The AI Drafts the Reply Before You Type a Letter
The moment a customer message lands, the AI drafts three separate replies. It reads the intent, summarises the conversation and pulls from the customer card and your knowledge base. Your team picks one, approves it, and sends. The suggestions your team recently approved and edited become examples for the next draft.
When a customer message arrives, the AI drafts a reply in the inbox from the conversation summary, the intent and your knowledge base. Your team picks and approves one. The AI that writes the suggestion never messages the customer on its own. In the flows you build, the bot writes without waiting for approval. The knowledge base feeds the suggestion; it does not guarantee that every suggestion is right.
This page is about the reply draft in the inbox. The suggested action in the Intent AI drawer is a separate job: there the AI tells you what to do and shows its reasoning, and you copy the text yourself.
Zeynep Y.
Hi, how much is your implant price and what do I need for an appointment?
14:23
AI suggestion · Intent: price and appointment question
The reply is ready the moment the message arrives
Your team picks with one tap and the answer goes out. Look at this example:
Conversation summary & intent
Zeynep asked for the implant price and what an appointment needs. She has the price range, wants to pay in instalments and is undecided on the exam day. Tone stays positive.
Intent
APPOINTMENT
92%
Objection
PRICE
Medium
Urgency
HIGH
Deciding today
Satisfaction
8.4/10
Positive
⚡ Suggested next action
Share the instalment options + offer available exam days → appointment
Three ready replies · conversation summary · intent reading
The AI weighs every incoming message against your knowledge base, sector patterns and the customer's history. It drafts three tones at once (formal, short, friendly). Your team taps to send or edits first. Conversation summary, intent score and the suggested next step sit in the same panel.
This page covers the suggestion side for agents; in the flows you build, the bot does send without your approval. We explain the difference between the two layers on our approach to AI page.
- Three drafts at once: formal · short · friendly
- Conversation summary: catch the context of a long thread in seconds
- Intent score: purchase, question, complaint, return or undecided
Automatic tags & an instant customer card
The AI reads the conversation and applies the tag itself (price question, campaign, undecided, follow-up needed). The conversation is matched to the right customer record. That person's card and earlier threads stay on the right side of the panel. Your team does not have to look for the history somewhere else.
- Smart tags: topic, intent, customer profile and urgency together
- Customer card and earlier threads stay open on the same screen
- The agent who takes over reads the summary instead of the whole thread
Customer card (auto-matched)
AUTOMATIC TAGS
CONVERSATION HISTORY
3rd conversation · Previous topic: check-up appointment · Preferred channel: WhatsApp
The agent's edit
Representative screenAI DRAFT
Hello, our open days for an examination are Tuesday and Thursday. Which one suits you?
WHAT THE AGENT SENT
Hello Ms Zeynep, Tuesday 14:00 or Thursday 10:30 works for the examination. We will also go through the instalment options that day.
This edit is saved and used as an example when the next draft is prepared.
Your team's edits become examples for the next draft
When an agent approves, edits or rejects a suggestion, that decision is saved. Recent decisions and edits are given to the AI as examples when the next draft is prepared. It is not a guarantee of accuracy; the agent takes the last look before sending. This section is about the suggestion for the agent; in the flows you build, the bot writes without waiting for approval.
- Approve, edit and reject decisions are saved
- Recent edits go to the next draft as examples
- The decision to send stays with the agent
Knowledge base integration (RAG)
Load your PDF or your website content into the system. When a customer asks something, the AI drafts from the documents you uploaded. When the draft rests on a document, your team sees which one. The source feeds the suggestion, it does not limit it. The agent is the one who catches a wrong suggestion before it goes out.
If you add an FAQ step to a flow, the bot sends the answer it finds in your documents without waiting for approval.
- Brings the information in your documents into the draft
- When the draft rests on a document, that document is listed next to it; approval stays with the agent
- Cross-language search: a question asked in Turkish is found in an English document
Customer question
"How many days do I have to return? Do I pay the shipping?"
Draft from the KB, the agent approves
Our return period is 14 days. For unused items with tags still attached, we cover the return shipping. For damaged or used items the shipping cost is paid by the customer.
Give your team a higher gear
Instead of typing into a blank box, your agent edits a ready draft and sends it. A new hire finds the clinic's saved replies and knowledge base in front of them from day one.
