Self-Study Assignment 6.3: Think & Act💡Design an Intelligent Inbox Assistant

Learning Outcomes Addressed: 

• Apply computational thinking concepts such as decomposition, pattern recognition, abstraction and algorithms to workflow problems.

Scenario

Your organisation receives hundreds of emails each week. Employees spend significant time reading, sorting, and prioritising messages before taking action. Leadership would like to explore whether AI could help streamline this process while ensuring important communications are not missed.

Task

Design a simple AI-assisted inbox workflow that automatically categorises incoming emails into:

• Urgent
• Needs Action
• FYI

Step 1: Define Your Rules

Determine how emails will be classified using criteria such as:

• Keywords or phrases
• Sender type (manager, client, customer, colleague, automated system)
• Deadlines or time-sensitive information
• Attachments or supporting documents
• Email subject lines

Step 2: Allocate Responsibilities

For each category, decide:

• What can be automatically labelled by AI
• What should be flagged for human review
• What actions can be automated
• What actions require human judgement

Step 3: Assess the Design

Consider the following questions:

1. Which parts of the workflow are suitable for automation?
2. Where could incorrect classification create risks?
3. What safeguards would you put in place to ensure important emails are not missed?
4. How would the workflow improve productivity and user experience?
5. Which decisions should remain human-led and why?

• Estimated Duration: 30 minutes

  Note: This is a practice activity and will not be graded or impact your programme completion. However, we strongly encourage participation for a more holistic learning experience.