The setting

Lumen Learn sells self-paced professional courses to working adults. You are the UX researcher on the learner-experience team, and course completion has been slipping.

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. research planstarter

Plan the research on why Lumen learners quit mid-course

Course completion at Lumen Learn dropped from 48 percent to 39 percent over two quarters, and the flagship course Data Foundations shows the sharpest fall. Leadership wants to redesign, but the head of product, Ines Vari, insists on understanding why learners leave before anyone touches the design. She wants a plan...

You deliver: A research plan with question, objectives, method, participants, timeline, and how findings will be used.

Scored on: Sharp research question, Method fit, Participant plan, Scope and use.

Working from: completion_brief.md, prior_findings.md.

2. interview guidestarter

Write the interview guide for lapsed Lumen learners

Eight interviews are booked with learners who started Data Foundations and stopped mid-course. The quality of what you learn depends almost entirely on the guide, and an early draft already slipped in a leading question that would push people toward the answers the team expects to hear.

You deliver: An interview guide with warm-up, themed non-leading core questions, probes, and a wrap.

Scored on: Non-leading questions, Theme coverage, Probes present, Logical flow.

Working from: research_plan_summary.md, screener.md.

3. synthesiscore

Synthesize the eight lapsed-learner interviews

The eight interviews are done and the raw transcripts are in. Leadership is waiting on the themes, and the risk is two-sided: miss the pattern that most people raised, or over-index on a one-off complaint and send the redesign chasing the wrong thing.

You deliver: A synthesis of the interviews with themes, participant counts, and quoted evidence.

Scored on: Theme identification, Frequency counts, Evidence quotes, Separates signal from noise.

Working from: interviews_1_4.md, interviews_5_8.md.

4. usability issuecore

Write up the module-3 assignment usability issue

The synthesis pointed straight at the module 3 assignment screen, so the team ran a quick moderated usability test on it. The observer notes are damning, and now product needs a clean, credible write-up they can prioritize, not a vague this screen is confusing.

You deliver: A structured usability issue report with problem, evidence, severity, scope, and root cause.

Scored on: Issue clarity, Evidence and severity, Root cause, Scope and impact.

Working from: usability_session_notes.md, module3_screen.md.

5. recommendation memostretch

Write the recommendation memo to lift Lumen course completion

The research is done and product leadership wants a memo they can act on: what did we learn, what should we change, and what will it be worth. Ines Vari funds recommendations tied to evidence and expected impact, not a list of observations.

You deliver: A recommendation memo with findings recap, three ranked evidence-backed recommendations, expected impact, and success metrics.

Scored on: Evidence linkage, Prioritization, Expected impact, Measurable success.

Working from: synthesis_summary.md, metrics.csv.

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 ux research" something an employer can check.