Gen AI & AI Agents

What is an Application?

Definition and examples of applications across platforms (desktop, web, mobile).

Types of Applications

Native, web, hybrid, microservices and serverless app types.

Web Application Fundamentals

Client-server model, request/response lifecycle, REST and APIs.

Web Technologies

Frontend: HTML, CSS, JavaScript, React.

Backend: Python, Java, Node.js.

Databases: SQL (MySQL, PostgreSQL), NoSQL (MongoDB).

Software Development Life Cycle (SDLC)

Phases: Planning, Analysis, Design, Implementation (Coding), Testing, Deployment, Maintenance.

Application Development Methodologies

Agile: Core principles, Scrum, Kanban.

Waterfall model overview and differences vs Agile.

What is Data?

Understanding raw facts, measurements, and observations used to derive information.

Types of Data

Structured, unstructured, semi-structured, categorical, numerical, time-series.

Data Storage

File systems, relational databases, NoSQL stores, data lakes, warehouses.

Data Analysis

Exploratory data analysis, visualization, basic statistics and summarization.

Data Engineering

ETL/ELT processes, pipelines, batch vs streaming, data quality and lineage.

Data Science

Model building, evaluation, feature engineering and deployment basics.

The Importance of Computing Power

Compute enables data processing, model training, and real-time services.

Key Computing Technologies

CPU: architecture, cores, threads, clock speed.

GPU: parallel processing for graphics and deep learning workloads.

Cloud Computing

What is the Cloud? Shared infrastructure, on-demand resources, pay-as-you-go.

Cloud Service Models

IaaS: virtual machines, storage, networking.

PaaS: managed runtimes, app platforms.

SaaS: software delivered over the web (examples and use-cases).

What is Artificial Intelligence (AI)?

Overview, goals and historical perspective.

How AI Works

Data, models, training, inference and evaluation loop.

Key Concepts

Machine Learning (ML) and Deep Learning (DL) basics.

Generative AI

What is Generative AI? Models that create text, images, audio and code.

Examples: Large Language Models (LLMs), image generation networks.

AI in Everyday Learning

Use-cases in education, productivity tools and personalized learning.

Customer Relationship Management (CRM)

Overview of CRM systems and typical features.

Human Resource Management Systems (HRMS)

Payroll, attendance, talent management basics.

Retail & E-Commerce

Online storefronts, payments, inventory and recommendation engines.

Healthcare

Electronic health records, telemedicine, AI in diagnostics.

Introduction to Python

Real-world applications and ecosystem overview (libraries and use-cases).

Installation & Environment

Installing Python, virtual environments, pip, conda basics.

Basic Syntax

Variables, data types, operators, input/output and script execution.

Conditionals & Loops

if, elif, else; for and while loops; break/continue/pass.

Functions

Defining functions, arguments, return values and best practices.

Advanced Function Concepts

Lambda functions, map/filter/reduce, modular programming.

Strings

Slicing, formatting and common methods.

Collections

Lists, Tuples, Sets, Dictionaries; mutability and iteration.

Advanced Techniques

Nested structures, comprehensions, iterators and generators.

File Operations

read, write, append, and context managers using with.

Working with Data Files

Handling CSV and Excel files using csv and pandas libraries.

Exceptions

try/except/finally/else, raising exceptions and creating custom exceptions.

Regular Expressions

Pattern matching for validation and text processing.

OOP Fundamentals

Classes, objects, attributes, methods, constructors and destructors.

Advanced OOP

Inheritance, polymorphism, encapsulation and abstraction.

Additional Concepts

Decorators, property methods, and combining OOP with file handling in a capstone project.

What is AI?

Evolution, objectives and subfields overview.

Types of AI

Narrow AI, General AI and Super AI explained at a conceptual level.

Key Subfields

ML, DL, NLP, Robotics, Expert Systems and their real-world impact.

Ethics & Bias

Responsible AI, fairness, privacy and governance basics.

ML Overview

Supervised, unsupervised and reinforcement learning categories.

Core Concepts

Features, labels, training/testing splits, overfitting and underfitting.

Algorithms & Metrics

Linear/Logistic Regression, K-Means, Decision Trees; accuracy, precision, recall, F1-score.

Deep Learning Basics

What DL is and how it extends ML with deeper architectures.

Neural Network Anatomy

Neurons, layers, activations, forward/back propagation (high level).

Architectures & Frameworks

CNNs, RNNs, Transformers; intro to TensorFlow, PyTorch and Keras.

Language Data

Text preprocessing, tokenization and normalization techniques.

Embeddings & Models

Word2Vec, GloVe and contextual embeddings overview.

NLP Tasks

Text classification, NER, sentiment analysis, summarization and QA systems.

From Traditional AI to GenAI

Differences between predictive models and generative models.

Enabling Factors

Role of quality data, compute and model architectures for GenAI.

Responsible AI & Governance

Data governance, bias mitigation and ethical considerations.

NN Refresher

Perceptrons, feedforward networks and training basics.

Sequence Modeling Limits

RNN/LSTM/GRU limitations and vanishing gradients motivating attention.

Attention Intuition

How attention helps focus on relevant parts of input data.

QKV & Scaled Dot-Product

Queries, Keys, Values and how scaled dot-product attention is computed.

Self-Attention vs Cross-Attention

Differences and when each is used.

Encoder-Decoder Overview

Roles of encoder and decoder stacks in sequence-to-sequence tasks.

Multi-Head Attention

Parallel attention heads and why they help representation learning.

Other Components

Feed-forward layers, residual connections and layer normalization.

Architecture Types

Encoder-only (BERT), decoder-only (GPT) and encoder-decoder (T5) families.

Tokenization & Embeddings

Tokenizers, positional encodings and embedding strategies.

Implementation

Building transformers with PyTorch and Hugging Face Transformers (high-level steps).

Transformers to LLMs

How transformer architectures scale into large language models.

Fine-tuning & Transfer Learning

Strategies for adapting pre-trained models to downstream tasks.

Limitations & Ethics

Bias, hallucination, compute costs and ethical deployment practices.

What is Generative AI?

Definition and differentiation from discriminative models.

Architectures

GANs, VAEs, Diffusion models and LLMs overview.

Popular Tools

ChatGPT, Claude, Midjourney, DALL·E, Copilot and their use-cases.

Prompt Principles

Zero-shot, few-shot and instruction-based prompting techniques.

Advanced Prompting

Chain-of-thought, self-consistency and iterative refinement approaches.

Evaluation & Debugging

How to measure prompt effectiveness and iterate on prompts.

Model Families

GPT, T5, LLaMA, Gemini and their typical use-cases.

Training & Fine-tuning

Pre-training objectives, transfer learning and adapters.

Limitations

Hallucinations, context/window limits and resource constraints.

Key Libraries

Hugging Face Transformers, OpenAI API, Cohere and supporting tooling.

Workflow Automation

Using n8n or Zapier to automate model calls and post-processing.

Experimentation Environments

Running experiments in Colab, Jupyter and local setups.

Content Generation

Generating text, images, code and multimedia with GenAI.

Deployment Choices

Cloud vs on-premise model serving, latency and cost trade-offs.

Capstone

Build and deploy a mini GenAI app integrating an API and frontend.

Agent Definition

Characteristics, lifecycle and autonomy levels of agents.

Agent Types

Reactive, goal-based, deliberative and hybrid agents with examples.

Knowledge Representation

Rules, ontologies and knowledge graphs for agent reasoning.

Decision-Making

Utility-based planning, goal-oriented strategies and feedback loops.

Learning Paradigms

Supervised, unsupervised and reinforcement learning in agents.

Coordination & Communication

Strategies for agent negotiation, collaboration and resource allocation.

Simulation Environments

Tools and frameworks for simulating multi-agent workflows.

Agent Frameworks

CrewAI, LangChain, LangGraph, AutoGen overview and when to choose each.

Orchestration Tools

n8n, Zapier and other workflow tools to glue agents and APIs.

Design Patterns

Designing goal-oriented and collaborative agent systems for scale.

Deployment & Ethics

Cloud deployment, scaling, and safety/ethical guardrails for agents.

What is RAG?

Retrieval-Augmented Generation concept and benefits for grounded responses.

Vector DBs Overview

Purpose of vector stores and how embeddings power semantic search.

Embeddings

Word, sentence and document vectors and how they're generated.

Similarity Measures

Cosine similarity, Euclidean distance and practical considerations.

Popular Platforms

Pinecone, Weaviate, Milvus, FAISS overview and pros/cons.

Indexing & Retrieval

Index types, ANN methods and CRUD operations on vector data.

Integration Patterns

Connecting LLMs to vector DBs for context retrieval and prompt augmentation.

Prompting Strategies

Building prompts that include retrieved context and managing token budgets.

Hybrid Search

Combining embeddings with keyword search for robustness.

Production Considerations

Latency, caching, scaling and monitoring RAG systems.