All work

A reference library Claude scores, and a visual brief that finds what a client actually likes, not just what they say.

Two image cards standing side by side over a phone. The left card holds one open circle and is labelled quiet; the right card has the same layout with a filled, ringed circle and a block, labelled loud. One thing changes, the rest stays the same. On the phone the client picks which feels closer, about 20 pairs in 8 minutes. This Quiet That Loud One thing changes The rest stays the same Which feels closer? About 20 pairs, 8 minutes
For
Amplifier, the small design studio I’m a partner in
My role
Research, design and build
When
Rebuilt October to November 2026 (first version 2025)
Used by
Our three designers; clients on their phones, through a private link or the studio’s site
Status
Brief and library in testing with the studio; the site in progress with Francis
Built with
Next.js 16, Supabase (Postgres, row-level security, pgvector), Claude Sonnet and the Message Batches API, Voyage multimodal embeddings, a Chrome extension
CH_01

The problem

“Minimal” can turn out to mean calm rather than empty.

Clients usually know what they like when they see it, but the words they use for it can point somewhere else. The first meeting is where that gets untangled, and we were walking in with a few adjectives and a guess.

The 2025 version of Amplifier tagged our reference library and turned a client questionnaire into keywords. It worked, but creating and maintaining tags was a chore, so nobody kept them up, and the brief could only match the words a client typed. In October 2026 I rebuilt it from scratch around two ideas: describe the library with definitions instead of tags, and learn what a client likes from what they choose.

For a client to finish the brief on a phone
~8 min
This-or-that pairs, each aimed at what it’s least sure of
~20
Right side of each dimension, with simulated clients
91–95%
Before a client’s private link expires
30 days
Prep page for a test brief, a tea shop brand identity: a one-paragraph headline, then What they’re asking for, with notes on the project, on Amul as a named reference, on their character and on what their picks add, and questions for the meeting.
The prep page for a test brief opens with what they’re asking for. The client and project are made up.
CH_02

Which feels closer?

Each pair changes one thing and keeps the rest the same.

Which feels closer?

A small version of the brief. Say what you want in words, then pick between eight pairs. The next pair goes after whatever it’s least sure about. The images here are shapes drawn from numbers; the real brief uses the studio’s library.

First, in words: what should it feel like? Pick a side where you have a view.

CH_03

The brief

About eight minutes on a phone. No account, no app.

One brief, link to first meeting: pick a station

01A link, or the site

Who
The studio, or a visitor to the studio’s site
Before
A client questionnaire, turned into keywords.
Now
The studio sends a private link that expires after 30 days, or a visitor starts one from the site with a name, email and project type. No account, no app.
Where
The client’s phone

02Welcome and one question

Who
The client
Before
A few adjectives in a questionnaire.
Now
A short personal note, then one question in words: what are you making, and who is it for? The answer picks the images: about three quarters are the library images closest to it, the rest open to anything.
Where
The client’s phone

03Warm-up

Who
The client
Before
The brief could only match the words a client typed.
Now
Twelve images to keep or skip. Answers save in the background, so swipes feel instant.
Where
The client’s phone

04This or that

Who
The client
Before
Keywords matched against tags nobody kept up.
Now
About twenty pairs, each aimed at the dimension the system is least sure about, using two images close on everything else. A few come back with the sides swapped to check the answer holds.
Where
The client’s phone

05Early read

Who
The studio
Before
Keywords from the questionnaire.
Now
As soon as the client finishes: where each choice leans, how unsure it still is, and how many repeated pairs got the same answer.
Where
The studio’s brief page

06First meeting

Who
The studio and the client
Before
A few adjectives and a guess.
Now
The prep page, screen-shared: what they’re asking for, where their words and picks really differ with a question to ask, the taste profile, hesitations and a starter moodboard.
Where
The first meeting

Now and then a quick “what caught your eye?” offers a few chips to tap, and the remaining questions in words come at the end, then a thank-you with the meeting date. I tested the engine with simulated clients before any real one saw it. With a library of 100+ images, it picks the right side of each dimension 91–95% of the time.

Brief on a phone: “Hi Maya.” with a short welcome and a note from the studio, and a Start button.Brief on a phone: “What are you making, and who is it for?” with the client’s answer typed in.Brief on a phone: “Keep or skip?”, warm-up image 4 of 12, with Skip and Keep buttons.
Brief page in the studio: the private link (blurred), dates, and an early read showing where each dimension leans with a band for how unsure it is, and “3 of 3 repeated pairs got the same answer”.
The studio sees an early read as soon as the client finishes: where each choice leans, how unsure it still is, and how many repeated pairs got the same answer.
CH_04

The prep page

Read the client as a whole, then compare looks.

When the client finishes, the prep page builds itself. It’s made to be screen-shared in the first meeting.

  • What they’re asking for comes first: a summary of the whole brief, notes on the project, on what a reference they name stands for (as something to check), on their character and on how their picks fit, and questions for the meeting. Editable like the rest.
  • Said against showed, on every dimension of the rubric. Their words go on a visual scale only when they’re about the look, so feeling-words like “warm” or “quiet” stay off it, and placements Claude isn’t fairly sure of are left out.
  • Differences, not just gaps. Each dimension says whether words and picks agree, differ, or differ in a way their story explains. Only real differences are listed, each with a question to ask, and ones resting on few pairs are marked “Early hint”.
  • Hesitations: their slowest picks, and any answer that changed when a pair came back swapped.
  • A starter moodboard from their picks and close matches. “Copy as layers” pastes it into Figma as separate layers, and images dropped onto the board go into the library too.
Taste profile: on each dimension a ring for what the client said and a square for what they chose, a line where the gap is worth asking about, and how sure each placement is; below, what they consistently chose and passed over, with examples.
Said against showed, with the gaps worth asking about.
Hesitations listing the slowest pairs and a changed answer, and a starter moodboard with Copy as layers, Download images and Add from library.
Where they hesitated, and a moodboard ready to paste into Figma.
CH_05

The library

Instead of tags, the studio writes a rubric.

Up to ten dimensions, each a spectrum between two ends, and each end described by what you can see, like elements, colour, line and texture. Claude scores every image on every dimension.

  • Anchors: library images pinned as examples of an end. Claude sees them every time it scores.
  • Corrections are recorded and fed back into scoring. A designer’s edits are kept when an image is rescored, and changing a definition marks the old scores stale and offers a rescore.
  • Embeddings (Voyage multimodal, stored in Postgres with pgvector) power “More like this” and catch near-duplicates on upload, alongside exact hash matching.
  • Coverage shows which ends of which dimensions need more images, because the brief needs every end filled.
  • Pinterest boards come in whole: the Chrome extension reads a board in the designer’s own browser and sends each pin, labelled with who imported it and the board’s name.
  • Scoring in the background through Anthropic’s Message Batches API, at half price and usually within the hour, with a count like “Scoring 0 of 79”, a bar and about how long is left.
Library grid with one image open: Claude’s description, its medium, and eight scores on spectrums such as Minimal to Rich and Quiet to Loud.
Every image scored on every dimension. Designer edits survive a rescore.
Rubric settings: each dimension with a left and right end, each end described by what you can see, slots for anchor images, and a count of corrections.
The rubric: each end defined by what you can see.
More like this: twenty library images ordered by similarity to the selected one.
“More like this”, closest first, from image embeddings.
Library Review screen, all caught up, showing Scoring 0 of 79 with a progress bar and about 5 minutes left, and the details open: 79 images with Claude, sent a minute ago, in batches of up to 100 at half price.
Imports score in the background, with progress you can see.
Coverage: histograms of how approved images spread across each dimension, with thin ends flagged, and a count of images per medium.
Coverage: which ends need more images.

Library images are saved references by other designers, shown as they appear inside the studio’s tool.

CH_06

The studio site

In progress: not launched yet

One app now runs the studio’s site, the brief and the library.

The studio’s new public site is being built in collaboration with Francis, the designer, on top of Amplifier. Projects are written in Studio › Portfolio: details, images and video, and a case study made of text and media blocks, with a French version beside each one.

Every page can also start a brief. A visitor gives their name, email and project type and goes straight into their own visual brief, marked “From the site” in the studio. Until launch, amplifier.studio still serves the old site.

Start a brief on the studio site: a short intro (a few questions and a run of images, about 8 minutes, no right or wrong answers), then fields for name, email and what they’re making, and a Start my brief button.
Starting a brief from the site.
CH_07

What changed after feedback

Using it with the studio changed what the report reads, and how the library keeps up.

  1. 22 Oct

    The studio takes on any client, not only artists.

    Project types for brand identity, website, packaging, signage, campaigns, releases and events. A brief’s images now start from the client’s own answer to “What are you making?”, and whole Pinterest boards can be imported.

  2. 1 Nov

    Imports slowed the whole studio down.

    One scoring run at a time, time limits on every call, and batches that carry links instead of image files. The library shows where scoring is up to, and an idle studio leaves the database alone.

  3. 1 Nov

    “Every project starts with a visual brief,” so the site needed a way in.

    A start form on the site, with limits instead of an account.

  4. 2 Nov

    The report only placed the client’s words on the visual rubric and called the differences contradictions.

    It now reads the whole brief first, keeps feeling-words off the visual scales, leaves out placements Claude isn’t fairly sure of, and only lists differences their story doesn’t explain.

  5. 3 Nov

    Some imported images sat at “scoring” forever.

    Images whose adding was cut off part-way are finished automatically, and the ones that can’t be are listed in Review with Retry and Remove.

CH_08

Decisions

Definitions instead of a tag vocabulary

The first version’s tags were never maintained because creating them was a chore. A rubric is a handful of definitions the studio writes once. Claude does the scoring, and anchors and corrections keep it close to the studio’s eye.

A deterministic engine, tested before any client

Choosing the next pair, tracking how sure it is and checking consistency are plain code, not a model. That meant I could run simulated clients through it and know it worked before a real client ever saw it.

Read the whole client, then compare looks

A difference between words and picks is only listed when the words are about the look, Claude is fairly sure where they sit, and their story doesn’t explain it. Ones resting on few pairs are marked “Early hint”, so a thin signal never reads as a finding.

Half-price scoring that can’t pile up

Imports are scored through Anthropic’s Message Batches API, with one run per studio at a time, time limits on every call, and batches recorded before they’re sent, so nothing is paid for twice. Embeddings come from thumbnails, in batches, so cost stays low as the library grows.

Limits instead of accounts

Clients never sign up. The studio sends a private link that expires after 30 days, and the site’s start form is checked on every request instead: two briefs a day per visitor (counted by a one-way hash, the address never stored), one open brief per email, twenty a day across the site, plus a hidden field and a timing check for bots.

CH_09

Where it is now

Status
Brief and library in testing with the studio using test briefs; the site in progress with Francis
Tested
Right side of each dimension 91–95% of the time, with simulated clients and 100+ images
Next
The first real client briefs, and launching the site
CH_10

Reflection

The first version taught me that a tag vocabulary nobody maintains is worse than none. The rebuild puts the studio’s effort in the one place it pays off, writing definitions, and leaves the repetitive scoring to Claude, kept honest by anchors, corrections and an engine I could test before anyone used it.