Gautham Palanisamy
WORK ABOUT CONTACT CV ↓
← ALL WORK
02 · KUSHALS FASHION JEWELLERY · 2026 · AI TOOLING

imaGenie

The creative team was waiting weeks for product imagery. I wrote the PRD, designed the tool, prototyped it myself, and shipped it with two engineers — the first thing I've owned from problem statement to production.

MY ROLE
PRD, product design, working prototype
TEAM
2 engineers · creative team as users
STATUS
In production, iterating
WHY IT MATTERS
Designed and built by a designer, not specced and thrown over
[ HERO — IMAGENIE GENERATION VIEW, FULL BLEED ]
01 / THE PROBLEM

Every campaign needed imagery. Every image needed a shoot.

A jewellery catalogue turns over constantly, and the creative team was the constraint on everything downstream — campaign pages, ads, app banners, category art. A lifestyle image meant scheduling a shoot, which meant a two-to-three week lead time for something that would run for four days.

Generic AI image tools were already being used unofficially, and the output was unusable: the product came out wrong. Stones in the wrong cut, clasps invented, gold that didn't match the actual SKU. Nobody could ship it, so everyone went back to waiting.

02 / THE INSIGHT

The product is not negotiable. Everything around it is.

Watching the creative team work, the pattern was obvious: they never wanted the AI to invent the jewellery. They wanted to keep the real product photograph exactly as shot and change the world around it — a model, a setting, a season, a mood.

So imaGenie isn't a prompt box. You start from a catalogue SKU, and the product pixels are treated as fixed. The generation happens around them. That single constraint is what made the output shippable, and it came from an hour of watching rather than a feature request.

Generic tools failed because they gave too much freedom. The design decision was deciding what the user isn't allowed to change.
03 / THE TOOL

Four steps, and the third one is where the craft is

The whole flow is designed so a creative who has never written a prompt gets a usable result on the first attempt, and a good one by the third.

STEP 01
Pick the SKU
Pulled live from the catalogue with its master shot. No uploads, no wrong-product risk.
STEP 02
Choose the scene
Curated presets — festive, editorial, studio, on-model, seasonal — instead of a blank prompt field.
STEP 03
Review the variants
Four at a time, each flagged for product fidelity. Rejecting is one tap and it teaches the preset.
STEP 04
Export to the queue
Straight into the asset library at campaign crops, tagged by SKU and campaign.
[ SCENE PRESET PICKER ]
[ VARIANT REVIEW — FIDELITY FLAGS ]
04 / BUILDING IT

I stopped handing over specs and started handing over something that ran

I don't have an engineering background. What I have now is AI-assisted tooling, which was enough to build a working prototype wired to a real generation API — not a clickable mock, an actual thing that produced actual images and failed in actual ways.

That changed the conversation with engineering completely. Instead of debating whether a fidelity flag was feasible, we looked at my version doing it badly and talked about how to do it properly. Scope arguments got shorter because the disagreements were about behaviour we could both see.

It also changed what I caught. Generation latency made my first design wrong — a four-up grid that appears all at once is a very different experience when it takes eleven seconds. I only found that because I sat waiting for my own prototype.

05 / WHERE IT LANDED

In production with the creative team, still being sharpened

<24 HRS
CAMPAIGN IMAGERY TURNAROUND
WAS 2—3 WEEKS
PRD → PROD
OWNED THE FULL
PRODUCT LIFECYCLE
1 RULE
PRODUCT PIXELS ARE
NEVER GENERATED
06 / IN HINDSIGHT

The honest caveat: adoption is still uneven. Two of the creatives use it daily, one doesn't trust it yet, and I think that's a legitimate position — the fidelity flag is a heuristic, not a guarantee, and I haven't solved how to communicate that confidence properly.

What I'd repeat everywhere: prototyping in the real material. Every meaningful decision here came from using the thing, not from reviewing a frame of it.

NEXT CASE STUDY →
The March Sale
5.74M sessions in a week, across six teams, with no degradation.
GAUTHAM PALANISAMY — PRODUCT DESIGNER BANGALORE, IN · 2026