Open Source Learning Material
Generative AI & Agentic AI: A Hands-on Journey
A comprehensive, 5-day hands-on curriculum designed by Akshar Prabhu Desai. Master LLM application building, LangGraph orchestration, multi-agent workflows, and AI research tools.
View Details & Agenda →Agentic AI Bootcamp: One-Day Immersive
An intensive, hands-on developer bootcamp designed by Akshar Prabhu Desai. Master ReAct control loops, tool calling, LangGraph state-machines, and multi-agent systems in a single day.
View Details & Agenda →Getting Started Guide
A step-by-step introduction to implementing your first agentic protocol.
Start Here →Glossary of Agentic AI
Reinforcement Learning
A machine learning paradigm where an AI agent learns to make decisions by performing actions in an environment to maximize cumulative rewards. Through trial and error, the agent receives feedback in the form of rewards or penalties, enabling it to optimize its strategy (policy) for complex tasks over time.
Context Window
The maximum amount of text (measured in tokens) that a Large Language Model can process and consider at any single time during prompt execution and generation. It includes both the input prompt (instructions, system prompts, retrieved data) and the model's generated output, defining the boundary of the model's active memory.
Tokenization
The process of breaking down a sequence of text into smaller, meaningful units called tokens, which can be words, characters, or subwords. Tokenization serves as the essential first step in preparing raw text data for numerical processing by neural network models.
RAG (Retrieval-Augmented Generation)
An architectural pattern that enhances a generative Large Language Model by fetching relevant, up-to-date information from external data sources (such as vector databases, documents, or APIs) and injecting it into the prompt context. This allows the model to answer queries using specific, verified facts, reducing the risk of hallucinations.