Day 1: Overview of Generative AI

Learning Objectives:

• Understand what Generative AI is and how it differs from traditional AI.

• Explore its history, growth, and current applications.

• Identify industries adopting Generative AI.

Topics:

• Evolution of AI → Generative AI.

• Core concepts: Generative vs. Discriminative AI.

• Applications: Text, Images, Audio, Video, and Code.

• Real-world case studies (ChatGPT, DALL·E, Copilot, etc.).

Activities:

• Group discussion: “How AI is changing our everyday lives.”

• Short quiz on AI basics.

Day 2: Large Language Models (LLMs) & Tools

Learning Objectives:

• Learn the fundamentals of LLMs.

• Understand their architecture and training process.

• Explore common generative AI tools.

Topics:

• What are LLMs? (GPT, BERT, LLaMA, etc.).

• Training methods: Transformers, self-attention, fine-tuning.

• Key platforms: OpenAI, Gemini, Claude, Perplexity, GitHub Copilot, MidJourney, etc.

• APIs & integrations.

Activities:

• Hands-on demo: Interact with ChatGPT and Google Gemini.

• Exercise: Compare answers from two different tools.

Day 3: Prompt Engineering & Responsible AI

Learning Objectives:

• Learn the art of writing effective prompts.

• Understand the role of prompt engineering in accuracy and creativity.

• Explore ethics and responsible use of AI.

Topics:

• Prompt structures: Zero-shot, few-shot, chain-of-thought.

• Techniques: Role prompting, context setting, constraints.

• Bias, misinformation, and hallucinations in AI.

• Responsible AI principles (fairness, accountability, transparency).

Activities:

• Hands-on: Write prompts for summarization, idea generation, and coding.

• Role play: “Ethical vs. unethical AI use case scenarios.”

Day 4: AI Use Cases, Multimodal AI & Software Development

Learning Objectives:

• Learn how AI is applied in technical workflows.

• Understand multimodal AI (text + image + speech).

• Explore AI’s role in software development lifecycle.

Topics:

• AI use cases for developers, analysts, finance, healthcare, education.

• Multimodal AI: Vision-Language models (GPT-4V, Gemini Pro Vision, etc.).

• AI in SDLC: Requirement gathering, code generation, testing, debugging.

• Tools for developers: GitHub Copilot, TabNine, Test automation.

Activities:

• Hands-on: Generate code snippets using Copilot.

• Case study: “AI-assisted bug fixing in real projects.”

Day 5: Hands-on Lab & Limitations

Learning Objectives:

• Apply all learnings in a practical lab.

• Understand challenges and limitations of Generative AI.

Topics:

• Lab session: End-to-end project (e.g., “Build a chatbot using OpenAI API” OR “Create an AI-generated report”).

• Limitations: Hallucinations, data dependency, lack of reasoning, security concerns.

• Future of Generative AI.

Activities:

• Group project presentations.

• Q&A and feedback session.

• Certification test.

Outcome of the 5-Day Training

Solid foundation in Generative AI concepts.
Practical exposure to LLMs, tools, and prompt engineering.
Awareness of ethical and responsible use of AI.
Hands-on experience with real-world AI applications.
Prepared for intermediate/advanced AI courses.