Bulk update evaluators

Scopes the permission check to a specific agent (either this or project is required). When provided, also overrides each evaluator's agent to this ID.

Scope the permission check to a specific project. Either this or agent is required.

Replace each evaluator's personality with this ID.

Replace each evaluator's test profile with this ID.

Text appended to every evaluator's instructions. Concatenates on each call — not idempotent.

Replace each evaluator's first message.

Replace each evaluator's outbound phone number ID.

Replace each evaluator's inbound phone number ID.

Move every evaluator into this folder. Dot-separated (e.g. "Sales.Inbound").

Replace each evaluator's max duration in seconds.

Unique identifier for the AI agent Example: 123

Name of the scenario

Foreign key reference to the personality used in this scenario

Name of the personality used in this scenario Example: "Normal Male"

Name of the agent associated with this scenario Example: "Customer Support Agent"

Expected outcome prompt for the scenario Example: "The user should be able to complete the order"

Scenario Instructions - format depends on scenario_type:

For scenario_type="instruction": Plain text describing the caller's behavior. Example: "You are a customer calling to inquire about your order status. Be polite and provide order number 12345 when asked."

For scenario_type="conditional_actions": Use the structured conditional_actions field instead. If you must send via this field, pass the same object as a JSON-formatted string. The earlier id-based format (id, condition, action, type, fixed_message) is still accepted on writes. Responses return this shape unless conditional_actions_format=legacy is passed:

{
  "role": "A friendly customer calling about an appointment",
  "first_message": "Hi, I'd like to check on my upcoming appointment <silence time=\"1.5s\" />",
  "conditions": [
    {"when": "The agent asks for your name", "say": "My name is Sarah Johnson"},
    {"when": "The agent asks for your date of birth", "say": "January first, nineteen ninety"},
    {
      "when": "The agent confirms your identity and provides appointment details",
      "say": "Thank you, that's all I needed",
      "then": ["<endcall />"]
    }
  ]
}

Structure:

• role: Personality/role description
• first_message: What the caller says first; empty means wait for the agent. Use {"say": "...", "then": [...]} to add follow-ups.
• conditions[].when: A third-person description of the agent's observable action, matched semantically against the conversation
• conditions[].say: The caller's reply, spoken verbatim. Wrap the whole step in <ai_generated>...</ai_generated> to let the caller improvise from it instead
• conditions[].then: Optional follow-up steps, each fired on the caller's next turn after one agent reply, in order
• Steps support SSML <silence time="1.5s" /> (interruptible), <hold time="2s" /> (not interruptible), [laughter] and <endcall /> in verbatim steps

Language code for the scenario (ISO language code)

• af - Afrikaans
• ar - Arabic
• bn - Bengali
• bg - Bulgarian
• zh - Chinese Simplified
• cs - Czech
• da - Danish
• nl - Dutch
• en - English
• et - Estonian
• fi - Finnish
• fr - French
• de - German
• el - Greek
• gu - Gujarati
• hi - Hindi
• he - Hebrew
• hu - Hungarian
• id - Indonesian
• it - Italian
• ja - Japanese
• kn - Kannada
• kk - Kazakh
• ko - Korean
• ms - Malay
• ml - Malayalam
• mr - Marathi
• multi - Multilingual
• no - Norwegian
• pl - Polish
• pa - Punjabi
• pt - Portuguese
• ro - Romanian
• ru - Russian
• sk - Slovak
• es - Spanish
• sv - Swedish
• th - Thai
• tr - Turkish
• tl - Tagalog
• ta - Tamil
• te - Telugu
• uk - Ukrainian
• uz - Uzbek
• vi - Vietnamese

Type of scenario:

• instruction: Standard instruction-based scenario where instructions field contains plain text
• conditional_actions: Conditional action-based scenario where instructions field contains JSON

• instruction - Instruction
• conditional_actions - Conditional Actions

Foreign key reference to the AI agent that owns this scenario

(Deprecated) Foreign key reference to the phone number. Use phone_number field instead. This field is maintained for backward compatibility and will be automatically synced with phone_number.

Details of the phone number used for inbound calls

List of metrics associated with this scenario for evaluation

List of metric names associated with this scenario Example: ["Metric 1", "Metric 2", "Metric 3"]

The initial message that the AI agent will send when the scenario starts

Test profile ID Example: 123

Timestamp when the scenario was created

Timestamp when the scenario was last updated

ID of the user who created this scenario

ID of the user who last updated this scenario

Path of an existing folder to assign this evaluator to, e.g. "Sales" or "Sales.Inbound". Create it first with the create-folder endpoint.