AI in Customer Service: What It Does Today, in Numbers
AI in customer service today does four things: it answers chat questions, drafts replies to email, sends the simple replies on its own, and prepares decisions for people. It does not decide refunds. That is the short version. The rest of this page is one live operation, counted on 19 November 2026, so the claims come with numbers.
The operation is an online brand selling in eight languages through nine storefronts. The background is in our case study.
1. Chat: answered by AI
15,725 chat conversations in 30 days. 11,010 came from the website and 4,715 from the mobile apps. A human agent typed in none of them.
The chat AI answers questions of fact and published policy: product specifications, stock, where an order is, how to fix a fault, what the warranty says. It looks the order and the tracking up itself. Of these conversations, 44 percent started outside 09:00 to 18:00 Central European Time and 22 percent at the weekend.
2. Chat: requests passed to people
When a customer in chat needs something a person must carry out, such as a refund, a replacement, a cancellation or an invoice, the AI does not agree to it. It creates a ticket with the facts and gives the customer a ticket number. It created 1,694 tickets in the 30 days. A chat reply is sent the moment it is written, with no review, so the AI commits the company to nothing there.
3. Email: a draft for every message
36,789 customer emails arrived in 30 days, across five mailboxes. For each, the AI gathers the facts first: the order, the tracking status, what was said earlier in the thread, what the knowledge base says. Then it proposes a solution and drafts the reply in the customer's language.
26,451 replies were sent using an AI draft:
- 19,339 were edited by an agent before sending.
- 3,781 were sent by an agent without changing a word.
- 3,331 were sent by the AI on its own.
Seven in ten drafts are edited. That is the honest state of AI in email support: the draft saves the lookup and most of the typing, and the agent's judgement finishes it.
4. Email: simple replies sent alone
The 3,331 replies the AI sent on its own are replies with no decision in them: an order status, a warranty term, an invoice request, a public discount code, an address change before shipping. They went out a median of 6.3 minutes after the customer's email. On 18 November 2026, the AI sent 290 of the day's 1,397 replies this way.
These replies are listed in a review queue, sorted by type, where a person checks them. When a reply involves an action, the action is created after the reviewer passes it. The list of types the AI may send alone grows one type at a time, by risk.
5. Decisions: prepared, not made
Refunds, compensation, replacements and cancellations are decided by people. The AI's part is to have everything ready: the facts, a proposed solution from a fixed list, the draft. When the agent approves, the task goes to the person who carries it out and one line is written to a shared ledger, taken from the version the agent approved. Where the lines sit is in who approves what.
What customers think
Over two days from 17 November 2026, 217 customers rated an email reply. Among the 64 ratings for replies the AI sent alone, 7 were low, 11 percent. Among the 107 for tickets an agent closed, 21 were low, 20 percent. The AI handles the simple cases, so this is not a like-for-like contest. It does show that the replies the AI sends alone are not where the low scores come from. The full reading is in CSAT for AI customer service.
What AI gets wrong
- It invents. A shop name, an order number, a policy detail. See hallucination examples and fixes.
- It promises. In a review of 400 edited drafts, 53 percent of the edits removed a promise the agent did not want to make.
- It misses what is in front of it. In long threads it overlooks what was already agreed, unless the thread is turned into a short list of facts first.
- It misreads tone. A sarcastic "thanks" was once read as thanks.
Each of these has a fix in the system around the model, not in the model.
What it changes for the team
Agents stop looking things up and start deciding. The work that remains is the work that needs a person: money, exceptions, angry customers. The team also gains cover it did not have: 35 percent of emails and 44 percent of chats arrive outside office hours. See after-hours customer service with AI.
Where to start
Start with one channel and one type of question, keep a person reviewing everything, and measure what they change. The method is in running a pilot on real work. Tell us your channels and volume and the free plan sets out the first step within two working days.