AI for Business Analysis Capstone Exercise
Deliberate Academy Editorial Team
Reviewed for accuracy and professional relevance
You're 10 lessons in — don't lose your progress.
Sign up free to save where you are and earn a verified certificate when you pass.
- Apply skills from across this course in a single realistic professional scenario
- Produce a concrete, role-relevant deliverable using AI tools
- Self-assess your output against professional quality criteria
Across this course you have worked through AI-assisted requirements gathering, process mapping, data analysis, insight communication, solution evaluation, business case development, UAT scenario generation, and change impact assessment. Each of those skills exists to serve a single outcome: helping stakeholders make better decisions faster. This capstone asks you to deliver exactly that, under the kind of time and scope constraints a BA genuinely faces.
The scenario is a real-world BA situation: qualitative complaint data, a product team expecting a requirements pack, and a tight turnaround. Your job is to use AI to move from raw data to structured requirements, while maintaining the analytical rigour that separates a good BA from a prompt-forwarding service.
Capstone Exercise
Requirements Pack for a Returns Portal: From Complaint Data to User Stories
Context
You are a business analyst at a mid-size retail company. The product team is scoping a new self-service returns portal. Your starting point is a set of 40 customer complaints about the current returns process, collected from email support over the last quarter. The complaints cover topics including missing return labels, delayed refunds, unclear eligibility rules, and no status updates after drop-off. The product manager wants a requirements pack by end of week. They need themes, user stories, acceptance criteria, and any gaps you have identified. They are not interested in raw complaint summaries.
Your Task
Use an AI tool to work through the requirements pack in four steps. First, write a prompt that describes the complaint dataset to the AI and asks it to extract the top thematic clusters. Second, use the themes to generate three user stories in standard format (As a... I want to... So that...). Third, create an acceptance criteria table for each of those three user stories, with at least two criteria per story. Fourth, write a short paragraph identifying one gap or ambiguity in the requirements that the AI could not resolve and that you would need to take back to the product manager for clarification.
Your notes (optional)
Deliverable
A requirements pack containing: a thematic analysis summary of three to five complaint clusters, three user stories in standard format, an acceptance criteria table covering all three stories, and one clearly written gap or open question to raise with the product manager.
This capstone sets a single test for whether something you have written is an acceptance criterion at all. What is that test?
Select one answer.
- AI is most useful in BA work when it accelerates the structuring of qualitative information, not when it replaces the analytical framing step
- Requirements quality depends on the specificity of your inputs: vague complaint descriptions produce vague themes and unusable user stories
- Acceptance criteria must always be testable: if you cannot verify it in UAT, it is not a criterion, it is an aspiration
- Every AI-assisted requirements pack should contain at least one explicit gap: if it looks complete, you have probably not looked hard enough
Complete all lessons to take the free exam
Pass the exam to earn your AI for Business Analysis — Certified AI Practitioner — a verifiable certificate you can share on LinkedIn.