Agent UXNaming the agent

A named agent is a product. A generic assistant is a forgotten feature.

Q: Should the agent pretend to have feelings to seem friendly?

No. An agent that says it feels, cares or promises is performing an inner life it does not have, which is the most dangerous form of over-promising. You can have warmth, humour and a recognisable voice without claiming sentience. Friendliness comes from being genuinely useful and candid, not from manufactured emotion.

Give the agent a name, a role and a voice and you give the user something to form a relationship with, and a clear model of what it can do. Get the personality wrong and you over-promise capability. With a live demo.

See the live demo Agent UX

Published 19 June 2026
Observed convention
Live demo

(01) The problem

An empty chat box is a hard thing to use. It offers everything and suggests nothing, so the user has to invent both the request and the expectation of what might come back. Naming the agent solves that in one move.

Give it a name, a role and a consistent tone, and the text box becomes a character. Not a gimmick, a model. The user now knows roughly what it is for, what to ask, and what good looks like. The name does the quiet work of setting expectations that a blank cursor never could.

The name carries the role

The reason a name works is that it is never just a name. "Finn, your accountant" or "Ace, your property manager" bundles a role, a domain and a promise of competence into one word. The user reads all of it instantly and calibrates accordingly. That is the upside, and it is large.

It is also the risk. A name that implies a capability the agent does not have is a broken promise waiting to happen. The anthropomorphism that makes a persona engaging is the same force that makes users over-attribute competence and inner life to it. Personality dialled up too far reads as a guarantee the agent cannot keep.

The craft is a persona that is warm and specific but candid about where it stops. Over-promise personality and you over-promise capability. The agents users trust most are the ones with a clear role and the nerve to say "that is outside what I do".

(02) Live demo

The same request, to two agents

One is a faceless assistant that offers to help with anything. The other is Zero, a named ops lead that knows its job and its limits. Toggle between them.

AI Assistant

How can I help you today?

Can you sort out my overdue invoices and chase the late payers?

I’m an AI assistant and I’m here to help with a wide range of tasks. I can provide information and guidance. Could you tell me more about what you’d like to do?

A faceless feature. No role, no scope, no character. The user has no idea what it is actually for, so they get a vague offer to help with anything, which in practice means nothing. Nobody remembers this. Nobody comes back to it by name.

Note: Zero is p0stman’s own agent persona. Figures are illustrative.

(03) The anti-pattern

Over-personification: the tells

A persona can tip from helpful into misleading. Watch for these:

Claims of feeling or caring

An agent that says it "feels excited" or "really cares" performs an inner life it does not have, priming the user to over-trust its judgement.

A name that out-promises the product

"Your lawyer" on an agent that cannot give legal advice. The name writes a cheque the capability cannot cash.

Confidence in place of competence

Personality used to paper over gaps. A charming agent that bluffs is more dangerous than a plain one that admits it does not know.

A persona that shifts between surfaces

Bubbly in chat, robotic in voice, anonymous on video. The user cannot tell it is one agent, so the relationship never forms.

(04) The rules

What a good persona looks like

Six rules for a named agent that builds a relationship without writing cheques it can’t cash.

Give it a name, a role and a consistent toneA name turns a text box into something a user can form a relationship with. A role tells them what it is for. A consistent tone makes it recognisable across every surface it appears on.

Let the name set capability expectations, then meet themCalling it "your accountant" or "your ops lead" makes a promise about what it can do. The fastest way to break trust is to name a capability the agent does not actually have.

Be warm, but honest about the limitsThe craft is a persona with personality that is still candid about what it cannot do. A friendly agent that admits its edges is trusted more than a slick one that pretends it has none.

Do not fake emotion or sentienceAn agent that claims to "feel", "care" or "promise" is over-promising on the most dangerous axis. Personality is fine; manufactured inner life is anthropomorphism that sets the user up to over-trust.

One persona per product, consistent across channelsIf the agent is Zero in chat, it is Zero in voice and Zero on the video call. A persona that changes voice between surfaces reads as several half-built features, not one product.

Degrade gracefully, in characterWhen the agent cannot help, the persona should hand off cleanly rather than bluff. "That’s outside what I do, here’s who can" protects the relationship far better than a confident wrong answer.

(05) How to build it

How to build it

Write the persona down before you write the prompt. A short character document, name, role, domain, tone, and crucially the explicit list of what it does not do, becomes the stable core of the system prompt. The limits matter as much as the personality: they are what stop the agent improvising past its competence.

Tie the name to the role, not to a mood. "Zero, your ops lead" sets a useful expectation. A cute name with no role attached gives the user nothing to calibrate against. The persona should answer the question "what is this for?" in its first line.

Keep one persona across every surface. The same name, voice and character appear in chat, in voice and on the video call, sharing the underlying conversation state. A consistent agent across channels reads as one product; a different voice per surface reads as several unfinished ones.

Bake graceful handoff into the character. When a request falls outside the role, the agent should say so in its own voice and route the user onward, rather than bluffing. Honesty delivered in persona protects the relationship better than competence faked in persona ever could.

(06) Questions

Frequently asked questions

Is naming the agent a real pattern or just branding?

It is an observed convention with a real basis, not just a logo exercise. Giving an agent a name, a role and a consistent voice changes how users relate to it and what they expect of it, and the anthropomorphism trade-offs involved are well established in human-computer interaction research. The "name the agent as the product" framing is a practitioner pattern rather than an academic law, so we present it as p0stman’s synthesis backed by the wider HCI literature on anthropomorphism.

Why does a named agent beat a generic AI assistant?

Because a name carries a role, and a role carries expectations. "Zero, your ops lead" tells the user what it is for, so the request lands somewhere specific and the agent acts. A generic "AI assistant" offers to help with anything, which gives the user no model of what it actually does, so the interaction stays vague and forgettable. A defined persona is a product; an undefined one is a feature nobody remembers.

What is the risk of giving an agent a personality?

Anthropomorphism. The more human you make it feel, the more capability and the more inner life users project onto it. Over-promise personality and you implicitly over-promise competence, which is exactly where trust breaks when the agent gets something wrong. The discipline is a persona that is warm and characterful but honest about its limits, and that never fakes emotion or sentience.

Should the agent pretend to have feelings to seem friendly?

No. An agent that says it "feels", "cares" or "promises" is performing an inner life it does not have, and that is the most dangerous form of over-promising. You can have warmth, humour and a recognisable voice without claiming sentience. Friendliness comes from being genuinely useful and candid, not from manufactured emotion.

Does p0stman build named agents?

Every agent-first product we build is structured around a named agent positioned as a role rather than a chatbot: Finn the accountant, Ace the property manager, Mo the mortgage agent, Reena the chief people officer, and Zero across p0stman’s own touchpoints. The user talks to the agent and the agent does the job, with the persona kept consistent across chat, voice and video.

Take it with you

Don’t just read this. Put it to work.

The whole series is distilled into one Markdown file: every pattern, the do and don’t rules, and how well each is evidenced. Download it into your project, or paste the link into any chat with your agent and tell it to improve your agent UX. It’s free, no sign-up, no attribution required.

Paste this into your agent

Use these Agent UX principles to review and improve our agent's interface: https://p0stman.com/agent-ux/agent-ux-principles.md

Download the .md

Part of the Agent UX series

Finn, Ace, Mo, Reena, Zero: every product we build is structured around a named agent with a clear role and honest limits, consistent across chat, voice and video. If you want an agent users remember and trust, that is the job we do.

Back to the full Agent UX reference