LearnLab
Core Course Trending

Using Generative AI to Develop Active Learning Experiences

Enroll Now View syllabus

Beginner level

No prior experience required

Flexible schedule

3 weeks, 6 to 8 hours per week

Instructor feedback

Get guidance on your work

Verified certificate

Share on LinkedIn

*Proof of full-time student enrollment required. Acceptable forms of ID include a letter from your university’s registrar office or an unofficial transcript. Email your documents to learnlab-help@lists.andrew.cmu.edu.

What you will learn

  • Use prompt engineering to create and improve learning activities, examples, feedback, and assessments.
  • Design AI-supported activities that promote active learning, personalization, tutoring, and meaningful practice.
  • Integrate generative AI into educational tools using APIs, DSPy, and structured workflows.
  • Build agentic AI solutions with Skills, MCP servers, and workflows while considering ethics, privacy, and human judgment.

Course description

Generative AI can speed up content creation, but its real value in education comes from helping teams design more active, engaging, adaptive, and tool-supported learning experiences. The opportunity is not simply to produce materials faster, but to create better practice, feedback, personalization, tutoring, and interaction for learners.

In this course, you will learn how to use generative AI to design active learning experiences through prompt engineering, top-down task design, structured content generation, LLM APIs, DSPy, and agentic AI workflows. You will examine where AI can support learning design effectively, where human judgment is essential, and how to build practical solutions using tools such as Skills, MCP servers, and workflows while attending to reliability, ethics, privacy, and learning impact.

Syllabus

Module 1: Leveraging LLMs: Prompt Engineering, from Definition to Evaluation
  • Analyze recent research on generative AI in education to identify where and how it outperforms traditional approaches.
  • Apply prompt engineering strategies to optimize the performance of Large Language Models (LLMs) in generating desired educational outputs.
  • Differentiate between zero-shot and few-shot prompting, explaining appropriate scenarios for their utilization.
  • Demonstrate how to refine prompts through additional instructions or context to shape the output of Large Language Models.
  • Critically evaluate the output from Large Language Models for reliability and accuracy, identifying potential instances of hallucination.
Module 2: Top-Down Design: Implementing Educational Tasks with LLMs and Learning Science Principles
  • Divide an educational task into subtasks as part of top-down design based on the concept of LLM chains.
  • Contextualize educational problems to match individual student interests in intelligent tutoring systems using large language models.
  • Design personalized learning experiences using generative AI tools to adapt content and support to individual learner needs.
  • Implement AI-driven tutoring and feedback strategies grounded in pedagogical best practices to enhance student mastery.
  • Apply generative AI to boost student engagement and motivation through interactive and adaptive learning activities.
Module 3: Integrating LLMs in Educational Tools: Practical Examples
  • Differentiate between LLM APIs and conversational chatbots justifying the use of APIs in educational contexts despite the convenience of chatbots.
  • Analyze the implications of hyperparameter tuning in prompt engineering for optimizing the LLM outputs.
  • Utilizing DSPy for programming foundational models with minimal code to solve a given task.
  • Integrate generative AI tools to provide timely, formative feedback on student work, thereby improving the revision process and learning outcomes.
  • Create effective distractors for multiple-choice questions using LLMs that align with learning outcomes and target students’ misconceptions.
  • Address ethical, privacy, and cognitive challenges when integrating generative AI in learning designs.
Module 4: Agentic AI Assistants: Skills, MCP Servers, and Workflows
  • Explain what Agent Skills are and when to use them.
  • Decide what belongs in each part of an Agent Skill: description, instructions, and supporting files.
  • Write Agent Skill descriptions that help agents know when to use them.
  • Build and test a working Agent Skill, then improve it based on how the agent responds to real requests.
  • Recognize how the same MCP server works across different AI clients.
  • Recognize where MCP tool code runs and where it does not.
  • Choose the right MCP primitive (Tools, Resources, or Prompts) for a given capability.
  • Trace how a multi-step workflow decomposes work into focused steps that mix LLM calls and deterministic code.
  • Choose between Skills, MCP servers, and Workflows, or combinations of them, for a given project.
Module 5: Course Project

At the end of the course, you’ll have an opportunity to complete a two-step project from three choices based on your area of interest: Educational Tool Design (UX/UI), Educational Tool Development (Technical), or Prompt Engineering Template (Instructional Design). The project gives you experience applying the fundamentals you learn in the modules to a larger, more authentic context. It will be graded by the instructor, and you will receive personalized feedback.

Meet the instructor

Gautam Yadav

Gautam Yadav

Senior Learning Engineer
Carnegie Mellon University

Gautam Yadav is a Senior Learning Engineer at Carnegie Mellon University’s School of Computer Science. He designs online and blended learning experiences that help learners apply learning science, data analytics, and AI-supported tools to real educational challenges. Across LearnLab certificate programs, he focuses on creating practical, evidence-based courses that support meaningful learner progress and scalable course improvement.
View profile

Where to go next