The setting

Cadence Health is a telehealth app where patients book and join video visits with clinicians from their phones. You are the UI designer on the mobile product team, responsible for the patient-facing screens.

Every mission on this path happens at the same company, so context carries over the way it does in a real job: the data you cleaned in mission two is the data the finance lead questions in mission four.

The missions

1. layout hierarchystarter

Fix the visual hierarchy on Cadence's appointment screen

The Cadence appointment detail screen is what patients open in the five minutes before a video visit, and it tests badly: people miss the Join call button and the start time. Support tickets are piling up from patients who could not tell how to get into their visit.

You deliver: A layout hierarchy spec ranking screen elements by priority with placement and visual-weight rationale.

Scored on: Priority ranking, Addresses the critique, Hierarchy rationale, Scannability.

Working from: appointment_screen_inventory.md, critique_notes.md.

2. component statesstarter

Define every state for Cadence's book button and slot picker

Engineering is about to build the Cadence booking flow and keeps stopping to ask what each component does when it is loading, disabled, or when something goes wrong. Right now only the happy path is drawn, so the edge cases get invented on the fly and look inconsistent.

You deliver: A component states spec covering all interaction states for the book button and the slot picker.

Scored on: State coverage, Edge cases handled, Behavior clarity, Consistency.

Working from: component_inventory.md, flow_notes.md.

3. responsive polishcore

Make Cadence's visit summary work from small phones to tablets

The Cadence visit summary appears right after a video visit ends and lists the diagnosis, medications, and a follow-up action. It breaks on small phones and wastes half the screen on tablets, and one of the breaks is a patient-safety problem: a medication dosage gets cut off.

You deliver: A responsive spec defining layout and reflow across three breakpoints with truncation and spacing rules.

Scored on: Breakpoint coverage, Fixes the named issues, Reflow and spacing rules, Touch targets.

Working from: breakpoint_notes.md, summary_screen_inventory.md.

4. tokenscore

Reconcile Cadence Health's color and spacing tokens

Cadence's design system has drifted. Different screens use slightly different blues and off-grid spacing, so the app looks subtly inconsistent and engineering hardcodes hex values. The design lead asked you to audit what is actually in use and propose one clean token set.

You deliver: A token specification with named color, spacing, and type tokens plus a migration map from the current values.

Scored on: Consolidates the drift, Grid alignment, Token completeness, Migration map.

Working from: brand_rules.md, current_styles.csv.

5. developer handoffstretch

Ship the developer handoff for Cadence's reschedule flow

The Cadence reschedule flow is approved and engineering starts building it Monday. If the handoff has gaps, they will fill them by guessing, and reschedule touches billing and clinician calendars, so guesses are expensive. This handoff has to be complete enough to build from without a single follow-up question.

You deliver: A developer handoff spec with screen details, states, measurements, tokens, edge cases, and acceptance criteria.

Scored on: Spec completeness, States and edge cases, Measurements and tokens, Acceptance criteria.

Working from: reschedule_flow.md, redlines_notes.md.

How the scoring works

Each deliverable is graded against the rubric written for that mission. Separately, every mission on every path is graded on how you used AI, against the same four criteria:

  • Understood the task. The learner framed the goal for the assistant clearly instead of pasting the brief and hoping.
  • Grounded in the material. The learner directed the assistant into the provided files and based the work on them, not on invented facts.
  • Verified the output. The learner checked claims, numbers, or coverage against the source material before submitting.
  • Iterated with judgment. The learner refined weak parts of the draft with specific follow-ups rather than accepting the first answer.

Both scores, with the work behind them, go on your proof profile. That is what makes a claim like "I can use AI for ui design" something an employer can check.