Course Syllabus

1. TW‑GenAI‑Python (8 h)
   • Overview: Python-centric generative AI techniques—prompt engineering, model APIs, ecosystem tools.
   • Hands-on: Build basic content generators, fine-tune small LLMs, manage prompt‐based workflows.
2. AIML Foundations (6 h)
   • Theory: Essential AI/ML concepts—supervised/unsupervised learning, model evaluation, feature engineering.
   • Workshop: Train and evaluate ML models using scikit‑learn
3. NLP Techniques (8 h)
   • Core Concepts: Tokenization, embeddings, sequence modeling, sentiment analysis, transformers.
   • Lab Work: Use NLTK for text preprocessing ; build a sentiment classifier.
4. Computer Vision (6 h)
   • Fundamentals: Convolutional neural networks, image augmentation, object detection.
   • Practical: Employ pre­trained models for image classification; implement inference pipelines.
5. Agentic AI Frameworks (12 h)
   • Concepts: Agent architecture, memory, multi‐agent coordination, tool integration .
   • Implementation: Build Python agents—
     • Module: Agent Loop & G.A.M.E. fundamentals
     • Tool & function‑calling integration,
     • Multi-agent workflows (LangChain, LangGraph).

6. Capstone Project (6 h)
   • Real-world Agent: Combine modules—e.g., NLP + CV agent for document/image analysis and task automation.

• Key Features

    Hands-on labs & assignments: Apply theory to real-world projects.

    Guided tool integration: Work with OpenAI APIs, LangChain, HuggingFace.

    Modular learning: Build transferable agent architectures from scratch.

    AI ethics & safety: Design guardrails and bias checks.

    Capstone showcase: Present integrated agent solution.