Comprehensive AI Bootcamp

A grounding in what AI actually is, followed by the Python skills every later module depends on.

Core Topics

• What is AI? AI vs ML vs DL vs Generative AI
• AI use cases across business, cybersecurity, finance, healthcare, marketing and operations
• Python environment setup: VS Code/Jupyter/Google Colab; packages and virtual environments
• Python essentials: variables, data types, operators, conditions, loops, functions
• Collections, comprehensions, modules, exceptions and file handling
• Object-oriented programming essentials for AI projects
• Working with APIs, JSON and HTTP requests
• Git and GitHub fundamentals; project structure and README writing

The data-handling skills that sit beneath every AI system: cleaning, exploring and preparing real data.

Core Topics

• NumPy arrays, vectorization and numerical operations
• Pandas Series/DataFrames, indexing, filtering, joins and groupby
• Data cleaning: missing values, duplicates, outliers and inconsistent data
• Exploratory Data Analysis (EDA)
• Visualization with Matplotlib and Seaborn concepts
• Feature types, encoding, scaling and train/test splitting
• Data leakage and common data-quality mistakes
• SQL essentials for AI data pipelines

The full ML workflow, from problem framing to evaluation, across the algorithms used most in practice.

Core Topics

• ML workflow: problem framing → data → features → model → evaluation → deployment
• Supervised vs unsupervised learning
• Linear and logistic regression
• Decision trees, random forests and gradient boosting concepts
• K-Nearest Neighbors and Support Vector Machines
• Clustering: K-Means and hierarchical clustering concepts
• Dimensionality reduction: PCA
• Feature engineering and feature selection
• Cross-validation, hyperparameter tuning and pipelines
• Metrics: MAE, MSE, RMSE, R², accuracy, precision, recall, F1, ROC-AUC
• Imbalanced datasets and threshold selection
• Model interpretation and error analysis

From a single neuron to Transformers — how neural networks learn, and how to train them.

Core Topics

• Neural networks: neurons, layers, weights, activation functions
• Forward propagation, loss functions and backpropagation
• Gradient descent and optimization
• Overfitting, regularization, dropout and batch normalization
• PyTorch/TensorFlow ecosystem overview
• Building and training a basic neural network
• CNN fundamentals for image classification
• Transfer learning and pretrained models
• Sequence data and introduction to RNN/LSTM concepts
• Introduction to attention and why Transformers changed AI

Working directly with modern LLMs — prompting, APIs, structured outputs and evaluation.

Core Topics

• Generative AI landscape: text, image, audio, video and multimodal systems
• LLM fundamentals: tokens, context windows, parameters and inference
• Transformer architecture at a practical conceptual level
• Prompt engineering: zero-shot, few-shot, role/context/task patterns
• Structured prompting, JSON outputs and schema-driven generation
• System prompts, instruction hierarchy and context management
• LLM APIs: authentication, requests, retries, rate limits and cost awareness
• Text summarization, classification, extraction and transformation
• Function/tool calling and external data access
• Embeddings and semantic similarity
• Open-source models and Hugging Face ecosystem
• LLM evaluation: relevance, factuality, consistency and task success
• Hallucinations, prompt injection and data privacy basics

Grounding LLMs in real documents and data through retrieval-augmented generation.

Core Topics

• Why RAG? Limitations of standalone LLMs
• Document ingestion and parsing
• Chunking strategies and metadata design
• Embeddings and vector representations
• Vector databases and similarity search concepts
• Retrieval strategies: semantic, keyword and hybrid search
• RAG pipeline: ingest → embed → retrieve → augment → generate
• Source citations and answer grounding
• RAG quality evaluation and retrieval debugging
• Conversational memory and context management
• RAG security: access control, prompt injection and sensitive information

Building controlled, tool-using agent workflows for real business automation.

Core Topics

• What is an AI agent? Workflow vs agent distinction
• Agent architecture: model, tools, memory, planning and execution
• Tool/function calling
• Multi-step reasoning workflows and state management
• Agent frameworks and orchestration concepts
• Human-in-the-loop approval workflows
• Browser/API/database/tool integrations
• Agent reliability, guardrails and failure recovery
• Business automation use cases: research, reporting, support, lead processing and operations
• Building controlled agent workflows rather than unconstrained autonomous systems

Turning notebooks into deployable, monitored applications people can actually use.

Core Topics

• Turning notebooks into applications
• FastAPI fundamentals for AI APIs
• Streamlit-style interfaces for rapid AI prototypes
• Environment variables, secrets and configuration
• Docker fundamentals and containerizing an AI app
• Cloud deployment concepts and architecture
• Model serving and API integration patterns
• Logging, monitoring, latency and cost tracking
• Model/version management and reproducibility
• Basic CI/CD concepts for AI projects
• Responsible AI: privacy, bias, security, governance and human oversight

Bringing everything together into one demo-ready AI product and a portfolio to show for it.

Core Topics

• Problem discovery and business requirement definition
• Dataset/source identification and solution architecture
• Implementation sprint
• Evaluation and testing
• UI/API integration
• Deployment/demo preparation
• Documentation: README, architecture diagram, setup guide and limitations
• Presentation: problem → approach → demo → results → business value → future roadmap
• Portfolio and interview preparation