EST. 2026
6:15:27 UTC
Prompt Privacy
/
2026
One input. Every model.
Nothing in between.
A ground-up rebuild of an enterprise AI workspace — taking a dark, card-
cluttered chat product and turning it into one input-first canvas where choosing a
model, speaking a prompt and reading the receipts all happen in the same place.
WHO WAS ON THIS?
Just me
ROLE
Product Designer
SCOPE
IA · UI · Interaction
PLATFORM
Web Application
YEAR
2026
MY ROLE AND SUMMARY
I took an enterprise AI chat tool that had grown in every direction at once and
rebuilt it around the one thing every session actually begins with — the input.
Model switching, attachments, voice and dispatch all collapsed into a single
container anchored to the middle of the canvas. Chat history got a spine. Answers
got somewhere to keep their receipts. Everything that wasn’t the exchange
between prompt and response got cut.
The measure for every decision was the same: does this shorten the distance between what the user means and what the system gives back?
CHALLENGE, PURPOSE AND DEFINITION
What’s actually wrong with most AI workspaces?
Enterprise AI tools tend to accumulate. A model gets added, so a card goes on the home screen. A feature ships, so a button joins the tray. Nothing is ever obviously wrong, and then one day the prompt field — the only element every single session touches — is the smallest thing on the page, pinned to the bottom edge, below four cards explaining models the user already knows.
PROBLEM
The one thing every session begins with was
the hardest thing on the screen to reach.
I PULLED THE LEGACY BUILD APART, AND HERE’S WHAT I FOUND
01
An isolated input zone, detached from the controls that govern it — the model
picker lived in the top bar, attachments in a tray, the field itself at the bottom.
02
Static model cards holding the centre of the canvas, describing Auto Pilot,
Gemini 1.5 Pro, Llama 3.1 70B and Runway to people who switch models
twelve times a day.
03
Chat history with no semantic grouping — nine consecutive threads all
reading “1- Greetings & Salutations…”, which is a list that technically works
and practically doesn’t.
SO I DEFINED WHAT THE REDESIGN HAD TO DO
People running six models a day need one place to
type, one place to look, and no decisions in between.
Before and after, drag to compare
FOCUS & CHOICE
The main action was buried — and the model was asked twice
OLD DESIGN
Buried primary action. The prompt input — the whole reason to open the app — was a thin strip at the bottom, overpowered by a grid of model cards in the centre. The main task didn’t look like the main task.
Decision overload. Models could be picked in two competing places — a top dropdown and the centre card grid — forcing a choice before you’d even started.
NEW DESIGN
One focal point. The prompt bar moves to the centre with a greeting and a short cue, so the first thing the eye lands on is the thing to do.
One place to choose. Model selection collapses into a single control inside the prompt bar — surfaced only when it’s relevant.
THE DESIGN APPROACH
Consolidation first
The model cards came off the canvas entirely. In their place, a single input container sits at the optical centre of the screen and absorbs everything that used to be scattered around it — the attachment control, the model selector, the microphone, the dispatch button. One footprint, four jobs.
Chat history moved into a structured sidebar and picked up chronological grouping — July 2026, June 2026, April 2026, December 2025 — so locating a prior session became a matter of remembering roughly when, not scanning a flat column of near-identical titles. Vector Vault and My Data sit above the fold, where the work actually starts.
MODEL AND VOICE
Both live inside the same footprint
An in-line switcher with search surfaces the whole catalogue — Auto Pilot, Amazon Nova Micro, Azure ChatGPT 3.5 and 4o, ChatGPT 4 Turbo, 4.1 and 4.1 Mini — without the user ever leaving the input context. The default is labelled as the default, so the common path needs no decision at all.
Voice renders as a live waveform inside the field rather than over it. Recording
state, elapsed duration and dispatch occupy exactly the footprint the text cursor
just vacated. No modal, no overlay, no state to dismiss before you can type again.
MODEL ACCESS
Switching models meant leaving the prompt
OLD DESIGN
The model selector sat in the top bar while the prompt input stayed pinned to the bottom. Choosing a model for what you were about to write meant travelling the full height of the screen and back — every time.
NEW DESIGN
The selector now lives inside the prompt bar. Choosing a model and writing the prompt happen in the same place, in one motion.
Model selection
NAVIGATION
It collapses when you don’t need it
Navigation is multi-tier and independently collapsible. The primary rail compresses
to icons; the history panel folds away on its own. At full collapse the canvas is
almost entirely input and answer, which is the point.
Per-conversation actions — Pin Chat, Edit, Delete — moved into contextual hover
menus instead of permanent affordances. And a Prompts panel on the right edge
lists every prompt in the session in sequence, so a long thread stops being
something you scroll and becomes something you navigate.
STRUCTURE & SCALE
One flat sidebar that couldn’t scale
OLD DESIGN
Everything shared one flat sidebar — logo, new chat, history, settings, profile — with no hierarchy between where you are in the app and what’s inside a section.
NEW DESIGN
Navigation splits into a slim icon rail for global sections and a contextual panel for the chat list — clearer now, with room to grow without clutter.
NEW FEATURES · PROPOSED
Additions, not fixes
These three weren’t on the old canvas at all — they’re capabilities I proposed to make the everyday flow faster: talk into the field, go fully hands-free, and navigate a long thread instead of scrolling it.
SPEECH-TO-TEXT
Dictate
Talk instead of type; it lands in the field inline.
HANDS-FREE
Voice mode
Hand the whole input to a listening canvas and converse.
WAYFINDING
Prompts panel
Jump between every prompt in a thread instead of scrolling.
dictate
Voice mode
A hands-free conversation, not just capture. Tapping the mic hands the whole input over to a voice canvas — a live listening orb, running duration and a single control to end — so the user can think out loud and let the model reply in kind.
Listening…
0:07
Prompts Panel
OBSERVABILITY
When an answer needs receipts
A complex AI response is three different things at once, so it segments into three
views. Answer carries the structured content, comparative tables included.
Sources exposes the reference links, clickable, for anyone who needs to verify
before they forward. Details surfaces the execution metadata — runtime, model
attribution — so “Executed: 17.40s” is available to the people who care and
invisible to the people who don’t.
In an enterprise context this is the difference between an answer and a usable one.
Full observability, no visual overload.
Long-form answer
Design Principle
AI Chat · 5.0
In AI tooling, restraint is a feature. Every element I removed from the canvas gave attention back to the exchange between prompt and response.
IMPACT AND LEARNING
What changed
Fewer decisions per prompt. Consolidating model, attachment, voice and
dispatch into one container removed the cross-screen hunt that used to precede
every message.
History you can actually re-enter. Chronological clustering replaced linear
scanning, so returning to a session from three months ago is a date recall, not a
reading exercise.
Answers that survive scrutiny. Sources and execution details are one tab away,
which is what makes an AI output forwardable inside an enterprise.
What did I learn from this?
Subtraction is a design move. The cards weren’t badly designed — they were
well-designed things in the wrong place. Removing them was the largest single
improvement in the project.
Consolidation beats arrangement. I could have spent the whole redesign
moving controls closer together. Putting them in the same container was the
version that actually worked.
Enterprise users want the metadata, just not constantly. Runtime and model
attribution matter enormously — right up until they’re on screen all the time.
STILL CURIOUS?
That’s the case study — see more of the work, or say hello.