Application exercises are the most critical components of a TBL that should be designed as complex, real-world problems to elicit deep learning and foster student engagement. The process of crafting these exercises is fraught with veritable challenges for educators - time constraints, alignment with learning objectives, learner engagement, scaffolding, and authentic simulation of real-world problem-solving.

The purpose of this workshop is to empower educators to write effective prompts (prompt engineering) using AI to create engaging application exercises that meet the 4S principle of TBL application exercises and to promote critical thinking/clinical reasoning. Participants will first be introduced to the key elements of creating an effective prompt using the TRACI framework. The AI tool, Anthropic’s Claude 3.5 Sonnet, will then be used to demonstrate how to design application exercises for team-based learning sessions (TBL) to promote higher-order thinking and learner engagement, aligned to Bloom’s taxonomy. This will go beyond the multiple-choice question (MCQ) format to include matrix creation, sequencing, structured problem solving etc. among others.

Mastering effective prompting is a skill that develops over time with several iterations, obtaining feedback from the LLM and thoughtful refinement of prompts based on the output received. Higher-order application exercises should balance the tightrope walk between complexity level and cognitive load without overwhelming learners. Therefore, educators should be willing to experiment with prompting and intentionally reflect on the appropriateness of the application exercises generated. AI-generated content always should be verified by the subject matter expert.