How do I set the AI's tone and what it can and can't say?

Your AI assistant's personality and boundaries live under Settings, then AI Assistant. Give it a name and greeting, pick a tone, and decide what it is allowed to talk about, what it must always mention, and what it must never say. This page is limited to your organization's admin.

Name and greeting

Under the Agent tab:

1. Optionally give it a name, shown in its greeting and through the rest of the conversation.
2. Choose whether it says hello when someone opens chat, and optionally write your own greeting message.

Tone

Under the Advanced tab, pick one of three tones: Friendly, warm and conversational, Professional, courteous and polished, or Direct, concise and to the point. This applies on top of everything else it says.

What it can talk about

Under Topics & Rules:

• How strict should it be? Strict answers only your listed services and always deflects anything else. Balanced stays focused on your services but can handle adjacent questions using its general knowledge. Open answers anything, noting when something is outside what you offer.
• In-scope services are what you actually offer, they keep the AI focused. Out-of-scope topics are things it should refuse even if asked directly, legal advice, say, if that is not something you do.

Must-say and never-say rules

Add short rules the AI always follows. A must-say rule is something it should always mention when relevant, like a guarantee. A never-say rule is something it must never say, even if a customer pushes. Some never-say rules are set by Peakify for every customer and cannot be removed, marked Platform rule in the list, these exist for everyone's safety and always show above your own.

The off-topic and "I don't know" messages

Set a custom line for when a visitor asks about something out of scope, and a separate one for when the AI genuinely does not know the answer and needs to bring in your team. Leave either blank to use Peakify's standard wording.

The raw system prompt

If you want full control, the Advanced tab shows the actual instructions sent to the AI, built automatically from everything above. Switch to Edit manually to write it yourself instead, or use Enhance with AI to describe a change in plain English, make it warmer, add a rule about after-hours messages, and review the rewrite before accepting it. A few safety rules are always added on top of whatever you write and cannot be removed, they stop a customer's message from being treated as a hidden instruction, and stop the prompt itself, or any API keys, from ever being revealed.

Restoring the defaults

Any section, in-scope services, out-of-scope topics, must-say or never-say rules, or the off-topic response, has a Restore industry defaults button that resets just that section back to the starting point for your kind of business.