Output

Definition

The Agenda Output feature in Persona Studios allows users to extract structured data from conversations conducted by their personas. Outputs are data fields generated during or after a conversation, capturing essential information for further processing or analysis.

Types of Outputs

1. Asked Outputs: These are direct questions posed to users during a conversation. For example, collecting a user’s name or email address.
2. Inferred Outputs: These are derived from the conversation context without explicitly asking the user. For instance, determining if a user is located outside a specific region based on their responses.

Asked Outputs

Asked outputs are the specific questions to ask the user. Only Gather Item can have asked outputs.

• 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”

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.

You can test and reset inferred outputs by clicking on the buttons below:

The Reset Output option restores the output description to its original state, discarding any modifications made. This is useful when you want to revert back to the default description (which is a summary) without applying changes.

The Testing Output feature allows you to select a previous conversation, input a new output description, and observe how the system processes it. This provides a way to preview how the updated description affects the response. Once satisfied with the results, you can apply the new description to update future interactions accordingly. Step by step:

1. Hit the test button of your desired inferred output to test
2. Select an agenda conversation in the past to test
3. Change the output description to describe how to extract your target information
4. Hit the Test button, new output value and reasoning will show up.
5. Verify the new output value if it match your needs. Then hit the Apply button to update the output description. Note: don’t forget to hit Publish agenda to save the changes.

Usage

Outputs enable seamless integration with external systems like CRMs by mapping collected data to predefined fields.They provide a summarized view of the conversation, highlighting key points and user-provided information.

Best Practices

• Clearly define the data fields required for your use case.
• Use asked outputs for mandatory information and inferred outputs for supplementary insights.
• Regularly review and refine output configurations to ensure data accuracy and relevance.
• Use the test button to experiment with the prompt to get your desired result.