First 5 AI use cases for a business analyst

Five business analyst tasks that are the easiest place to start with AI: each with a ready prompt you can copy and a hint on what to check in the answer.


How to use this

Open Claude Code or Codex (or a regular chat), copy the prompt and replace the text in square brackets with your own. Read the answer critically and refine the prompt if needed.

Data: in all examples use anonymized or test data, not real company documents. How to decide what you may give AI is covered in the AI Champion Blueprint. Check every AI answer: it can invent facts, which is why each scenario has a "what to check" line.


1. Find the holes in requirements

What AI does. AI plays a sceptical reviewer: it looks for contradictions, unclear parts and edge cases where the logic breaks.

Prompt:

You are a sceptical requirements reviewer. Here are the requirements:
[paste text]
Find contradictions, unclear parts and 5 edge cases where the logic breaks. Answer as a table: what is wrong, why, what question to ask the customer.

What to check. Is every point really in your text? Are there invented contradictions?


2. Task readiness check (Definition of Ready)

What AI does. AI checks a task description against a readiness checklist before development.

Prompt:

Check the task against a readiness checklist: clear goal, acceptance criteria, dependencies, mockups, estimate. Task:
[paste description]
Answer as a table: item, present or not, what is missing.

What to check. Does the checklist match your team's own? Add your items.


3. From a meeting transcript to requirements

What AI does. AI turns a meeting transcript into decisions, open questions and draft requirements.

Prompt:

Here is a meeting transcript:
[paste text]
List: decisions made, open questions, actions with owners and draft requirements. Mark separately anything that was not said explicitly.

What to check. Check decisions and owners against what was really said. Especially dates and numbers.


4. Match requirements against tracker tasks

What AI does. AI finds requirements with no tasks and tasks with no requirement.

Prompt:

Here is a list of requirements:
[paste]
Here is a list of tracker tasks:
[paste]
Find requirements with no task, and tasks that match no requirement. Answer with two tables.

What to check. Spot-check 3-4 pairs by hand: AI may have mismatched them.


5. A process diagram from text

What AI does. AI draws a process diagram (steps and participants) in a format you can paste into a document.

Prompt:

Describe this process as a sequence diagram in Mermaid format (participants and steps):
[paste process description]
After the diagram, list the assumptions you made.

What to check. Open the diagram and walk through the steps: does it match the real process?

AI Sandbox Lab

Turn these scenarios into your own system

In the 6-session program you turn prompts like these into ready agents and templates for your role. Not sure the format fits? Book a free 15-minute call on Telegram.

See the program

← All materials

Ask a question