Working with customers
Guardrails: spam, floods and blocking
AI spam detection that pauses chats, a per-visitor rate limit, blocked countries and blocklists.
Open Build → Guardrails.
Spam detection
After the customer's 2nd, 4th, 8th and 16th message, AI checks the chat. When it's clearly spam — ads, link farms, gibberish, bots, attempts to make the assistant break its rules — the chat is paused: the AI stops answering (so it doesn't spend credits), and the chat is marked ⛔ Paused in the inbox. You can describe what counts as spam for your business in your own words. Real customers — even rude ones — aren't paused.
Rate limit
How many messages one visitor can send on your website chat in a time window (20 per minute by default), and the message they see when they go over.
Blocked countries
Visitors from the countries you choose don't see the chat bubble or your help center, and can't use the chat. WhatsApp, Messenger and other apps aren't affected.
Blocklists
IP addresses (end with * for a range), emails (or @domain.com) and phone numbers. Chats from them are paused right away.
In the inbox
⛔ Pause stops the AI in any chat. On a paused chat, Block visitor adds their IP, email and phone to the blocklists; Not spam — un-pause lets the AI answer again (and removes them from the blocklists).