--- title: "AI in customer service: what works and what fails | attendo" description: "Which uses of AI in customer service work today, which do not, and what to ask about cost, errors, data and control before you switch anything on." url: "https://attendo.me/en/blog/ai-in-customer-service-what-works" lang: "en" --- # AI in customer service: what works and what doesn’t We keep hearing that AI will transform customer service. Some things it has already changed, and others still do not work well. It is worth telling them apart before you spend money. - By the attendo team - Published September 27, 2026 - 4 min read **In this article** 1. What works today 2. What does not work well 3. Four questions before you switch anything on 4. Where to start ## What works today ### Draft replies It is a use with a good balance of benefit and risk. The AI reads the thread and the customer’s history and proposes a reply. The agent edits it and sends it. Adjusting text that is almost right takes less time than writing it from scratch. It works because a person is still in the loop and because mistakes are cheap: if the draft is bad, you throw it away. ### Classifying and prioritizing what comes in Reading an email and deciding its type, priority and queue is a repetitive task AI does well. And mistakes are easy to fix: a misclassified ticket gets reclassified. ### Transcribing and summarizing calls Turning a fourteen-minute call into four useful lines saves the most tedious part of the job. And calls finally become searchable. ### Filtering out what is not a request Spam, newsletters and auto-replies, gone before they create work. Not glamorous, and very worthwhile. ### Questions about your own data “How many hours have we spent on this customer this year?” without waiting for someone to build a report. It works if the system does not let the AI write free-form database queries. The safe approach is for it to propose a plan over approved tables and to show what it looked up. ## What does not work well ### The chatbot that solves complex technical cases It handles frequent, documented questions well: opening hours, the status of a ticket or how to do something covered in the knowledge base. Beyond that it gets stuck. The problem is not that it gets stuck, but that the customer has already spent five minutes before reaching a person, and arrives annoyed. What does work is a chatbot for the frequent questions with a clear, quick way out to a person, not one hidden behind three menus. ### AI closing tickets on its own It is technically possible and commercially dangerous. A ticket closed by mistake leads to a reopen and a complaint. And the complaint is against the company, not the model. ### Technical diagnosis without your documentation A general-purpose model does not know how your specific equipment fails. With your documentation loaded, it helps. Without it, it makes up answers with great confidence, which is the worst thing that can happen. ### Predicting failures without data It gets sold a lot, but it needs data: sensor readings or a long, well-kept history. If your history covers two years and has gaps, no model can predict anything, however good it is. ## Four questions before you switch anything on 1. **How much will it cost me each month?** There must be a usage screen and a budget with a cap, not an estimate. Without that, do not turn it on. 2. **What happens if it gets it wrong?** If the answer is an angry customer, a person must review before anything is sent. 3. **Can I turn it off?** Feature by feature, without breaking the rest. 4. **Where does my data go?** Which provider processes each request, and whether your data leaves the region it has to stay in, such as the European Union. ## Where to start With draft replies, for one month, on a small budget, measuring time per ticket. If it saves time, expand it. If not, turn it off; you have lost almost nothing. What does not work is switching on six things at once. You will not know which one helps and which one gets in the way. Today, AI in support is a good assistant for agents and a poor replacement for them. Anyone who pitches it the other way around is selling you a problem. Last updated: September 27, 2026 ## How attendo handles it In attendo, marIA proposes and a person decides. It drafts replies the agent sends, classifies incoming email and transcribes and summarizes calls. It also answers questions about your data in read-only mode, and shows what it looked up. Every operation is logged with its cost, spending has a monthly cap and it can be turned off module by module. - [Artificial intelligence](https://attendo.me/en/artificial-intelligence) - [AI-Chat and DB Assistant](https://attendo.me/en/modules/ai-chat) - [Web chatbot](https://attendo.me/en/modules/web-chatbot) ## More on support and customer service ### When the shared inbox stops working A shared inbox is the spreadsheet of customer support: it works fine until it stops working. And by the time you notice, you have already lost things. 3 min read ### WhatsApp for customer service: how to get it right In Europe, Latin America and many other markets, customers already message companies on WhatsApp, whether the company decided to or not. The question is not whether to use it, but whether it is set up to work or still lives on someone’s phone. 4 min read Processes and compliance ### Which processes to automate first, and which to leave alone Automating the wrong process costs you twice: the time to build it and the time to undo it. Three simple questions separate what is worth automating now from what is better left alone. 4 min read [All blog articles](https://attendo.me/en/blog) ## Shall we look at it with your operation? Tell us how you work today and we will show you attendo with your own data. If it is not a fit, we will say so. - With your operation, not a generic demo - A real person from our team replies - No cold calls afterwards Would you rather talk first? - Phone [+34 910 053 530](tel:+34910053530) - Email [sales@attendo.me](mailto:sales@attendo.me) - Monday to Thursday 9:30 AM to 6:30 PM and Friday 9:30 AM to 2:30 PM (Spain time)