Special Topic · Taste Engineering: Make the Output Worth Keeping

Feeding References to AI

Describing style by mouth alone is inefficient. When to use reference images, style descriptions, or design variables — plus templates — so AI ships from your reference library

THE QUESTION THIS PAGE ANSWERS

ANSWER FIRST

What is the key idea behind “Feeding References to AI”?

Describing style by mouth alone is inefficient. When to use reference images, style descriptions, or design variables — plus templates — so AI ships from your reference library

DECISION RULE

Turn taste into a behavior the product can repeat. The useful outcome is not a nice opinion. It is a visible rule, a small example, and a way to tell when the experience falls below the bar.

TRY NEXT

Capture one before-and-after example that shows the quality bar without extra explanation.

WATCH FOR

Polish that improves the surface while leaving the user's uncertainty untouched.

Admit it first: adjectives never reach the AI

"A bit warmer, a bit more premium"—say it ten times, nine warp inside the model. Adjectives take two translations: you compress feeling into words, the model expands words into pictures; both ends lose fidelity. Feed references straight to AI—least loss, one shot.

Three postures for feeding references—each covers a stretch. Pick from the table:

MethodWhat you giveBest forWeak spot
Reference image1–3 reference imagesOverall vibe, composition, style transferEasy to copy layout too
Style descriptionA spec paragraph: density, primary, radiusStyles you can state as rulesVibe you can't spell out stays unwritten
Design variablesToken list: primary / radius / type / spacingHaving AI write UI codeLocks style, not layout or copy
Try it · Scenario match: three needs, one feed each
Have AI redraw my event poster and keep brand vibe Single choice
AReference image: attach past posters so it learns the vibe
BStyle description: write a "premium and grand" blurb
CDesign variables: hand over a CSS variable list
Make Cursor's admin pages feel like Linear Single choice
AReference image: screenshot a few Linear screens
BStyle description: write "as clean as Linear"
CDesign variables: token list for primary, radius, type, spacing
Make AI's detail page drop the AI look—but I can't name the style Single choice
AReference image only: give it one detail page you like
BReference + style description: image sets vibe, text fences rules
CRetry until you luck into something that looks right
Style description needs a base: pick three adjectives for the product first

You don't invent style descriptions from scratch—there's a method. About Face 4, Chapter 17, records Cooper's practice: experience attributes. Before designing, pick 3–5 adjectives with the client that describe product vibe and brand promise—"clean, restrained, trustworthy." Once set, those words referee every visual call: when unsure, ask whether the words would approve.

Adjectives are allowed to fight. The book says "safe" and "flexible" can both sit at the table—keep that tension: where two words clash is exactly what early style drafts should answer first.

Moved to feeding AI, it fits flush: pin the vibe with adjectives, then translate each into a concrete spec. Adjectives alone, AI reads the average; finish the translation step and the style description is done. The workbench below does that translation.

Try it · Experience-attributes workbench
Experience-attributes workbench Pick 3 words
Think of your product, pick 3 adjectives from the bank—spec snippets generate on the spot

          
Duel · Same adjectives, two ways to feed

Brief: home for a budgeting app, vibe locked as "clean, restrained, trustworthy." Version A sends the three words as-is; B runs the workbench first, translates word by word into specs, then sends. Tap the one you think is better.

Budgeting app home Tap the better version
A · Adjectives as-is
qingzhang.app/preview-a
Simple budgeting you can trust
Clean · Restrained · Pro · Trustworthy
Get startedLearn more
Smart categories
Secure encryption
Multi-device sync
B · Translate to specs, then send
qingzhang.app/preview-b
October spend
¥3,482
¥217 less than last month; dining is 40%
Add expenseSee details
Month budget¥5,000
Still free¥1,518
Tool · Prompt template generator

Each feed method gets a ready prompt. Pick a method, copy, swap the placeholders, send. For style description, drop the workbench output straight into the body.

Prompt template generator Copyable

        
A variable list is the standard you set for AI

The third method deserves its own line. Tear a reference into design tokens—primary, radius, type, spacing each become a variable—and what you hand over is more than a reference: it's an interface standard.

Why are standards valuable? About Face 4, Chapter 17, cites Nielsen: a unified interface standard helps users learn faster and err less, because experience in one place predicts behavior elsewhere; for the team, ready decisions skip round after round of debate. The same ledger holds for AI: once the token list is in, every generation lands on the same standard—ten revisions won't drift, and you have a yardstick at review.

Standards earn their keep through predictability: predictable behavior means faster learning, fewer errors. Adapted from Nielsen, as retold in About Face 4, Chapter 17.

The same chapter says the hard part first: follow the standard unless you have a strong alternative. Breaking is allowed—reasons must be hard. That rule fits you and AI alike. One last duel settles this lesson's ledger on the spot.

Duel · Same brief, two inputs

Brief: brand page for a bakery studio. A's input is only "a bit warm, a bit premium"; B brings a reference image and a variable list. Tap the better version.

Bakery studio brand page Tap the better version
A · Mouth only: "warm, premium"
tianyu-bakery.cn
Opening deal
Welcome to Sweet Isle Bakery
Quality · Craft · Warm · Premium
Buy nowLearn moreContact us
New arrivalsMember perksLimited discount
In-store 10% off; ¥10 more off over ¥88
B · Reference image + variable list
tianyu-bakery.cn
Sweet Isle Bakery
Handmade loaves—forty a day
Stone-oven fresh; when it's gone, it's gone
Book a visitThis week's menu
Oven onWed–Sun 10:00
SignatureWalnut whole wheat · Sea-salt croissant
Address12 Warehouse St, Old Town
Key Takeaways

Adjectives warp; references don't. Stuff images, spec text, and variable lists straight into the chat—least loss.

Three feeds, three stretches: Reference images cover vibe, style descriptions cover rules, design variables cover code. Combine if you want—just know who owns what.

Style description has a method: Pick 3 adjectives to pin the vibe (experience attributes), then translate word by word into specs. Words referee; specs execute.

A token list sets the standard for AI: Value is predictability—every generation lands on the same variables, drafts don't drift, review has a yardstick.

Mediocre output? Check the input first. Adjectives alone land on the average; swap in references and variables and the same model changes face at once.

Source: Original to Xiaoshan Academy's Taste Engineering series; some design principles adapted from About Face 4, Chapter 17 (Alan Cooper et al.); experience attributes and standards discussion from the same chapter.

Turn the feeling in “Admit it first: adjectives never reach the AI” into a judgment

“"A bit warmer, a bit more premium"—say it ten times, nine warp inside the model.” points out that AI has lowered the bar for making something usable. The skill readers need is noticing what is wrong and turning that feeling into an actionable requirement.

Watch the user's next action, not just the surface

Turn “Three postures for feeding references—each covers a stretch.” into observable questions: does the user know what happened, what to do next, and how to recover from an empty or failed state? Does the hierarchy make the important information visible first?

Pretty is not the same as usable

Apply “Mediocre output?” to a second screen or flow. Record one moment of hesitation and the user action after the change; observable behavior is stronger evidence than polish alone.

From “Admit it first: adjectives never reach the AI” to “Try it · Scenario match: three needs, one feed each”

“Admit it first: adjectives never reach the AI” grounds the problem in “"A bit warmer, a bit more premium"—say it ten times, nine warp inside the model. Adjectives take two translations: you compress feeling into words, the model expands words into pictures; both ends lose fidelity…”. “Try it · Scenario match: three needs, one feed each” then moves it toward “Have AI redraw my event poster and keep brand vibe Single choice A Reference image: attach past posters so it learns the vibe B Style description: write a "premium and grand" blurb C Design variables: hand over…”. Together, they show that the lesson is not just a conclusion to remember, but a claim with conditions.

Carry the judgment into the next situation

For experience work, turn abstract impressions into user actions: did the person understand the state, find the next step, recover from an error, and want to continue?

  • “Admit it first: adjectives never reach the AI”: "A bit warmer, a bit more premium"—say it ten times, nine warp inside the model. Adjectives take two translations: you compress feeling into words, the model expands words into pictures; both ends lose fidelity…
  • “Try it · Scenario match: three needs, one feed each”: Have AI redraw my event poster and keep brand vibe Single choice A Reference image: attach past posters so it learns the vibe B Style description: write a "premium and grand" blurb C Design variables: hand over…
  • “The closing point”: The third method deserves its own line. Tear a reference into design tokens—primary, radius, type, spacing each become a variable—and what you hand over is more than a reference: it's an interface standard

The final “The closing point” brings the discussion to “The third method deserves its own line. Tear a reference into design tokens—primary, radius, type, spacing each become a variable—and what you hand over is more than a reference: it's an interface standard ”. The useful thing to carry forward is knowing which judgments must be revisited when input, scale, or risk changes.

Mark as learned Your reading progress updates automatically
← PreviousNext →

Keep reading

The next useful article in the thread.

ARTICLE DISCUSSION

Leave one useful thought here.

Keep the idea that clicked, the question that stayed open, or a small note for the next learner.

Discussing Feeding References to AI Taste Engineering: Make the Output Worth Keeping
3discussionsArticle discussion · synced with the Circle
View in the learning circle
AM
Asha MorganContent editor
INSIGHTField note

I turned one judgment from this article into a small experiment I could run today. Knowing what to observe next is more useful than simply remembering the conclusion.

ARTICLE DISCUSSION7 helpful
LH
Lin HarperIndie developer
INSIGHTInsight

After reading this, I first looked for the conditions behind the idea instead of copying the method into a project. That order made the later trade-offs much clearer.

ARTICLE DISCUSSION5 helpful
KM
Kiki MooreProduct operations
QUESTIONQuestion

When this judgment reaches real work, which constraint should be added first? I am curious which step matters most between reading and the first practical attempt.

ARTICLE DISCUSSION4 helpful