AI for University Students
This course introduces university students to Artificial Intelligence as a field, a set of tools, and a social force. Students will learn how AI and Large Language Models (LLMs) work, how to use them effectively and ethically, and how to apply them in their own disciplines. The course includes hands-on practice with prompt engineering, AI-assisted research, data analysis, automation, and critical evaluation of AI outputs. By the end of the course, students will be able to use AI tools responsibly for study, research, creativity, and problem-solving and will understand their limits, risks, and ethical implications. Basic of computer literacy is required for success
What You'll Learn
By the end of this course, students will be able to:
Explain core AI concepts, including machine learning, neural networks, LLMs, and generative AI.
Use AI tools critically and effectively for academic and professional tasks.
Design clear, reliable prompts using frameworks such as R-T-F, few-shot prompting, and chain of thought.
Evaluate AI outputs for accuracy, bias, hallucinations, and academic integrity risks.
Apply AI to a discipline-specific problem through a capstone project.
Discuss ethical, legal, and social issues related to AI.
Build simple AI-supported workflows using prompt chaining and retrieval-augmented generation (RAG).
Course Curriculum
- 🔒 Lesson 1.1: What Is AI?
- 🔒 Lesson 1.2: AI vs. ML vs. Deep Learning vs. Generative AI
- 🔒 Lesson 1.3: AI in University Life
- 🔒 Lesson 2.1: Data, Training, Inference, and Evaluation
- 🔒 Lesson 2.2: Types of Learning
- 🔒 Lesson 2.3: Overfitting, Underfitting, and Model Errors
- 🔒 Lesson 2.4: Neural Networks, Transformers, and Attention
- 🔒 Lesson 2.5: Why Deep Learning Changed AI
- 🔒 Lesson 3.1: Tokens, Parameters, and Context Windows
- 🔒 Lesson 3.2: Temperature, Top-P, and Controlling Randomness
- 🔒 Lesson 3.3: How LLMs Predict Text
- 🔒 Lesson 3.4: Strengths and Weaknesses of Major LLMs
- 🔒 Lesson 4.1: The Anatomy of a Prompt
- 🔒 Lesson 4.2: System, User, and Assistant Roles
- 🔒 Lesson 4.3: The R-T-F Framework
- 🔒 Lesson 4.4: Clarity, Specificity, and Constraints
- 🔒 Lesson 4.5: Zero-Shot, One-Shot, and Few-Shot Prompting
- 🔒 Lesson 4.6: Chain of Thought
- 🔒 Lesson 4.7: Delimiters
- 🔒 Lesson 4.8: Output Formatting: JSON, CSV, and Markdown
- 🔒 Lesson 5.1: Prompt Chaining
- 🔒 Lesson 5.2: Retrieval-Augmented Generation (RAG)
- 🔒 Lesson 5.3: AI Agents and Tool Use
- 🔒 Lesson 5.4: Building Simple AI Workflows
- 🔒 Lesson 6.1: AI for Literature Search and Summarisation
- 🔒 Lesson 6.2: Citation Caution and Verification
- 🔒 Lesson 6.3: AI Disclosure and Academic Integrity
- 🔒 Lesson 6.4: Brainstorming and Drafting with AI
- 🔒 Lesson 7.1: AI for Data Analysis
- 🔒 Lesson 7.2: Using AI to Learn Python, R, and SQL
- 🔒 Lesson 7.3: Debugging with AI
- 🔒 Lesson 7.4: No-Code and Low-Code AI Tools
- 🔒 Lesson 7.5: AI for Images, Audio, and Video
- 🔒 Lesson 7.6: Transcription, Translation, and Accessibility
- 🔒 Lesson 7.7: Risks( Deepfakes, Misinformation, and Copyright)
- 🔒 Lesson 8.1: Algorithmic Bias and Fairness
- 🔒 Lesson 8.2: Data Privacy and What Not to Share
- 🔒 Lesson 8.3: Copyright, Plagiarism, and AI-Generated Content
- 🔒 Lesson 8.4: University Policies on AI Use
- 🔒 Lesson 8.5: Hallucinations and How to Reduce Them
- 🔒 Lesson 8.6 — Prompt Injection and Jailbreaking
- 🔒 Lesson 8.7: Misinformation, Manipulation, and Security Risks
- 🔒 Lesson 9.1: AI for Personal Productivity
- 🔒 Lesson 9.2: AI Across Disciplines
- 🔒 Lesson 9.3: Building a Personal Prompt Library
- 🔒 Lesson 9.4: Course Close: Moving Forward with AI
Recent Reviews
No reviews yet.