Gather

The Gather item in an agenda is designed to collect specific information from users during a conversation. It enables the persona to ask targeted questions and store the responses as structured data, which can be utilized for further processing or integration with external systems.

How to Set Up

1. Navigate to the “My Persona” section in your dashboard and select the Agenda tab.
2. Create or edit an agenda and add a new item.
3. Choose the “Gather” type for the agenda item.
4. Configure the following settings:
   • Name: Assign a descriptive name to the Gather item.
   • Require Confirmation: Enable this option to confirm the collected data with the user before proceeding.
   • Number Of Fields Asked Per Message: Number of output fields asked per message.
   • Outputs:
     • Asked Outputs: Define the specific questions to ask the user (e.g., “What is your email address?”).
     • Inferred Outputs: Specify data to infer from the conversation context without directly asking the user.
5. Save and publish the agenda.

Asked Outputs

Asked outputs are the specific questions to ask the user.

• Output Name: The name of the output field. For example, “email”, “name”, “location”, “checkin date”, etc.
• Gather Logic (Optional): Define your rule when collecting the output data. For example:
  • Checkin date with format: “User checkin date, format as YYYY-MM-DD”
  • Location with full address: “User current location, format as full address: street, city, state, zip code”
  • Phone number with a pattern of 10 digit and start with 0: “User phone number, must be 10 digit number and start with 0”
• Condition Logic (Optional): The condition logic to control which output field will be asked or skipped. Just input your prompt:
  • Skip asking email if phone is provided: “Phone is not provided”
  • Skip asking checkin date if location is in london: “Location is not in london”
• Pre-Populate Logic (Optional): At the start of the agenda item, the AI will follow the pre-populate logic to pre-populate the output field. If the output field is successfully pre-populated, the AI will not ask the user in the conversation.

Inferred Outputs

Inferred outputs are data to infer from the conversation context without directly asking the user.

• Output Name: The name of the output field. For example, “email”, “name”, “location”, “checkin date”, etc.
• Gather Logic (Optional): Define your rule when collecting the output data. Similar with Asked Output.

Output data type

Define the data type you want to collect. This is usefull when you want to percisely collect information from the user. For example: when you collecting number of team members, you can define the data type as “number” so that the system can collect the number from the user and prevent collecting “one”, “two”, “three” etc.

Supported data types:

• String
• Boolean (true/false)
• Integer (natural number)
• Float (decimal number)

Control the conversation flow

• Only Asked Outputs will be asked in the conversation.
• The order output is the order of questions asked in the conversation.
• Use output condition logic to control which output field will be asked or skipped.

Advanced Settings

• Condition Logic: Define conditions under which this item should be triggered. Learn more
• Communication Mode: Define communication mode to interact with the user. Learn more.

Best Practices

• Clearly define the information you need to collect and ensure the questions are concise and relevant.
• Use “Require Confirmation” for critical data to minimize errors.
• Combine Gather items with other agenda types for a seamless user experience.
• Regularly review and update the Gather item settings to align with evolving requirements.