AgentSafeRead

An agent is a configured AI assistant within a product. Its behavior — model selection, thresholds, enabled tools, outreach settings and schedules — lives in its config. AgentSafeRead is the lightweight form (returned by the list endpoint) without the config blob; AgentRead includes the full config.

idIdrequired

Unique numeric identifier of the record.

product_idProduct Idrequired

ID of the product (workspace) that owns this record. Most endpoints scope access by product.

nameNamerequired

Human-readable agent name.

bot_typeAgentBotTyperequired

Agent behavior mode. outreach is the default; support enables support-ticket processing.

Possible values: [outreach, support]

is_activeIs Activerequired

Whether the agent is active.

created_atdate-timerequired

Creation time (UTC, ISO 8601).

AgentSafeRead

{
  "id": 0,
  "product_id": 0,
  "name": "string",
  "bot_type": "outreach",
  "is_active": true,
  "created_at": "2024-07-29T15:51:28.071Z"
}