AI assistant
What it is
The AI assistant is an employee you describe in words rather than program. It reads the customer's incoming messages, replies on its own, finds out what you need to know, and hands the conversation to a real person at the right moment.
It works across every connected channel at once — WhatsApp, Instagram, Telegram, the website widget. There is no need to configure it per channel.
The assistant subscription is billed per company, not per channel. Building the assistant, filling in every section and testing it in the sandbox is free — the subscription is what lets it start replying to real customers.
Getting started
Open AI assistant in the left menu. The settings are split into four groups: Settings, Scenarios, Knowledge and Connections. Sections marked with an asterisk are the ones the assistant will not start without — the rest can wait, they add knowledge but are not required to launch.
The minimum to get it running:
- Role — who it speaks as. For example: "You are a sales manager at company X".
- Goal — what exactly it needs to find out from the customer.
- Qualification checklist — at least one item the assistant should establish during the conversation.
Until those three are filled in, the assistant cannot be switched on — the button will tell you which sections are missing.
Setting its character
- Tone of voice — brief or detailed, formal or casual, emoji allowed or not.
- Restrictions — what the assistant must never promise. This rule outranks the scenario: it holds even when the customer pushes hard. For example: "never promise a discount or an exact delivery date".
- Additional instructions — anything that did not fit the other fields. For example: "the Abay branch is closed on Saturdays — offer Satpayev instead".
- Maximum questions per message — not a suggestion but a guarantee: if the model tries to ask more, the extra questions are trimmed before the message reaches the customer.
0means no limit.
Restrictions hold more reliably than requests placed in other fields. If something is critical — "never quote a price over the phone", "never agree to a refund" — put it in Restrictions.
When a human is called in
The Hand over to a manager if field describes the condition under which the assistant stops running the conversation. For example: "the customer asks for a discount or a call", "asks for a company invoice", "complains".
After a handover the assistant stops replying in that conversation — from then on it is the manager only. This is deliberate: a customer who has already been passed to a human should not start receiving robot answers again.
What happens when qualification finishes
When the assistant considers the task done, it leaves the manager a note with the collected data. If a CRM is connected, two more actions become available:
- Add a note to the CRM — the summary lands in the lead or deal timeline.
- Move the deal to a stage — you pick the pipeline and the stage.
Moving the deal overwrites its current stage in the CRM. If a manager is working that deal in parallel, the assistant can roll it backwards — enable this action deliberately.
Both actions require a CRM connected in the "CRM integration" section.
Testing before launch
The Test button opens the sandbox — a conversation with the assistant that no customer ever sees. It behaves exactly as it would in production: it uses its knowledge, works through the checklist, and hands over on your condition.
Run three scenarios in the sandbox before switching it on:
- A customer who answers willingly and reaches the end of the checklist.
- A customer who immediately asks for a human — to confirm the handover fires.
- A question the assistant has no answer to — to see whether it invents one.
Knowing that it works
Go to Analytics → AI assistant. The numbers that matter:
| Metric | What it means |
|---|---|
| Conversations | How many distinct conversations the assistant handled |
| Forms collected | Where it reached a complete form and left a note |
| Collection rate | What share of conversations reached a form |
| Handed to a human | Where the assistant went quiet and called a manager |
| Replies per conversation | On average. Too many means the customer got tired; too few means conversations were breaking off |
| Cost | What the model calls cost, in dollars |
A separate Build summary button analyses every conversation in the period as a whole: the AI looks for patterns invisible in a single dialogue — where people drop off, what they ask about repeatedly, how things skew by city and time of day. The analysis takes up to a minute.
Assistant statistics start from 16 September 2026. For earlier conversations there is no technical way to tell an assistant reply from a broadcast, so they are not included.
Common questions
Does the assistant always reply instead of a manager? No. It stays silent in conversations already handed to a human, and in those where your handover condition has fired.
What if it does not know something? The more thoroughly the "Knowledge" sections are filled — reference lists, documents, frequent questions, exceptions — the less often it gets stuck. Check with the sandbox: that is where you see whether it invents an answer or honestly calls a human.
Can it be switched off temporarily? Yes, with the toggle at the top of the section. The settings are kept — switch it back on and it continues with the same knowledge.