Personal Project

Segment Manager – AI Segmentation Design

Solo · product design & coded frames2026

A personal product design project: an AI-native tool a pharma brand team uses to rank doctors into tiers. I set a point of view on where AI belongs (it drafts and explains, a person decides), designed every screen at three sizes including the failure moments, and built the frames in React and Tailwind so each one imports into Figma.

ReactTypeScriptTailwind CSSVitePlaywrightFigma
Segment Manager home: You have 2,096 Star doctors. 31 moved up this month, 23 slipped. Four tier cards, an Ask AI box, a leaderboard with a podium and a This month panel
The simple view, the default for brand directors · invented doctors and data

Introduction

Project description

Segment Manager is a personal product design project, worked from a brief: an AI-native tool that ranks doctors into tiers for a pharma brand team. It has two very different users. Priya is an analyst who sets the rules. Daniel is a brand director who wants an answer without the maths.

I treated it as a product rather than a set of screens: a point of view on where AI belongs, every screen at three sizes including what happens when things go wrong, and a plan for taking it to a first release. Everything is in Figma: a clickable prototype, and a canvas with every screen, the design system and the deck.

Timeline
November 2026. I planned the work against a 10–12 hour timebox.
My role
Solo: product thinking, interaction and visual design, the deck, and the coded frames.
The brief
High-fidelity screens, with the weight on a rule builder with live preview and a set of stress scenarios, plus a point of view, an 18-month vision, a leadership plan and a note on how I used AI.
Assumptions
I haven't worked in pharma, so team conventions, refresh cadences and review times are written down as assumptions to test in analyst interviews.
86
Frames across desktop, tablet and phone
5
Principles for where AI belongs, each with a test
7
Failure moments designed in full

01Point of view

AI drafts and explains. A person decides.

A live preview already shows Priya how many doctors a threshold gives. It doesn't tell her whether the threshold is sensible, why last quarter's top tier shrank, or whether last month's data broke the list. AI helps exactly there, and is dangerous wherever its output could reach the field unchecked.

So the product follows one rule, written as five principles, each with a test it has to pass.

The system counts. AI explains.

Every number, including numbers inside AI sentences, comes from a query result. A number in AI text that isn't bound to one fails validation.

AI output is an editable rule, never an answer

A request becomes the fields a person would fill in, each marked AI. If you can't reproduce an AI result by editing fields by hand, the feature is wrong.

Assume when readings agree, ask when they don't

If the plausible readings of “high writers” pick mostly the same doctors, AI picks one and flags it. If not, it asks one question.

What a person sets, AI leaves alone

An edited field shows a lock, and the system, not the prompt, rejects any AI change to it.

AI drafts. A named person commits.

No version exists without a person's name on it. Daniel sends drafts for an analyst's review instead of publishing.

02Two depths

One list, two depths

My first drafts were built for analysts: histograms, percentile sliders and tier tables. But most people who open this tool are brand directors and sales leaders, and a statistics-style screen would lose their trust.

So every list has two depths. The simple view reads like a leaderboard and passes a five-second test for someone who dislikes maths. “Show the rules” opens Priya's full builder on the same list. The person's role decides which one opens first.

The rule builder: Cardivex prescriptions per doctor as a histogram with tier cutoffs, a tier table compared with the last version, and history
Show the rules: Priya's builder with live preview
The Ask AI panel showing Here is what I understood, separating the user's words from the AI's guesses before building a list
“Here is what I understood”
The save dialog: This change moves 812 doctors from Star down to Strong. Nobody leaves the list. With an editable AI note
Saving explains the change in doctors
The Northeast list while AI is taking a break: tier cards, leaderboard, filters and search all still work
AI unavailable: the list still works
Desktop frames from the coded designs, with invented doctors and data

03What I built

The parts I owned

A simple view for people who aren't data people

The default screen reads like a leaderboard: a sentence on how many Star doctors there are and who moved, four tier cards, a ranked list with a podium and an Ask AI box.

  • Tier names describe level only (Star, Strong, Steady, Light); rising and slipping show separately as up and down chips
  • Each tier has a signal-bar glyph as well as a shade of green, so the level never depends on colour alone
  • Yellow only ever means “look at this”, so the podium has no gold

AI trust moments

Every place AI acts is designed so the person can see it, check it and undo it.

  • “Here is what I understood” separates your words from the AI's guesses
  • Saving explains the change in doctors (“This moves 812 doctors from Star down to Strong”) with an editable AI note
  • A field a person set shows a lock, and AI leaves it alone

The rule builder

Priya's full builder sits one tap behind the simple view, and is the default for analysts: live preview with a histogram, tiers compared with the last version, where each value came from, and history.

  • AI proposals appear inside the rules, to accept, edit or reject

Failure moments

Seven designed in full: doctors with no records yet, a draft with an empty top tier, AI slow, AI unavailable, protected information, a monthly update that shrank a list by 22%, and AI asking one question when a request is ambiguous.

Compliance and review

Brand directors send lists to an analyst for approval instead of publishing them, and a plain change log shows who approved what, when, and what AI did.

Point of view and plan

A six-page deck: principles, a lifecycle and system map, scope and assumptions, an 18-month vision, a leadership plan and a note on how I used AI.

04Screen tour

Every layer, at three sizes

The simple view, the AI moments and the failure moments come at desktop, tablet and phone sizes. The first version's analyst-first frames stay on as an appendix for the detail analysts and compliance need.

The simple view on every size

On smaller screens the sentence and the tier cards come first, and the leaderboard follows.

Home on a tablet and a phone
Home on tablet and phone
A list's page on a tablet and a phone
A list on tablet and phone

AI trust moments

Asking, understanding, the result, sending for approval and a field AI won't touch.

Ask AI while typing, with a list of what AI can and can't do
What AI can and can't do
The resulting list of 371 top doctors in the Northeast, marked suggested by AI and confirmed by you
Suggested by AI, confirmed by you
Daniel's send for approval dialog, with the team's new-patients convention flagged in plain words
Daniel sends it to an analyst
A rule field marked You with a lock, and AI saying it left it alone
You set this, so AI left it alone

Failure moments

Missing records, a monthly update that shrank a list, protected information and an ambiguous request.

578 doctors with no records yet, listed separately rather than hidden
No records yet, listed, not hidden
This month's update made your list 22% smaller, with what happened in plain words and a choice of what to do
A monthly update shrank the list
Ask AI explaining it can't use speaker fees to choose doctors, with a request-access link and an allowed alternative
Protected information
Ask AI asking which kind of growing the user means, with how many doctors each answer gives
AI asks one simple question

Analyst appendix

The first version's deeper frames: the segment portfolio, metric conventions, drift after a refresh and the audit trail.

A portfolio of 312 segments with flags for drift and duplicates
Portfolio of segments
A warning that the team ranks top Cardivex doctors by new-to-brand prescriptions, not total prescriptions
A metric convention check
A segment that shrank 22% after a refresh, split by cause, with a decision to make
Drift after a refresh
The governance view with a version's audit trail, approvals and AI contributions
Audit trail

Shared on request

See every screen

Segment Manager is company work, so I share the full set of screens with people I know are looking: recruiters, hiring managers and engineers I'm talking to. Tell me who you are and I'll email you a private link.

This opens your mail app with everything filled in. Or email sachin@sachinkamat.com

Coded frames with invented doctors, brands and numbers.

05Process

How AI helped, and where it misled me

I used AI tools throughout, and kept a note of where they helped and where they pulled me the wrong way.

Planning against the brief

AI broke the brief into its deliverables and their weights, so I could plan the hours against what mattered most.

Four tools, one dashboard

I ran the same problem through Claude, Claude Code, Magic Patterns and Figma Make. All four returned nearly the same screen. My prompt had named those elements, so I was getting my own assumptions back, not ideas.

Rewriting the prompt around the user

I removed the chart vocabulary and set a test for every screen: could a brand director who dislikes maths understand it in five seconds?

Swinging too far, then back

AI helped me swing to a leaderboard-first design. Rereading the brief, Priya is the primary user and the rule builder carries the most weight, so it stays one tap away and opens first for analysts.

Numbers from the data only

Every number on screen comes from the sample data, never from AI, so I checked counts across frames and made it the first principle.

AI drafted. I decided.

The point of view, the scope cuts, the assumptions and the leadership plan are my decisions.

06What's next

What I'd test first

The plan starts with the builder working well without AI, ships AI features lowest-risk first, and pilots with one brand. Before building, these are the things I'm least sure of.

Does Daniel want to self-serve at all?

Brand directors may prefer to message Priya. The pilot would show how many of his drafts get sent and how many are abandoned.

Can people catch a wrong assumption?

A prototype test with analysts and brand directors, with a planted wrong reading (total prescriptions where the team uses new-to-brand), and a recovery from “AI unavailable”.

Is AI helping, or just tolerated?

Tracked per feature: proposals accepted unedited, edited, rejected or ignored. Helping means the accepted share rises and edits fall over a quarter.

Engineering notes

  • Static React and Tailwind frames, each at its exact size on its own route, so they import into Figma one frame at a time
  • Design tokens in one CSS file: DM Sans, one forest-green accent, AI violet used only on AI content, and a dark theme
  • A Playwright script screenshots every frame and flags text that runs off a frame or gets clipped
  • A contrast script checks every token pair against WCAG
  • One invented data set (21,400 doctors) used everywhere, so counts agree from frame to frame

Impact

  • One list, two depths
  • AI trust and failure moments designed in full
  • Desktop, tablet and phone frames
  • Frames built to import into Figma

Looking for a Senior Frontend Engineer who can ship platforms like this?