AI settings

To configure the agent’s AI behavior, open your Agent and click the Settings tab in the top navigation menu.

Available settings

AI Model

The AI model that the agent will use to think, plan, and generate answers to user queries.

Every model has different capabilities, reasoning speeds, and costs (if applicable). We recommend testing with different models (such as Z.AI’s GLM 5, DeepSeek V4, or OpenRouter) in the Playground to see which one works best for your specific agent’s use case.

Temperature

Controls the randomness and creativity in the Agent’s writing and decision-making.

Lower values are more deterministic; higher values are more varied.

• 0.0 - 0.3 (Precise): Best for support, policy-bound replies, data extraction, or when strict adherence to facts and formats is required.
• 0.4 - 0.6 (Balanced): Good general setting for helpful responses with light creativity.
• 0.7 - 1.0 (Creative): Use for brainstorming, marketing copy, or when conversational variety is desirable. Expect less strict consistency.

Tip: If your Agent must follow exact steps (e.g., collecting specific parameters for an HTTP Request or Lead Form), keep the temperature low. Raise the temperature only where tone and creativity matter and accuracy isn’t compromised.

System Prompt (Instructions)

Define the Agent’s role, goals, guardrails, and style (often called the “system prompt” or “instructions”).

Here are some of the things you can include in the instructions to get the best results:

• Role & purpose: What the Agent is for and what success looks like.
• Scope & boundaries: What it should and shouldn’t answer.
• Tone & language: Brand voice, formality level, and multilingual behavior (e.g., instructing it to auto-detect and reply in the user’s language).
• Compliance & safety: Any legal disclaimers, restricted topics, PII handling rules, and instructions for masking sensitive values.
• Formatting: Preferred reply structure (e.g., “always use short summaries, bullet points, and tables when presenting data”).