Day 1
Python Programming & AI Developer Productivity
Module 1: Modern AI Development Landscape
- Introduction to AI Engineering
- AI vs Machine Learning vs Deep Learning
- Python for AI Development
- AI Development Lifecycle
- Choosing the Right AI Stack
- Overview of Modern AI Coding Assistants
- Setting up an AI Development Environment
Introduction to
- ChatGPT
- ChatGPT Projects
- GitHub Copilot
- Claude
- Claude Artifacts
- Cursor AI
- Windsurf
- Google AI Studio
- Gemini Gems
- Continue.dev
Hands-on Lab
- Configure Python environment
- Install required libraries
- Configure AI coding assistants
Module 2: Python Programming for Machine Learning
- Variables
- Data Types
- Operators
- Conditional Statements
- Loops
- Functions
- Modules
- Exception Handling
- File Handling
- Object-Oriented Programming
- Virtual Environments
Python Best Practices
Hands-on Lab
Build several Python mini applications.
Module 3: Data Analysis with Python
Libraries
Topics
- Importing datasets
- Cleaning data
- Missing values
- Duplicate handling
- Feature selection
- Data transformation
- Grouping
- Aggregation
- Feature engineering
Hands-on Lab
Perform complete data preprocessing on a real-world dataset.
Module 4: Exploratory Data Analysis (EDA)
Libraries
- Matplotlib
- Plotly
- Scikit-learn utilities
Topics
- Statistical summaries
- Correlation analysis
- Outlier detection
- Feature importance
- Data visualization
- Business insights
Hands-on Lab
Create an EDA report and visualization dashboard.
Day 2
Machine Learning Fundamentals
Module 5: Supervised Machine Learning
Topics
Regression
- Linear Regression
- Multiple Regression
Classification
- Logistic Regression
- Decision Tree
- Random Forest
- K-Nearest Neighbors
- Support Vector Machine
- Naïve Bayes
Concepts
- Training and testing
- Cross-validation
- Overfitting
- Underfitting
Hands-on Lab
Train multiple supervised learning models and compare their performance.
Module 6: Unsupervised Machine Learning
- Clustering
- K-Means
- Hierarchical Clustering
- DBSCAN
- Principal Component Analysis (PCA)
- Dimensionality Reduction
Applications
- Customer Segmentation
- Fraud Detection
- Pattern Discovery
- Recommendation Systems
Hands-on Lab
Cluster a business dataset and interpret the results.
Module 7: Model Evaluation & Optimization
Classification Metrics
- Accuracy
- Precision
- Recall
- F1 Score
- ROC Curve
- AUC
Regression Metrics
Model Improvement
- Hyperparameter tuning
- Grid Search
- Feature selection
- Feature scaling
- Pipeline creation
Hands-on Lab
Optimize machine learning models and compare performance improvements.
Module 8: AI-Assisted Coding & Intelligent Development
Using AI to
- Generate Python code
- Debug applications
- Refactor legacy code
- Write documentation
- Create unit tests
- Explain algorithms
- Generate SQL queries
- Build APIs
- Review pull requests
Using
- GitHub Copilot
- ChatGPT Projects
- Claude Artifacts
- Cursor AI
- Windsurf
- Google AI Studio
Hands-on Lab
Develop an AI-assisted Python application from requirements to implementation.
Day 3
AI Engineering, Automation & Capstone Project
Session 1 — AI-Powered Automation & Developer Productivity
- Prompt engineering for developers
- AI-assisted code generation
- Workflow automation
- Documentation automation
- Test case generation
- API development assistance
- AI-powered debugging
- Code review automation
- Building reusable developer workflows
Productivity Tools
- GitHub Copilot
- ChatGPT Projects
- Claude Artifacts
- Google AI Studio
- Gemini Gems
- Manus AI
- Kimi AI
- Perplexity AI
- Continue.dev
- VS Code AI extensions
Hands-on Lab
Automate repetitive development tasks using AI.
Session 2 — Building Intelligent Applications
- End-to-end machine learning workflow
- Model serialization with Joblib
- Creating prediction scripts
- Building simple REST APIs with FastAPI or Flask
- Integrating machine learning models into applications
- Introduction to MLOps concepts
- Responsible AI for developers
Hands-on Lab
Expose a trained machine learning model through an API and test predictions.
Session 3 — Capstone Project
Participants work in teams to build a complete AI solution, including:
- Data preparation
- Exploratory Data Analysis
- Feature engineering
- Machine learning model selection
- Model evaluation
- API integration
- AI-assisted documentation
- Presentation preparation using AI tools
Suggested project domains include finance, HR, healthcare, retail, or customer analytics.
Session 4 — Project Presentation, Future Trends & Wrap-Up
Topics
- Team project presentations
- Peer review and feedback
- Best practices for AI engineering
- Emerging trends in AI-assisted software development
- AI agents and autonomous coding
- Multimodal AI
- Retrieval-Augmented Generation (RAG)
- Agentic AI frameworks
- Personal learning roadmap and certification pathways