Back to blog
AI & AutomationSep 22, 20269 min read

What can an AI chat do on your website? Four layers, from knowing to handing over

An AI chat on your website can do exactly as much as you give it access to. Answering from your own texts, looking up orders, carrying out an action and handing over to a person in time: each layer needs different access. The question test shows which layer your site needs.

Een chatvenster op een webshop dat een antwoord opbouwt uit kennisbank en ordergegevens

An AI chat on your website can do exactly as much as you give it access to. The language model decides how smooth an answer sounds. What that answer contains depends on what the chat may read, look up and carry out. Two webshops using the same model can end up with a completely different product on their site.

So start with your own customer questions rather than a feature list. Every question needs a certain kind of access. That access falls into four layers.

Which four things can an AI chat do?

  1. Knowing. The chat answers from your texts: return terms, delivery times, warranty, payment methods. Example question: "Can I also collect my order?"
  2. Looking up. The chat retrieves data that differs per customer or per product. Think of an order status, stock or product specifications. Example question: "Where is order 10432?"
  3. Acting. The chat carries out something in another system. It changes a delivery address, cancels an order or registers a return. Example question: "Can the parcel still go to my work address?"
  4. Handing over. The chat recognises that a question belongs with a person and passes the conversation on with everything already said. Example question: "This is the second time my parcel has arrived damaged."

The layers build on each other. A chat that can look things up but doesn't know your return window helps the customer halfway. A chat that can act but doesn't know when to hand over is a risk.

What an AI chat can do = what it may read + what it may look up + what it may carry out + when it hands over.

How much can a chat do with only your own texts?

More than you might expect, as long as those texts are right. Questions about shipping costs, delivery times, returns and payment have a fixed answer. That answer usually already sits somewhere on your site. The chat brings it forward the moment a visitor asks, even when they phrase the question quite differently from your FAQ.

The weak spot is the source. On a webshop we scanned, the returns page stated a 100-day window. Elsewhere on the same site it said the withdrawal period was 30 days. Legally the two can coexist. Nowhere did the site explain how. A chat reading both texts then has to choose. If it picks wrong, you've promised something you didn't mean.

A good chat therefore says so when it doesn't know. A chat that gives a smooth answer despite doubt is more dangerous than no chat at all. The mistake only shows once a customer holds you to it. How to get that source in order is covered in the knowledge base as the foundation for AI answers.

Why "where is my order" needs a connection

A question about an order has no fixed answer. The answer differs per customer and per hour. Without a connection, a chat can only point elsewhere: to the tracking link in the confirmation email or to the contact form. The customer then has to take another step for a question they just asked.

With a connection, the chat asks for the order number, looks up the order and returns the status your system holds at that moment. Someone asking where their parcel is usually wants to know whether it arrives tomorrow and what to do otherwise. So mention the expected delivery day too, and what the customer can do once it has passed. More on that in reducing WISMO questions.

The same layer covers product questions. Is this item in stock? Does this filter fit my appliance? Does this size run small? With access to your product catalogue, the chat answers with the data your webshop itself uses. Without that access it guesses.

Only let the chat show order details once order number and email address belong together. An order number on its own is too easy to guess.

When may a chat carry out something itself?

Acting is where the most is to be gained and where the most risk sits. An address change the chat carries out itself saves an email back and forth. Nobody needs to log into the webshop for it either. A cancellation on the wrong order costs more than it saves.

So don't give a chat an independent right to an action before it has spent a while only proposing that action. Have a colleague approve every proposal and count how often they have to change something. If that number stays low, approval can come off for that one action. Refunds don't belong on that list for now. How to measure this is covered in measuring the edit rate and approval up front.

Where should a chat stop?

Some conversations belong with a person, however good the chat is. A complaint coming back for the second time. A question with a legal side to it. A customer who is angry and lets it show. There, a fast answer helps less than someone who can decide.

Handing over only works if the colleague receives the conversation with everything in it. If the customer has to tell their story again, the chat was a detour. Also decide up front which topics the chat stays away from. For price agreements or medical claims it then refers on straight away.

Outside opening hours nobody can take over. The chat should then say honestly when someone will be looking again, and record the question so it is ready the next morning.

What each layer needs

Knowing
your own texts, correct and not contradicting each other
Looking up
a connection to your webshop or order system
Acting
write access, first with approval per action
Handing over
someone reading along and a defined boundary

When does an AI chat add little?

A chat isn't an improvement for every site. In three situations it adds little:

  • You get few questions. With a handful of messages a week, a colleague answers them faster than you can set up a knowledge base.
  • Nearly every question needs judgement. A wholesaler that mostly writes custom quotes has few questions with a fixed answer.
  • Your policy isn't written down anywhere. If returns or delivery times are agreed case by case, the chat has nothing to read from. Writing those agreements down is then the first step, with or without a chat.

The question test: what can a chat do on your site?

Take the last fifty customer questions that came in by email, chat or phone. Mark for each one which layer it needs: knowing, looking up, acting or handing over.

  1. Count the knowing questions. A chat can take these on from day one, provided the answer on your site is right.
  2. Count the lookup questions. If they make up a large share, a chat without a connection to your webshop makes little sense.
  3. See which actions come up often. Those are the candidates for later, as proposals first.
  4. Read the handover questions separately. They decide where the chat's boundary should sit.

A site with mostly knowing questions can start tomorrow. A site with mostly lookup questions starts with the connection.

Is the first layer right on your site?

The knowing layer is as strong as the texts on your site. The Cuego scan reads your website the way a chat would. It shows which frequently asked questions have a complete answer, where information is missing and where pages contradict each other.

Scan your website

Cuego Chat

What the four layers look like in a system

  • Knowing: the AI agent answers from your own knowledge base and says so when it isn't sure
  • Looking up: connected to your webshop, it looks up the order and expected delivery during the conversation
  • Handing over: you read along live and take over a conversation with one click
  • Topics the agent stays away from go on a list you manage
  • In the first weeks the agent can be limited to suggestions you send or adjust
  • Acting is part of the full platform: an order action from the AI waits for a colleague's approval

Frequently asked questions

Yes, and the likelihood depends mostly on the source. A chat that only answers from your own texts and says when it doesn't know makes fewer mistakes than one that fills every gap with a general answer. Measure it by letting the chat only make suggestions for a few weeks and counting how often a colleague changes something.

Cuego

cuego.io

Your Cue to Go.

Everything around your customer. Together.

The Customer Contact Platform where conversations, customer data, knowledge, workflows, people and AI come together. Book a 30-minute demo and see it against your own situation.

30-minute demo · then we set it up together

Rather look for yourself first? Take the free website scan