Chapters
← All work

AI·Product design·Desktop & mobile

Pathways: AI-built courses that don't keep learners waiting

Turning a slow, manual course generator into a conversation that drafts, refines and starts teaching within minutes.

Grasp · Web & mobile web · Jul 2025 – Jun 2026 · Product Designer (sole designer)

Chapter 1

Overview

Pathways is Grasp's AI course builder. A learner says what they want to learn, an AI mentor asks a few questions, drafts a course of modules and lessons, and revises it until the learner is happy.

The first version worked, but it felt slow and fragile. Learners stared at a spinner, had to press buttons to move the AI along, and couldn't tell whether anything was happening. My job was to make generation feel fast, honest and in the learner's control, on desktop and mobile.

The problem

Building a course took several manual steps and minutes of silent waiting. Learners had to trigger "write lessons" themselves, could only generate one module at a time, and got no sense of progress or of how long it would take.

Outcomes

  • The first lesson is ready in about 3 minutes, and the rest of the course builds in the background
  • Learners can close the tab: an email arrives when the course is ready
  • The mentor can be stopped, edited and retried mid-response
  • Fewer learners abandoned their course while it was generating

Chapter 2

Role & constraints

Product Designer, and the only designer at Grasp. I led Pathways end to end: discovery, journey mapping, user flows, UX/UI for desktop and mobile web, the AI mentor's states, and reviewing builds before release. I worked directly with the founder, university professors and the engineering team in one-week delivery cycles, and sat on Product Owner recruitment panels to bring a UX perspective to hiring.

Product
MeCourse generationChat, drafts, course skeleton
MeLessonsLesson page and mentor chat
MeAI mentorThinking, stop, retry, error states
Marketing
MeLanding pageResponsive site at four breakpoints
Foundation
Grasp design systemBuilt on shadcn/ui (Radix + Tailwind)
Four workstreams, one design system underneath

2.1How I worked

Research into decisions

Co-led discovery through learner interviews and performance analysis, and turned findings into product priorities with the founder.

Diverse, hard-to-reach learners

Helped set up learner communities in Bengaluru and Hyderabad, bringing insights from international learners back into the product.

Prototype, test, iterate

Tested concepts early with rapid prototypes, iterating in one-week cycles rather than waiting for a big release.

Quality through delivery

Reviewed builds against the designs before release, and used the shared shadcn/ui-based design system so new screens stayed consistent.

  • AI is slow and unpredictable. Generation takes minutes, responses stream in, and the model can fail at any point.
  • Learners arrive with a goal, not a syllabus. The product has to do the structuring for them.
  • Mobile web matters. Every flow had to work on a phone, not just desktop.

Chapter 3

Discovery

3.1The end-to-end user flow

I started by mapping the whole service, not just the screen we were asked to fix: from landing on Grasp to building a second module. New and returning learners take different routes in, then share the same path through course generation and learning.

Arrive
Landing pageHas an account?No: sign up, verify emailYes: go to homepage
Personalise
Welcome: add backgroundUpload a CVAdd details manuallyPersonalised goal suggestions
Goal setting
What will you study today?Type a goalor pick a suggestion
Course generation
Open course chatMentor asks a question~3 questionsDraft 1Mentor reviewcompare with previous draftDraft XCreate final course
Lesson generation
Write Module 1 firstEmailwhen the first module is readyVisit lesson
Learning
Complete lessonComplete moduleBuild module 2Finish course
Rebuilt from the Pathways user flow in Figma. Highlighted steps are where I focused the redesign.

3.2Mapping the learner's journey

Then I mapped how that flow felt to a learner, stage by stage, using what learners told us in interviews. The emotional low point was obvious: the wait between agreeing a course and being able to start it.

Archetype: a self-directed learner. Wants a short course on a topic they care about, fitted around work.

01Arrive
02Shape the course
03Wait
04Learn
05Get unstuck
06Come back
Doing
Lands on the homepage and types a goal
Answers the mentor's questions and reviews drafts
Presses Make course, then Write lessons, then waits
Opens the first lesson
Asks the mentor; the answer is slow or wrong
Returns to carry on with the course
Thinking
Can this actually teach me what I need?
Is it listening to me?
How long will this take? Is it stuck?
Finally. But I've got a question.
I can't stop it, I just have to wait
Good, it's ready where I left it
Feeling
Pain point
A blank prompt; unsure what to ask for
Opening a draft hid the conversation
Minutes of silence, manual triggers, one module at a time
The mentor hid behind an unlabelled icon
No way to stop, edit or retry
Later modules needed building one by one
What I designed
Goal suggestions based on their background
Drafts open beside the chat, with Suggest changes or Keep going
Course skeleton, Module 1 first in ~3 minutes, email when ready
An Ask your mentor button and highlight-to-ask
Stop, edit and retry states for every response
Generate the rest of the modules in one go
Journey map built from learner interviews and the problems noted in the Figma files

I mapped every screen and action in the existing flow, from the homepage prompt to opening the first lesson, and marked where learners got stuck.

The original flow, with pain points and opportunities noted in orange

3.3Too much time spent waiting

A course took minutes to generate, and the screen gave nothing back. In my notes, the learner's needs during those minutes were blunt: I don't know roughly how long this will take. I don't have a sense of progress. I don't know how good it will be.

3.4Excessive manual input

After approving a draft, learners had to press "Make course", then press "Write lessons", and could only generate one module at a time. The AI was waiting on the learner, and the learner was waiting on the AI.

Before

Type a goalChat with mentor~3 questionsReview draftKeep goingSuggest changesDraft 2…XMake courseWrite lessonsOpen lessonafter a long wait

After

Type a goalChat with mentor~3 questionsReview draftKeep goingSuggest changesCourse skeletonModule 1 written first~3 minStart learningrest builds in backgroundEmailwhen the course is ready
Two manual steps removed. Learners start learning while the course finishes.

3.5The mentor was hard to find

Inside a lesson, the AI mentor sat behind an unlabelled icon in the corner. Learners with a question didn't know they could ask one.

Chapter 4

Solution

4.1Build a course through conversation

Learners start with a goal in plain language. The mentor shows that it's thinking, asks a few questions, then responds with a plan. The same flow works on a phone.

Mentor response on desktop
Homepage on mobile
Mentor response on mobile
Desktop and mobile web

4.2Drafts beside the chat

Each draft opens next to the conversation, so learners can read the course and talk about it at the same time. A few rules kept this calm:

  • Always show the action bar on drafts: Suggest changes or Keep going.
  • Always keep the chat input visible, but disable it while the mentor is thinking.
  • Notify learners when a new draft arrives if they switched views with the toggle rather than the message button.
Course draft beside the chat on desktop
Course draft on mobile

4.3A course skeleton instead of a spinner

Instead of generating everything before showing anything, Pathways now shows the whole course structure straight away and writes Module 1 first. Later modules appear as greyed-out outlines, and one button generates the rest.

Before
Before: nothing to see until the whole course was generated
Before: nothing to see until the whole course was generated
After
After: the full structure at once, with Module 1 ready first
After: the full structure at once, with Module 1 ready first

The waiting itself became honest. Four messages had to reach the learner:

No more input needed

The learner's job is done; Pathways takes it from here.

First lesson in ~3 minutes

A concrete time, not a spinner.

Safe to close the tab

Nothing is lost if they leave.

Email when it's ready

So they come back at the right moment.

  1. Set a goal

    1Set a goal

    Personalised suggestions under the prompt

  2. Structure appears

    2Structure appears

    A skeleton instead of a blank screen

  3. Preparing your course

    3Preparing your course

    The mentor says what's happening

  4. First lesson ready

    4First lesson ready

    A clear moment to start

  5. Start Module 1

    5Start Module 1

    Later modules keep building

The same generation flow on mobile, step by step

4.4A mentor you can stop and correct

AI responses can be slow, wrong or fail outright. I mapped every state the mentor can be in, so learners always have a way out: stop it, edit the message, or retry.

Mentor states while producing a course draft
Chat input states: default, typing, stop response and editing

4.5Making the lesson mentor discoverable

In lessons, the unlabelled icon became an Ask your mentor button. It opens a side panel with an empty state that explains what to ask, and learners can highlight text to get a focused explanation.

Before
Before: an unlabelled chat icon in the corner
Before: an unlabelled chat icon in the corner
After
After: a labelled button and a side panel that explains what to ask
After: a labelled button and a side panel that explains what to ask
Lesson page with the mentor panel open on desktop
Lesson page on mobile, with the mentor one tap away
The final lesson page on desktop and mobile

4.6Edge cases: limits and errors

Free learners hit a course limit. Rather than blocking the homepage, a quiet banner explains the limit and offers an upgrade, while their existing courses stay one click away.

Course limit reached: informed, not locked out

4.7Accessible AI, by design

Streaming AI is a hard case for accessibility: content moves, timing is unpredictable, and status often lives in an animation. These decisions kept Pathways usable for everyone, with WCAG 2.2 AA as the bar:

DecisionWhy it mattersWCAG 2.2
Learners can stop the mentor mid-responseMoving, auto-updating content can be paused2.2.2 Pause, stop, hide
Progress and time estimates are written messages, not just a spinnerScreen-reader users hear what's happening4.1.3 Status messages
The mentor icon became a labelled "Ask your mentor" buttonIts purpose is clear to everyone, including voice-control users2.5.3 Label in name; 2.4.6 Headings and labels
Every flow works on a phone, down to small screensNo horizontal scrolling or lost content1.4.10 Reflow
Learners can close the tab and get an email when the course is readyNo time pressure while the AI works2.2.1 Timing adjustable

4.8Landing page

A responsive marketing site built from the same components, at four breakpoints.

Chapter 5

Results

~3 min
from goal to first lesson, instead of waiting for the whole course
4
manual steps removed from course creation
1 in 3
learners used Ask your mentor in their first week

Fewer learners dropped off while their course was building, and more of them went on to finish Module 1. The conversational builder, background generation with an email when the course is ready, and the mentor's stop, edit and retry states shipped to all learners in 2026. Next on the roadmap was generating several modules in parallel, so learners would never wait between modules.

Chapter 6

Reflection

Design the wait, not just the result. With AI, latency is part of the product. Showing progress, giving an honest time estimate and letting people leave and come back did more for how fast it felt than any change to the model.

Keep the learner in control. Streaming responses feel alive, but they feel out of control when they go wrong. Stop, edit and retry let learners steer the mentor instead of starting again, and made the AI feel like a collaborator.

Tell the story, not just the spec. Mapping the journey and showing the waiting screen next to what learners told us made the case for background generation faster than any requirements document. The founder and engineers could see the problem, so we agreed the fix in a single session.

What I'd do differently. I'd measure the generation flow from day one. We had strong signals from interviews early on, but no baseline for drop-off until later, which made the improvement harder to put a number on.