Create and Configure an Intellect

← Back to Agent Components

An intellect is the config object behind your agent's brain. It holds the prompts, model settings, tools, knowledge base links, and feature capabilities that shape how the agent behaves. This page shows how to create one and configure its main fields.

Generate an Agent Profile

Optional first step: turn a one-line description into the prompt values an intellect needs.

POST https://api.avatar.us.kaltura.ai/v1/application/generateAgentProfile

{ "userDescription": "A friendly technical support agent for a video platform" }

Returns {goal, targetAudience, restrictedTopics, name, openingPhrase}. Nothing is saved: pass goal, targetAudience and restrictedTopics into the intellect's prompts and openingPhrase into the intellect's opening_phrase (§ Configure an Intellect, below). Leave the avatar's own openingPhrase unset (Agent Components · Create an Avatar and an Agent).

Create an Intellect

POST https://genie.nvp1.ovp.kaltura.com/v1/intellect/add

{ "type": "internal", "status": 2 }

Returns the full intellect object. Save id — this is your configId.

Configure an Intellect

POST https://genie.nvp1.ovp.kaltura.com/v1/intellect/update

{
  "id": 1389,
  "type": "internal",
  "status": 2,
  "prompts": [
    {
      "key": "goal",
      "label": "Goal",
      "headerTemplate": "Your core strategic goal:",
      "type": "custom",
      "value": "Help users troubleshoot video streaming issues"
    }
  ],
  "base_directive": "You are StreamBot. Be concise and technically accurate.",
  "capabilities": {
    "avatar": "on",
    "generate_followup_questions": "on",
    "use_knowledge_base": "off"
  }
}

Prompts — each block composes a system-prompt section:

Don't guess at key/headerTemplate values. Call mgmt.application.getCustomPrompts(ks) instead. It returns the backend's own live schema for this block: a 5-entry array (goal, targetAudience, restrictedTopics, name, knowledge), each shaped as {key, label, headerTemplate, type} (type is always "custom", matching the prompts[] block shape above).

Use this call to render a "describe your agent" form. The labels and instructions you show always match what the backend splices into the system prompt, so you don't have to keep hardcoded copy in sync by hand.

This call only reads data — it has no side effects. It works with any kind of session token, since the schema itself isn't specific to any one partner.

const fields = await mgmt.application.getCustomPrompts(ks);
// [{ key: 'goal', label: 'Goal', headerTemplate: 'The agent\'s goal is: {{value}}', type: 'custom' }, ...]

Top-level fields:

Capabilities — each is "on" / "off" / "disabled":

capabilities is a full-replace sub-dict. To change one key, read the current dict first and re-send it with your overlay. The SDK handles this automatically via mgmt.intellects.setCapability.

Note: force_experience is not an intellect field — it's a per-call option on converse() (values "markdown", "summarization", "flashcards", "avatar_only"; a hint, not a guarantee). See Converse.

Related docs