Skip to content
by Oussama Bougnouch

AI guide for UX & product designers

Everyone is handing you rotten AI advice. This is the one worth taking.

Eleven short chapters on what AI is really doing under the hood, written by a designer who ships with it. About an hour to read.

From the book

From chapter 2
The model does not know when it does not know. Confidence tells you nothing about correctness.

on why AI invents sources in the tone it uses for facts

From chapter 5
AI analyzes the problem you hand it. It will never ask whether that problem should exist in the first place.

on the one level of listening a machine cannot reach

01Highlights

Five lines from the book

  1. Ch. 1

    The model is not answering your question; it is generating text shaped like an answer to your question.

  2. Ch. 3

    The model can only work with what is currently in front of it. Deciding what goes into that window is your actual craft.

  3. Ch. 4

    The model is only as effective as the data placed before it. Most of your impact is decided before you even open the tool.

  4. Ch. 6

    Treat AI like an intern with a photographic memory and zero personal stake in the outcome. Brief it accordingly.

  5. Ch. 9

    Jeff had tools; Steve had a process. Build the strategy before you buy the gear.

02Outcomes

What you will be able to do by the end

Not theory. Things you can use on your next project, this week.

  1. 01

    Understand the single thing a model is doing every time it answers you, and watch every strange result you have ever seen suddenly make sense.

    Ch. 1
  2. 02

    Spot the confident invention, and learn the one habit that catches it every time.

    Ch. 2
  3. 03

    Know why what you paste in matters far more than how you word the request.

    Ch. 3
  4. 04

    Climb the data food chain that quietly decides how senior your work looks, before you ever open Figma.

    Ch. 4
  5. 05

    Turn a pile nobody has read into a roadmap. Tickets, reviews, cancellation reasons, thousands of them, in days.

    Ch. 4
  6. 06

    Reach the one level of listening to a user that AI cannot get to.

    Ch. 5
  7. 07

    Avoid the four places AI quietly ruins design work: generated screens, critique, microcopy and accessibility.

    Ch. 7
  8. 08

    Build the verification habit that came out of the night my own agent told me it had finished 113 files. It had finished 53.

    Ch. 8
  9. 09

    Say out loud which parts of your job are safe, and why.

    Ch. 6 & 9
  10. 10

    Run a model on your own machine when the data cannot leave the building.

    Ch. 10 & 11

03The letter

Why I wrote it

I spent fifteen years getting good at something, then watched everyone announce it was over.

You know the posts. Designers are finished. Learn to prompt or get replaced. Usually attached to a course.

I did not want to argue with it or ignore it. I wanted to know if it was true, so I did what we do with any unfamiliar system: I opened it up and looked at how it works.

What I found was not what either camp is selling. Machines really did get fast at the surface: the layout, the first draft, the tidy summary. But they did not get good at the part underneath. They cannot tell which of fifteen findings matters. They cannot know your users are pharmacists working under time pressure with gloves on. They cannot sit in a room and say the feature should not be built at all.

That part is what you have been quietly building for years. You have just never had to name it, because nothing was competing with you at the surface.

This book helps you name it. Plain language, real mechanics, and my own failures included, because the failures are where the useful rules come from.

Oussama

04Contents

The eleven chapters

Four parts. Read them in order the first time through.

Signal vs Noise Oussama Bougnouch

Contents

  1. Before we start page 3
  2. Part 1 How it thinks page 7
  3. 01 It just predicts the next word page 8
  4. 02 Why it lies to your face page 11
  5. 03 What it can actually see page 13
  6. Part 2 How you work with it page 16
  7. 04 Garbage in, garbage out page 17
  8. 05 Listening is a skill (and AI doesn’t have it) page 19
  9. 06 What it’s great at, what it’s terrible at page 21
  10. 07 Pointing AI at the design itself page 23
  11. Part 3 Why it fails and how you plan around it page 25
  12. 08 The agent that lied to me page 26
  13. 09 Two architects in the desert page 29
  14. Part 4 Going independent page 32
  15. 10 Why you would want your own setup page 33
  16. 11 Running local AI: the practical guide page 35
  17. Conclusion: where this leaves you page 37
6

Free PDF · 11 chapters · About an hour

Read it in an hour. Keep the parts that change how you work.

05Readers

What readers say

Real quotes only, from people who have read it.

No reviews yet

Inventing praise would be exactly the failure chapter 2 is about, so this space stays empty until real readers fill it. Read the book, then be the first to say what you think.

Signal vs Noise

Write a review

Every review is read before it goes on the page. Nothing is edited except typos.

06Proof

Why listen to me

Three things I can point at, rather than three things I can claim.

10,800
Support tickets analysed with AI on one project, then validated in a workshop with more than twenty real users before a single screen was redesigned.
113 vs 53
My own agent reported 113 files created. There were 53. The full story is in the book, because it produced the rule I now apply to everything.
15 years
Product and UX design, including work with teams at CHANEL, AT&T, HelloFresh and Fnac.

07Fit

Who it is for

Read it if

  • You design products and the AI conversation has started to feel personal.
  • You have used the tools and got answers that looked right and were not.
  • You would rather understand the machine than memorise tricks for it.
  • You want one honest hour instead of forty hours of hype.

Skip it if

  • You want prompt templates to copy and paste. There are none in here.
  • You are an ML engineer. You already know the first three chapters.
  • You want to be told everything is fine. Some of it is not, and I say so.

08Author

Who wrote it

Oussama Bougnouch

Oussama Bougnouch, product and UX designer, fifteen years.

I have built design systems, research operations and production interfaces for teams at CHANEL, AT&T, HelloFresh and Fnac. These days I build AI systems for design work: local models, agents, and the instruction files that keep them honest.

I publish what breaks alongside what works. I wrote this book because the advice designers were getting was either panic or cheerleading, and neither one tells you what to do on Monday morning.

09FAQ

Questions people ask first

Is it really free?

Yes. No card, no shipping fee, no trial, nothing hidden three pages in. You give an email address and the book arrives as a PDF.

Do I need to know how to code?

No. If you can read a Figma file you can read this. The single technical chapter sits at the very end on purpose, and you can skip it entirely.

I use ChatGPT every day. Will this be too basic?

The first three chapters will be partly familiar. Chapters four to eight are where daily users tend to find the gaps, particularly around what to feed it and how to check what comes back.

How long does it take to read?

About an hour end to end. Chapter four takes ten minutes on its own and is the one that changes how you work.

What happens to my email address?

You get the book, then roughly one email a week about using AI in real design work. Never shared, never sold, one click to leave.

An hour from now you could stop wondering where you stand.