
Key takeaways
- Most store conversations are routine – product questions before the purchase and order questions after it – and those are what AI handles best.
- Automate in three tiers: what AI resolves end to end, what it prepares for your team, and what stays human from the start.
- Customers get frustrated by AI that can’t answer or won’t let them reach a person – not by AI as such.
- Judge the result by how many questions were actually resolved, not by how many conversations never reached a human.
AI customer service: the full guide series
This guide is the overview. Each topic below has its own in-depth article:
| Topic | Guide |
|---|---|
| Automating support step by step | Customer service automation: what to automate first |
| Measuring the results | Deflection vs resolution rate · CSAT survey questions and benchmarks |
| Order questions | How AI answers “where is my order?” |
| Complaints | How to handle customer complaints |
| Evenings and weekends | After-hours customer support |
| The technology behind it | What is conversational AI? |
| Building it yourself | How to build an AI chatbot · AI chatbot cost: build vs buy |
| Outsourcing instead | Outsourcing customer support vs AI |
| Choosing a tool | Best AI chatbots for e-commerce · AskSpot comparisons |
What is conversational AI for customer service in e-commerce?
Conversational AI for customer service is software that understands a customer’s question in their own words and answers it from the store’s data – products, policies and orders – in a chat or by email. In e-commerce it usually covers two channels. The first is the chat on your website, where shoppers ask about products, sizes, delivery and their orders. The second is the support inbox – email, contact forms and marketplace messages – where most post-purchase questions land.
Customer service is one of the ten ways stores use AI today; the others are on the sales side – see AI in e-commerce: 10 use cases. For how the technology itself works – and how to choose a platform – read what is conversational AI.
Customer service chatbot vs AI customer service agent
Both answer customers automatically, but they work differently – and the difference decides what you can hand over.
| Customer service chatbot | AI customer service agent | |
|---|---|---|
| How it understands | Buttons, menus and keywords | The customer’s own words, in any language |
| Where answers come from | Scripted replies written in advance | Your catalogue, policies, knowledge base and orders |
| Order questions | Links to a tracking page | Verifies the customer and answers from the live order |
| When it can’t answer | Loops or shows a contact form | Hands over to your team with the conversation summarised |
Simple FAQ bots still have a place in a store with a handful of repeat questions. Once questions get specific – this order, this product, this size – you need an agent. The full comparison, including when a simple chatbot is enough: AI agent vs chatbot: what’s the difference for an online store?
What customers actually contact an online store about
Before deciding what to automate, look at what comes in. Across more than 240,000 conversations handled by AskSpot’s agents in 15 e-commerce categories, three patterns repeat:
up to 90%
of chats in a category are pre-purchase questions
AskSpot Internal Data · 48 stores
~1 in 4
support contacts is just an order question
AskSpot Internal Data
56%
of chats and emails arrive outside Mon–Fri 9–17
AskSpot Internal Data · 48 stores
Before the sale, shoppers mostly ask for help choosing: which model, which size, will it fit. After the sale, the same few questions dominate – where is my order, when will it arrive, how do I return it. And more than half of all conversations – chat and email together – come in when a typical support team isn’t working, as we showed in 56% of your shoppers arrive after hours. That mix is why AI customer service pays off in e-commerce: the bulk of the volume is repetitive, specific and urgent to the shopper, but rarely needs a judgement call.
Post-purchase experience: what customers need after they buy
The post-purchase experience is everything between “order placed” and “happy to buy again”: confirmation, shipping updates, delivery, returns and the occasional problem. It is also where most support work sits – on the median store running AskSpot’s Inbox Agent, two thirds of support emails come after the purchase.
| Stage | What the customer wants to know | Where AI helps |
|---|---|---|
| Order confirmed | That it went through, and what happens next | Confirms the order and the next steps from the order data |
| Shipped | Where it is and when it arrives | Gives the status and tracking in chat or email – see how AI answers “where is my order?” |
| Delivered | How to use, assemble or care for it | Answers from the product information in the knowledge base |
| Return or exchange | How, by when, and when the money comes back | Explains the rules and drafts the reply with the order details – see canned responses |
| Something went wrong | A fast, specific fix | Replies at once, looks up the order and hands the case to a person – see how to handle customer complaints |
None of these questions is hard on its own. What makes post-purchase support expensive is the volume, the order lookups and the hours – which is exactly the part AI can take over.
What it costs to keep doing it by hand
Answering everything by hand rarely shows up as one big cost. It leaks in four places:
- Your team’s day. About one support contact in four is an order question whose answer is already in your system – typed again, by hand, every time. More: how AI answers “where is my order?”.
- Sales before the purchase. On the median store, 74% of chats are pre-purchase. A product question answered tomorrow is usually a sale that went to someone else.
- The morning queue. Everything that arrives in the evening and at weekends waits, so the team starts every day already behind.
- Growth. Every new market, language or peak like Black Friday means more people – support that scales only with headcount.
Data behind these figures: AI chatbot statistics for e-commerce. Thinking of outsourcing instead? See what outsourcing customer support costs compared with AI.
What to automate and what to keep human
Sort your contact reasons into three tiers. The line between them is simple: can the answer be given from your data and rules, or does someone need to decide?
| AI resolves end to end | AI collects, your team decides | Keep human |
|---|---|---|
| Order status, carrier and delivery date | Order changes and cancellations | Damaged or missing goods |
| Delivery options, costs and times | Starting a return or exchange | Disputed refunds and chargebacks |
| Return and warranty policy | Complaints that need evidence (photos, order number) | Upset customers who ask for a person |
| Product questions, specs and comparisons | Custom orders and B2B or bulk enquiries | Health, safety or legal advice |
| Sizing, fit and compatibility | Invoice corrections | Anything outside your written policies |
The middle column is where most stores lose time today. An agent can’t approve a cancellation on its own, but it can gather the order number, the reason and everything else your team needs, and forward one complete request – so nobody has to write back three times for the basics. The order tracking and handling feature works exactly this way: status questions are answered from live order data, changes are collected and passed on. Ready-made replies for the simplest cases: 10 canned response templates. Six ready workflows – order status, returns, cancellations, invoices, courier problems and spam – are set out in customer service automation for online stores.
See AI customer service on your own store
Book a short demo – we’ll show the Agent answering product and order questions from your catalogue and orders.
How to roll out AI customer service without losing customers
Shoppers don’t dislike AI. They dislike being stuck: a bot that answers the wrong question, loops on the same three options or hides the way to a person. A careful rollout removes those risks before a single customer sees the agent:
- Ground it in your own data. Products from your catalogue, policies from your own pages and Q&A in the knowledge base – not the model’s general knowledge.
- Test before it goes live. Every reply is checked automatically against your catalogue and rules, specialists challenge it with the hardest questions, and your managers try it end to end on a private staging environment.
- Start where the risk is lowest. Launch after hours first, or with the inbox before the chat, and widen it once you’ve read the conversations. Later, add proactive messages that answer before the customer has to ask.
- Make the way to a person obvious. Write down which cases go to your team and let the agent hand over with the full conversation attached. Here is how AI chat and live chat hand over to each other.
- Speak the customer’s language. If you sell abroad, the agent should answer in the shopper’s language from the same knowledge – see multilingual support.
Measure resolution, not deflection
Many vendors report a “deflection rate”: the share of conversations that never reached a human. It sounds like success, but it also counts every customer who gave up and closed the chat. The number that matters is the resolution rate – how many questions were actually answered or handled. Read a sample of conversations every week, check what was handed over and why, and judge the agent on resolved questions, satisfied customers and sales, not on how quiet your inbox got. We compare the three metrics in detail in deflection rate vs containment vs resolution rate.
What stores get from AI customer service
Two published examples from stores running AskSpot on both the chat and the support inbox:
−90%
customer service costs
Morele.net · AskSpot Case Studies
90%
customer satisfaction level
Morele.net · AskSpot Case Studies
up to 77%
of support emails resolved end to end by AI
Meblobranie · AskSpot Case Studies
Morele.net, one of Poland’s largest electronics retailers, went from a 50-person support team to 5 with AI handling the chat, the inbox and marketplace messages. At Meblobranie, a garden furniture retailer, the inbox is mostly delivery logistics – dates, parcels, invoices – and routine tickets are answered end to end, while complaints and judgement calls go to the team (how to handle customer complaints). In both cases the people who stayed now handle the cases that need them.
Across all the stores in our data, results depend on the channel. On the median store, AI resolves 77% of chats and 33% of support emails – chat questions can usually be answered from the catalogue, while more emails need a decision. In our six published inbox case studies, the share of tickets resolved by AI ranges from 21% to 77%, depending on what each store’s queue is about. We break that down in customer service automation.
Start with your support inbox
The AI Inbox Agent answers support emails, contact forms and marketplace messages from your orders and policies, and hands the rest to your team, sorted. For questions on your storefront, the AI Chat Agent does the same in the chat.
How to choose AI customer service software
For an online store, check that a tool covers more than FAQs:
- Does it answer product questions from your catalogue, not only support questions?
- Can it look up live orders on your platform, and does it verify the customer first?
- Does it cover both channels – the website chat and the support inbox, including marketplaces?
- Can you set clear handover rules and test it before customers see it?
- Does it work in every language you sell in?
- Is it priced in a way that fits your volume – per conversation, per ticket, per resolution or per seat? See AskSpot pricing.
For side-by-side features and prices, see our comparison of the best AI chatbots for e-commerce and the head-to-head pages under AskSpot comparisons. AskSpot itself runs as two agents on one knowledge base: the AI Chat Agent on your site and the AI Inbox Agent in your helpdesk.
FAQ
What is a customer service chatbot?
A program that answers customers automatically in a chat window. Classic chatbots follow scripted buttons and keywords; newer AI chatbots understand free text. In an online store, the useful ones answer from the store’s catalogue, policies and orders and hand over to a person when needed.
What is an AI customer service agent?
An AI agent that handles customer conversations end to end: it understands the question, looks up the answer in the store’s data – including the customer’s order – takes the next step, such as collecting the details for a return, and passes the cases that need a decision to your team.
Will AI customer service annoy my customers?
Not if it answers correctly and lets them reach a person when they need one. Frustration comes from bots that guess, loop or hide the human option. An agent grounded in your catalogue, orders and policies, with clear handover rules, gives most customers a faster answer than they would get by email.
Can AI handle returns and refunds?
It can explain your return policy and collect everything needed to start a return – order number, items, reason – and forward one complete request to your team. Approving refunds and handling disputes should stay with people.
Will AI replace my customer service team?
It takes over the repetitive questions, so a smaller team can focus on the cases that need judgement – complaints, exceptions, important customers. Stores usually keep people for those and for reviewing what the AI handles.
How much does AI customer service cost for an online store?
Most tools charge per conversation, ticket or resolution rather than per seat. AskSpot’s Chat Agent starts at €250 a month for up to 1,250 conversations, and the optional Inbox Agent adds €120 a month plus a small fee per ticket, with no setup fee – see pricing.
Does AI customer service work in other languages?
Yes. Modern agents answer in the customer’s language from the same knowledge base. AskSpot supports more than 200 languages, so one setup can serve every market you sell in.
What is the post-purchase experience in e-commerce?
Everything a customer goes through after placing an order: the confirmation, shipping updates, delivery, using the product, returns or exchanges, and any problems along the way. Most of an online store’s support questions come from this stage – order status, returns and complaints.
What is AI customer support?
AI customer support means using AI to answer and handle customer questions – in the website chat, by email and in marketplace messages. In an online store it covers order status, delivery, returns and product questions, with an AI agent resolving routine cases and handing the rest to your team.
What is the best AI customer service software for e-commerce?
The one that answers from your catalogue and live orders, covers both the chat and the support inbox, works in your customers’ languages and lets you test it before launch. We compare the main tools side by side in best AI chatbots for e-commerce and on our comparison pages.









