email recipients for each report setup.
  • Reports are sent automatically and provide a broader view of that agent’s call activity and performance.
6

Extract Custom Fields

  • Captures structured data from each call and stores it against the contact’s record in thinkrr.
  • Toggle Extract custom fields on, then click Action setup.
  • Click + Add field to select which fields you want the agent to extract.
  • Fields must be created first in Profile Settings → Contacts → Custom Fields before they appear in the list.
For full setup instructions, see Abilities & Actions.

​
FAQs & Troubleshooting

​
General Questions

Yes, you can create multiple agents for different departments or use cases.
Yes, you can train the AI using the Key Information section to ensure it knows relevant business details.
Yes, you can deploy the same AI for phone calls and website interactions.
Yes, inbound agents are designed to handle multiple concurrent calls without any issue.
No. If you don’t paste a URL during agent creation, you can add one later at any time. Open the agent configuration screen, click Settings at the top, and paste your website URL there to retrain and overwrite the existing training fields.

​
Configuration

The Web Widget is configured under the Web Agent tab in the agent setup. You can customize the theme, size, placement, and the domains where it appears.
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.
Yes. You can use variables in fields like greeting or key information to personalize responses.
Click Manage at the top of the Agent Configuration screen and select Basic or Premium. Basic is reliable and efficient for shorter, linear conversations, and Premium is built for longer, more complex ones.

​
Usage and Results

Yes. Use the Save & Test feature to run simulations. Note: actions like bookings and transfers require live phone or web calls. Test calls consume credits, starting with your test credits while you still have them.
No. Call Transfers only work for phone-based agents.
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 hello@thinkrr.ai.