Artificial Intelligence Assistants

Summary: Built an AI assistant to evaluate short-answer responses from Certified Admin exams, reducing grading time by 50% while maintaining 95–99% accuracy with human graders. The tool aims to provide consistent, contextual feedback to learners, handle complex inputs, and scale human effort across eight exams and 80+ unique questions.

Challenge

The Certified Admin exams included over 80 unique short-answer questions across eight different assessments, each requiring manual grading. This process was time-consuming, inconsistent across graders, and difficult to scale.

Ensuring contextual, personalized feedback was also challenging due to vague, overly detailed, or partially correct responses from learners of varying backgrounds.

Solution

AI-Powered Grading Engine

  • Trained on course materials, answer keys, and company-specific context.
  • Handles vague, nuanced, and over-detailed answers.
  • Excludes biased or incorrect historical data from training.

Feedback Generator

  • Generates precise, supportive feedback (e.g., "missing concept," "good structure, incomplete logic").
  • Encourages learning without pass/fail bias.

Evaluation Pipeline

  • Uses blind comparison against human graders to refine model accuracy.
  • Implements rubric-based scoring aligned with SME validation.

My Role

  • Led project design and development from ideation to pilot testing.
  • Authored custom prompt architecture and validation scripts.
  • Ran blind testing with SMEs and iterated based on feedback.
  • Designed rollout and data governance framework.

Tools & Technologies

  • Development: Excel, Word, proprietary LLM
  • Integration: Skilljar (theoretical)
  • Evaluation: SME blind scoring, feedback loop design

Impact

  • 50% reduction in manual grading time
  • 95–99% agreement with human graders
  • Consistent, high-quality learner feedback delivered across all responses
  • Scalable solution for 70+ questions across 7 certification exams
  • Strategic roadmap for future rollout and ethical AI expansion
× Enlarged project image