It is highly recommended to use the Persona Builder to create your objectives, although you can use the Create Objectives API directly.
- Explain your entire ideal workflow to the Persona Builder. This will help create a robust branching structure that successfully takes the participant from start to finish.
- Think through the possible answers a participant might give, and ensure the workflow covers these cases.
- Ensure your persona’s system prompt does not conflict with the objectives. For example, a system prompt, “You are a tutor,” would not perform well with the objectives workflow of a sales associate.
- Add them during persona creation like this:
- Add them by editing the persona like this:
For the best results, try creating unique objectives for different conversation purposes or business outcomes.For example, a customer onboarding persona might use objectives focused on data collection, while a support persona might use objectives focused on issue resolution.
Parameters
objective_name
A desciptive name for the objective.
Example: "check_patient_status"
This must be a string value without spaces.
objective_prompt
A text prompt that explains what the goals of this objective are. The more detail you can provide, the better.
Example: "Ask the patient if they are new or are returning."
confirmation_mode
This string value defines whether the LLM should determine whether this objective was completed or not.
- If set to
auto
, the LLM makes this decision. - If set to
manual
, the participant must manually confirm that the objective was completed by the platform triggering an app message (conversation.objective.pending
) and the participant having the ability to send one back calledconversation.objective.confirm
. This can include having the participant review the collected values for accuracy.
The default value of
confirmation_mode
is auto
.output_variables
(optional)
This is a list of string variables that should be collected as a result of the objective being successfully completed.
Example: ["patient_status", "patient_group"]
modality
This value represents whether a specific objective should be completed based on the participant’s verbal or visual responses. Each individual objective can be visual or verbal (not both), but this can vary across objectives.
The default value for
modality
is "verbal"
.next_conditional_objectives
This represents a mapping of objectives (identified by objective_name
), to conditions that must be satisfied for that objective to be triggered.
Example:
next_required_objectives
This represents a list of objectives (identified by objective_name
) that should be triggered once the current objective is completed.
Example: ["get_patient_name"]
callback_url
(optional)
A URL that you can send notifications to when a particular objective has been completed.
Example: "https://your-server.com/objectives-webhook"