Assignment 5

A5Sketching, Low-fi Prototype & Usability Testing

We sketched three ways to help people reach their goals, picked mobile notifications, built a paper prototype and tested it with five commuters on a train platform.

Published5 participants3 tasks

01 · Sketching

Three concepts from dozens of sketches

A grid of more than thirty hand-drawn interface sketches.
Brainstorm sketches: dozens of ideas before we narrowed down.

Concept 1

Augmented reality

A camera overlay shows chances to work on your goal: a chair for lunges, the produce aisle for your diet, 5 km left on your run.

Concept 2 · selected

Mobile notifications

Notification prompts keep you on track to reach your goal.

Concept 3

Voice & audio

Talk through your goal with an AI that suggests next steps.

Three concept sketches: an AR overlay, a lock screen notification, and a talking phone asking What is your goal?
The three concepts we took further.

02 · Selected interface

Mobile notifications

Why notifications won

  • It prompts action directly.
  • It works anywhere. Voice needs a place where you can talk out loud.
  • It's cheaper to run.

The trade-off we're watching

Notifications get annoying if overdone. The plan also depends on the AI breaking goals into useful steps.

Model (via OpenRouter)Input / M tokensOutput / M tokens
GPT-5 Mini (text)$0.25$2.00
GPT Audio Mini$0.60$2.40

Audio input costs 140% more and audio output 20% more. Source: OpenRouter.

Hand-drawn flow: log in, describe your goal, review the generated steps, get a notification asking Have you run today?, then rate whether it was effective.
The notification flow we chose to prototype.

03 · Low-fi prototype

A paper phone with sticky-note notifications

Three photos of the paper prototype: a goal input screen with a paper keyboard, a Your Week screen with a 3 day streak, and an analysis screen.
Built from cardboard, paper, sticky notes and markers.
  • Screens: goal planning, stats, notifications and progress analysis.
  • Interactive: typing a goal, a simulated plan generation, notifications and progress reflection.
  • Notifications were yellow sticky notes we slid over the screen.
Pencil storyboard of the full prototype flow from home screen to updated plan.
Storyboard of the full flow, from a new goal to an updated plan.
Photos of the paper prototype for each task: goal input, generated plan, notifications, streak tracker and AI analysis.
The three task flows: plan your goal, remember it, then review progress and edit the plan.

04 · Testing methodology

Five commuters, three tasks

Participants

Five people: three in their early 30s and two aged 22 (tested together). An entrepreneur, two software engineers and two hardware interns. Recruited at a train platform at 7 PM, when we expected busy people. No compensation.

Roles

Facilitator: Josh · Computer: Ben · Notetaker: Roland

Process

  1. Demo the system.
  2. Set a goal: type it, tap +, understand the breakdown.
  3. Read the notifications and pick the most effective of three.
  4. Reflect on progress from the stats page.
  5. General comments on the interface.

What we measured

Time to complete each task, and the number of critical incidents or errors per task. Our goals were quick completion and few critical incidents.

A participant tests the paper prototype on a train platform at night.
Testing on the train platform.

05 · Results

Planning took longest

Hover a bar for its exact value, or open the table under each chart.

Time to complete each task (minutes)

Show as a table
ParticipantPlanNotificationsReflect
P11.00.850.5
P23.80.651.0
P34.10.24.15
P4/53.250.874.3

Critical incidents per task

Show as a table
TaskP1P2P3P4/5
Plan1310
Notifications0010
Reflect1110
General0001

Times are read from our original chart and rounded.

Summary

  • Planning took longest, likely from getting used to the interface and reading a long breakdown.
  • Without a script, times varied more.
  • Three participants weren't sure the AI breakdown was interactive.
  • Usability catastrophe: the vague "upcoming" navigation icon.

Other observations

  • The streak was engaging (participants 2 and 5).
  • Goals varied: train for a marathon, adopt a cat, wake up early, land a full-time job as a forward-deployed engineer.
  • Nobody wants annoying notifications (participants 1, 4 and 5).

06 · Critical incidents

Every issue, ranked by severity

SeverityParticipantTaskCritical incident
4P4/5GeneralUnsure what the upcoming button on the home page shows.
3P1ReflectToo many buttons on the analysis screen; stuck on what to press.
3P1GoalNot sure if the breakdown is interactive.
3P2GoalWonders how specific the goal has to be.
3P2GoalNot sure if the breakdown is interactive.
3P3GoalStarts filling in blanks in the breakdown instead of reading it.
2P2GoalWonders if the AI or the user sets the deadline; would prefer to set it herself.
2P2ReflectWonders if reviewing stats is a step toward her goal.
2P3ReflectWonders what the blank in Thursday's streak means.
1P3NotificationsWonders if the third notification ("Next week, work on…") asks for a recommendation.

4 = usability catastrophe · 3 = major · 2 = minor · 1 = cosmetic

07 · Discussion

What we're changing

Changes we're making

  • Make the breakdown clearly editable with + and − buttons.
  • Redesign the "upcoming" navigation icon.
  • Fewer buttons on the analysis page.
  • Tell people what a goal needs, like a deadline.
  • Make reflection stand out as its own step.

What testing couldn't show

  • How well the profile, upcoming and settings pages work.
  • How long it takes to update a plan after reflecting.

Open questions

  • Streaks may help retention, but what harm can they do?
  • We need a better picture of user goals to tune stats and breakdowns.
  • Notification frequency: one participant liked one a day, another said fewer is more powerful.

Slides

The full A5 presentation

Use the arrows, the thumbnails or your keyboard's arrow keys.