Project 01
AI-Assisted Mathematics Assessment Generator
A tested prompt-and-QA workflow for generating structured Grade 9 Mathematics assessments.
Workflow Artifact
Prompt design → testing → refinement
Requirements
Define task, constraints and expected behavior.
Architecture
Structure prompts, hierarchy and output rules.
Generate
Run the workflow under normal conditions.
Test
Stress and adversarial testing.
Failure Analysis
Identify root causes and weak instructions.
Refine + QA
Correct the architecture and verify again.
Requirements
Define task, constraints and expected behavior.
Architecture
Structure prompts, hierarchy and output rules.
Generate
Run the workflow under normal conditions.
Refine + QA
Correct the architecture and verify again.
Failure Analysis
Identify root causes and weak instructions.
Test
Stress and adversarial testing.
I converted a basic question-generation request into a structured AI workflow with difficulty control, concept diversity, duplicate prevention, misconception analysis, mathematical verification, adversarial testing, and graceful failure handling.
Problem
Open-ended generation produced too many uncontrolled decisions.
Approach
Separated task rules, verification, testing, and QA into a structured architecture.
Testing
Used standard, stress, and adversarial test cases.
Outcome
A tested portfolio prototype with documented failure handling.