The setting

Northwind Tutoring matches students with online tutors and runs on a stack of no-code automations. You are the automation specialist replacing slow manual steps with reliable workflows across intake, scheduling, and payouts.

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. workflow briefstarter

Brief the new-student onboarding automation at Northwind

Onboarding new students at Northwind is still done by hand, and it is slipping: last week two families never got a welcome email and one student was entered twice. Before building anything, you need a clear brief of the automated flow.

You deliver: A workflow brief describing the automated onboarding flow, the systems touched, and the human review points.

Scored on: Covers the whole flow, Names the systems, Prevents the known failures, Human review points.

Working from: current_process.md, intake_fields.md.

2. trigger designstarter

Design the triggers for Northwind's lesson-reminder automation

Families and tutors keep missing lessons, so Northwind wants automated reminders. The rules have real edge cases: timezones, quiet hours, cancellations, and students with two lessons a day.

You deliver: A trigger design spec stating each reminder's conditions and the edge cases it handles.

Scored on: Defines the reminder conditions, Handles quiet hours, Skips cancelled and rescheduled, Handles same-day lessons.

Working from: reminders_requirements.md, lesson_schedule.csv.

3. validationcore

Validate the tutor-payout automation before it goes live

The new tutor-payout automation ran once in test mode against last week's hours. Before it pays real money on Friday, you need to prove it computes correctly, because a wrong payout erodes tutor trust fast.

You deliver: A validation report recomputing payouts, naming every incorrect row, and giving a go or no-go call.

Scored on: Finds the miscalculation, Finds the zero payout, Notes the incomplete row, Clear go or no-go.

Working from: payout_runs.csv, payout_rules.md.

4. error pathcore

Design the error paths for Northwind's enrollment sync

The enrollment sync pushes new enrollments from the intake form into the SIS twice a day, and it has been failing quietly. The 02:00 run keeps timing out, and some enrollments land twice or half-written.

You deliver: An error-path design covering each failure type, the timeout pattern, and what alerts a human.

Scored on: Covers each failure type, Explains the 02:00 pattern, Idempotency and partial writes, Alert versus auto-recover.

Working from: sync_run_logs.csv, integration_notes.md.

5. handoffstretch

Write the handoff doc for the automations you built this quarter

You are out for three weeks and a new operations hire will cover the automations. Right now every workflow lives in your head, which is a real risk if something breaks while you are gone.

You deliver: A handoff document describing each automation, its triggers, known issues, and escalation steps.

Scored on: Describes each automation, Flags the fragile ones, Names the continuity risk, Escalation steps.

Working from: automation_inventory.csv, run_stats.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 no-code automation" something an employer can check.