Taste Engineering · 11 / 12

Feeding References to AI

Once you can see what's good, the next step is making AI know it too. This lesson covers three ways to feed references into the chat: reference images, style descriptions, and design variables—with prompt templates ready to copy.

Reference imageExperience attributesStyle descriptionDesign variablesPrompt templates
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.