How do I customize the copilot's behavior and response style?

Click the gear icon next to 'AI Copilot' in the panel header to open Copilot Settings. You can customize the greeting, closing, system prompt, AI model, and context size. The system prompt controls how the copilot drafts responses - you can instruct it to match your tone, include specific information, or follow particular formatting rules.

How do I open Copilot Settings?

Click the gear icon next to 'AI Copilot' in the panel header. The Copilot Settings dialog opens with the greeting, closing, system prompt, and an expandable Advanced section for the model and context size.

What does the system prompt control?

The system prompt is the set of instructions that guides how the copilot drafts every reply - its tone, formatting, and rules such as using knowledge base content as the source of truth and declining unrelated questions. You can customize it up to 6,000 characters, and Reset to Default restores the original prompt.

How do I change the greeting and closing of suggested replies?

Set the greeting and closing fields in Copilot Settings. Use [name] in the greeting as a placeholder for the sender's name, and replace the closing placeholder with your own name or team name so every suggestion is ready to send.

Does the AI model or context size affect credit cost?

Yes. Each suggestion costs credits, and the model you choose affects the credit cost per suggestion. A larger context size includes more knowledge base content per suggestion and costs more credits than the default.

Configuring Copilot Behavior - ChatLab Help Center

Click the gear icon next to "AI Copilot" in the panel header to open the Copilot Settings dialog.

Greeting

The opening line the copilot adds to every suggested response. Default: Hi [name],

Use [name] as a placeholder - it is replaced with the sender's name automatically.

Closing

The sign-off appended to every suggestion. By default it spans two lines:

Best regards,
[your name]

We recommend replacing the [your name] placeholder immediately with your actual name or team name, for example Best regards, ChatLab Support. This way every suggested reply is ready to send without manual editing.

System Prompt

Instructions that guide how the copilot drafts responses. The default prompt tells the copilot to:

Draft professional, concise replies in plain text
Use knowledge base content as the source of truth
Match the sender's tone and formality
Not invent facts beyond what the knowledge base contains
Decline unrelated questions politely
Append source URLs when knowledge base content is used

You can customize this prompt up to 6,000 characters. Click Reset to Default to restore the original prompt.

Advanced settings

Expand the Advanced section to configure:

Model - select the AI model used for suggestions. Each suggestion costs credits, and the model you choose affects the credit cost per suggestion.
Context Size - how much knowledge base context to include with each suggestion. Options:
- 8,000 tokens (default)
- 16,000 tokens
- 32,000 tokens

A larger context size lets the copilot access more of your knowledge base per suggestion but costs more credits.