The setting
Northwind Freight runs regional less-than-truckload delivery across five Midwest states. You are the business analyst on the operations team, sitting between the dispatch floor and the software vendor rolling out a new dispatch system.
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. requirement framingstarter
Frame the requirements for Northwind's missed-pickup problem
Dispatchers keep missing scheduled pickups and customers are noticing. The software vendor asked a simple question, what do you actually need, and nobody at Northwind has framed it. The dispatch lead is already asking to buy new tablets.
You deliver: A requirements framing document that reframes solutions as needs and grounds them in the incident data.
Scored on: Problems not solutions, Evidence from the log, Clear requirements, Prioritized.
Working from: dispatch_interviews.md, incident_log.csv.
2. process mappingstarter
Map Northwind's current pickup scheduling process
Before the vendor changes anything, they need the current-state process written down. Right now it lives only in the dispatch lead's head, and every person describes it differently.
You deliver: A current-state process map in text form with actors, decisions, handoffs, and pain points.
Scored on: Steps and actors, Decisions and handoffs, Catches the rework, Readable map.
Working from: process_narrative.md, systems_list.md.
3. user storiescore
Write the backlog of user stories for Northwind's new scheduling screen
The requirements are agreed and the vendor needs a backlog to build from. If the stories are vague or bundled, the vendor will build the wrong thing and bill you for it.
You deliver: A prioritized backlog of user stories traceable to the requirements.
Scored on: Story format, Traceable, Well sliced, Prioritized.
Working from: scheduling_requirements.md, personas.md.
4. acceptance criteriacore
Write acceptance criteria for Northwind's quote fuel surcharge story
The automated quote story is next to build, and QA plus the vendor need acceptance criteria they can test against. This is a billing feature, so a wrong number here becomes a customer dispute.
You deliver: Acceptance criteria in Given, When, Then form plus any raised rule conflict.
Scored on: Testable criteria, Case coverage, Catches the conflict, No silent assumptions.
Working from: story_quote.md, quote_rules.md.
5. impact analysisstretch
Assess the impact of mandatory delivery appointments at Northwind
Leadership wants to require appointment booking for every delivery to cut detention costs. Before committing, they need an impact analysis, because a hard mandate could push away the accounts that pay the bills.
You deliver: An impact analysis with affected parties, quantified exposure, risks, and a recommended rollout.
Scored on: Affected scope, Quantified exposure, Catches the key risk, Phased recommendation.
Working from: proposed_change.md, customer_volume.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 business analysis" something an employer can check.