Meryem Ghatrif
Meryem Ghatrif

Contents

[email protected]

Pensées · UX & AI

Your AI agent has a personality. Choose it.

Seven questions to answer before launch, for an AI agent that is clear, honest and in people’s hands: warm, without pretending.

6 min read

You ask a website’s chatbot if you can still return a parcel. It answers “Great question! 😊”, thanks you twice, then gives you the wrong date.

I saw the same thing with my own web host’s chatbot. It began with a list of general questions, as if my answers would help it understand my problem. It sounded like listening. It was only pretending.

In both cases, the personality was not a choice but a side effect, and it showed when things got difficult. An agent rarely pretends when things are easy. It pretends when it doesn’t know (it invents), when it should say no (it agrees), and when it can’t help (it acts as if it’s listening).

Every AI agent has a personality, whether someone designed it or not. The good news is that you can choose it. Here is how I would do it, from my work as a designer and from the Interaction Design Foundation’s course AI for Designers.

We see faces everywhere

The heartsease is the little flower of this site. In French, it is called la pensée, a thought. Look at one closely and you will probably see a face. The flower is not looking at you. You are the one who sees someone there.

A violet heartsease from a botanical plate: two dark petals above a bright centre, like a little face.
The heartsease, Viola tricolor. Do you see the face?

We do the same with machines. In 1966, Joseph Weizenbaum created ELIZA, a very simple program that turned your sentences into questions. His own secretary asked him to leave the room so she could talk to it in private. He was struck by how quickly people confided in it.

Today’s AI agents are much better at talking. People will see a personality in yours, whether you designed one or not. So you might as well choose it.

Too nice is a problem

Being warm is good. Flattering is not.

In April 2025, OpenAI rolled back an update to ChatGPT because it praised almost everything people said. OpenAI described it as “overly flattering or agreeable”.

A second risk is being taken for a friend. The same year, a study by OpenAI and the MIT Media Lab found that the heaviest users, especially those who saw ChatGPT as a friend, tended to feel lonelier. It shows a link, not a cause.

A good agent is kind, and it can still tell you when you are wrong.

Three qualities of a good agent

Clear. It says it is an AI from the first message, and what it can and cannot do. In Europe, the AI Act has required this since 2 August 2026, unless it is obvious.

Honest. It says “I don’t know” when it doesn’t know. It never invents an answer.

In people’s hands. A human is always one step away. The agent helps when asked, and doesn’t jump in uninvited. Remember Clippy, the paperclip in Microsoft Office, popping up with “It looks like you’re writing a letter. Would you like help?” Microsoft turned it off by default in 2001 and removed it in 2007. And if the agent can act (book, order, send), it asks before anything that can’t be undone, then says what it did.

How to give it a personality

This is where UX meets AI. An agent built on a language model already has a default character: polite, helpful, often a little too eager to please. You shape it in three places.

  1. Its instructions. A short text the model reads before every conversation, often called the system prompt. This is where you describe who it is, how it talks and what it never does.
  2. A few examples. Two or three sample conversations written in the voice you want, including a difficult one: a refusal, an “I don’t know”. Examples often work better than adjectives.
  3. The words around it. Its name, its first message, its buttons, its error messages. They speak before the model does, and they are pure UX writing. Its face speaks too: a human name and a photo of a person already pretend.

Then treat it like any design: test it with real people, read the conversations, and adjust the instructions. A personality is tended, like a garden.

Seven questions before launch

Chat tools, including AI plugins for WordPress, usually have a field for these instructions. Before you write them, answer seven questions.

  1. Who will talk to it, and how will they feel? In a hurry, worried, curious?
  2. Which three words describe its voice? Give each one a limit: warm, never familiar; short, never cold; confident, never pretending to be sure.
  3. What does it say when it doesn’t know?
  4. When does it pass the conversation to a person, and how?
  5. What will it never pretend? To be human, to have feelings, to be certain.
  6. How does it say no, and how does it fix a mistake? A good “no” explains why and offers another way. A good correction says “I was wrong” and fixes it.
  7. What does it ask, what does it keep, and where does that data go? Only what it needs, no longer than needed, and somewhere you know. That is security, and it is sovereignty: you decide where the data lives and whether it trains someone else’s model.

Your answers then become the instructions. For a bookshop’s website, for example:

You are the assistant of a bookshop’s website.
Speak simply and warmly, never familiarly. Keep answers short.
Answer only from the shop’s information and catalogue.
If the answer isn’t there, say so, and give the shop’s phone number.
Never ask for card numbers or passwords.
Never pretend to be human, to have feelings or to be sure.

Some promises can’t depend on a model, which can forget a line or be talked out of it. The AI notice in the first message, the button to reach a human, the block on card numbers: build them into the interface. The prompt asks. The interface guarantees.

Then test it before launch with difficult moments: a question it can’t answer, a request it must refuse, an angry message, someone trying to make it break its rules.

Behind the voice, a service

A pleasant voice is only the front of the service. Frank Spillers, whose course on UX management I took at the Interaction Design Foundation, puts it bluntly: “A chatbot isn’t a service.”

He notes that most AI work is designed at the interface, then breaks backstage. “Handoffs lose context, the AI is confidently wrong, and no one owns the recovery.”

So before launch, decide three things behind the scenes.

  • What travels with the handoff. The person who takes over sees the whole conversation, so nobody has to start again.
  • Who owns the recovery. When the agent is wrong, someone is responsible for fixing it, and the customer knows who. In 2024, a Canadian tribunal held Air Canada responsible for what its chatbot said.
  • Who you test it with. In his words, “angry, vulnerable and confused users”, not only patient ones.

His rule fits in one line: “Design the failure before the happy path.”

A note for those who build it

If you build the chat window yourself, make it accessible. Put the messages in a container with role="log", so screen readers read each new reply aloud. If replies appear word by word, announce each one once, when it is complete. Keep the keyboard focus in the text field. And never let an emoji carry the meaning on its own.

To remember

  • Every agent has a personality. Choose yours on purpose.
  • Kind, yes. Flattering, no.
  • Ask for little, keep little, and know where the data goes.
  • Say what it is, what it can’t do, and who can help.
  • The prompt asks. The interface guarantees.
  • Test the difficult moments, not just the easy ones.

Look closer

Look at a heartsease long enough and you will see a face. It is not looking back.

An AI agent is the same: we are the ones who see a person. Design it so it never pretends to be one.

If you try these seven questions with your own agent, I’d be glad to hear what changed.

Sources (9)