This guide explains how to launch automated outbound call batches using the Outbound CSV files column on the Widgets page. By creating items with structured CSV data, you can queue calls and define call reasons without interruption from platform updates.
Define the outbound call list
To start a batch of calls, you must create a new item on the Widgets page under the Outbound CSV files column containing your CSV data.
Navigate to the Widgets page in the Builder.
Locate the Outbound CSV files column.
Click the + (plus) button at the top of the column to create a new item.
Enter a Title for the batch (e.g., "Leads Batch 1").
Paste your structured CSV data into the Body field.
Click Save.
Once saved, the AI Employee analyzes the data and queues the calls. You can create multiple batches by adding new items to the Outbound CSV files column.
CSV format requirements
Your data in the Body field must be formatted as standard CSV.
Header row: Include a header row to define column names (e.g.,
Phone Number,Reason to Call). This helps the agent accurately identify the data.Phone numbers: Ensure phone numbers are in a valid international format (e.g., include the country code like
+1...). Invalid formats may prevent the call from being placed.
❗❗ IMPORTANT
Avoid duplicate phone numbers in the CSV. Duplicates can lead to issues with calling logic and result tracking.
Example CSV data
Phone Number,Reason to Call
+1234567890,Follow up regarding the recent laptop purchase. Ask if they are satisfied with the service.
+1987654321,Check in regarding their account. Inform them the account has been upgraded to premium status.
Retrieve call results
Once the agent processes the calls, the results are written to a project attribute.
Navigate to the Attributes page.
Search for the
project_attributes_outbound_call_table_csv_resultattribute.Copy the content from the attribute value.
Save the content as a
.csvfile (e.g.,results.csv) to open it in spreadsheet software for analysis
🗒️ NOTE
If your list contains many entries (typically more than 50), the system will automatically generate multiple result attributes (e.g., ..._batch_1, ..._batch_2) to store the data.