Generative AI
A 31-part beginner-to-advanced course that explains how large language models work and builds up to RAG, AI agents, and production AI systems, without heavy math.
Learn from: the original creator. Original content published on YouTube. DigitalSkillX organizes these public resources into a structured learning path. DigitalSkillX does not claim ownership or partnership.
Now playing: How AI Actually Works - No Code | AI Explained #1
This free learning path follows a 31-video course by Manoj that walks through generative AI and large language models from the ground up. It starts with how LLMs work, including tokens, transformers, and embeddings, then moves into training, fine-tuning, prompting, and RAG. The later lessons cover AI agents, memory, caching, and safety. The course is aimed at software engineers moving into AI, product managers who want to understand the terminology, and beginners starting from zero. Lessons are meant to be watched in order because each one builds on the previous. No advanced math is required.
Beginners who want a structured free introduction before deeper practice.
Lesson 1: How AI Actually Works - No Code | AI Explained #1
This opening lesson explains how AI works, focusing on large language models like ChatGPT, without any code. It uses analogies to describe the AI black box and how these systems make decisions. It sets the foundation for the rest of the course.
Open on YouTubeLesson 2: AI Tokenization Explained Simply | AI Explained #2
This lesson covers tokenization, the process of splitting text into pieces that a model can process. It explains why AI sometimes makes simple math or spelling mistakes. The goal is to understand token boundaries without needing a math background.
Open on YouTubeLesson 3: Transformer Models & Attention Explained | AI Explained #3
This lesson breaks down transformer architecture and the self-attention mechanism. It avoids heavy formulas and uses a crowded cocktail party analogy to explain attention. It helps learners read transformer diagrams with more confidence.
Open on YouTubeLesson 4: The AI Masterclass | Part 4 | Finally Understand AI Memory | Embeddings | #artificialintelligence
This lesson explains embeddings and how AI represents meaning as vectors. It translates semantic vector space into a large 3D map that is easier to picture. It also covers how this relates to AI memory.
Open on YouTubeLesson 5: The AI Masterclass | Part 5 | Choosing an AI Model for Complete Beginners | #artificialintelligence
This lesson helps beginners choose between AI models such as Llama and GPT-4. It addresses the problem of many new models launching each week. It gives practical guidance on matching a model to a use case.
Open on YouTubeLesson 6: The AI Masterclass | Part 6 | Why AI Can Be Slow? | Inference | #artificialintelligence
This lesson explains inference and why AI responses can be slow. It looks at latency in AI applications and why some answers appear instantly while others take time. It helps developers think about performance.
Open on YouTubeLesson 7: The AI Masterclass | Part 7 | The Truth About AI Pricing and Costs | #artificialintelligence
This lesson covers AI pricing and costs, including API pricing tiers. It explains hidden costs and how to budget for an AI project. It is aimed at anyone planning to build with paid AI APIs.
Open on YouTubeLesson 8: The AI Masterclass | Part 8 | Finally Understand How AI is Trained | #artificialintelligence
This lesson explains how AI models are trained from scratch. It traces the pretraining process, from data collection to the finished model. It gives a high-level view of how companies build systems like ChatGPT.
Open on YouTubeLesson 9: The AI Masterclass | Part 9 | Fine Tuning AI for People Who Hate Math | #artificialintelligence
This lesson explains fine-tuning without requiring advanced math. It shows how developers customize a model for specific behavior. It is meant for people who find the term intimidating.
Open on YouTubeLesson 10: The AI Masterclass | Part 10 | Understand LoRA & Local AI Shrinking Models | #artificialintelligence
This lesson covers LoRA and techniques for shrinking models to run locally. It explains the hardware demands of AI and how smaller models can still be useful. It focuses on the ideas behind the methods rather than the math.
Open on YouTubeLesson 11: The AI Masterclass | Part 11 | AI Alignment for Complete Beginners | RLHF | #artificialintelligence
This lesson introduces AI alignment and methods like RLHF and DPO. It explains how human trainers shape the behavior of large models. It is written for beginners who are new to AI safety terminology.
Open on YouTubeLesson 12: The AI Masterclass | Part 12 | AI Distillation & Synthetic Data Explained | #artificialintelligence
This lesson explains AI distillation and synthetic data. It looks at how large models can teach smaller ones, which helps models run on phones and other limited devices. It covers the basic idea without deep math.
Open on YouTubeLesson 13: The AI Masterclass | Part 13 | Prompt Engineering for Complete Beginners | #artificialintelligence
This lesson covers the fundamentals of prompt engineering for beginners. It focuses on how to get better responses and stop fighting with the model. It is a starting point for the prompting lessons that follow.
Open on YouTubeLesson 14: The AI Masterclass | Part 14 | Finally Understand Few-Shot AI Prompting | #artificialintelligence
This lesson explains few-shot prompting, where a few examples are given to guide the model. It shows how a small number of examples can change the output significantly. It builds on the basic prompting lesson.
Open on YouTubeLesson 15: The AI Masterclass | Part 15 | How AI Reasons | Chain & Tree of Thought | #artificialintelligence
This lesson covers reasoning techniques such as chain-of-thought and tree-of-thought. It explains how asking a model to think step by step can improve results on logic and math tasks. It focuses on practical prompting.
Open on YouTubeLesson 16: The AI Masterclass | Part 16 | AI Context Limits Explained Simply | #artificialintelligence
This lesson explains context windows and why AI can forget earlier parts of a conversation. It covers how to structure text so the model keeps the important information. It is useful for anyone building chat applications.
Open on YouTubeLesson 17: The AI Masterclass | Part 17 | Hack Proofing Your AI | Prompt Injection | #artificialintelligence
This lesson introduces prompt injection and AI security risks. It explains how attackers can trick a model into ignoring instructions. It also covers basic steps to protect an AI application.
Open on YouTubeLesson 18: The AI Masterclass | Part 18 | Finally Understand RAG | #artificialintelligence
This lesson introduces retrieval-augmented generation, often called RAG. It explains how to let a model use external data to answer questions. It is presented as a core architecture in modern AI applications.
Open on YouTubeLesson 19: The AI Masterclass | Part 19 | Data Chunking for RAG Explained Simply | #artificialintelligence
This lesson covers data chunking, the process of splitting documents for RAG. It explains why chunking matters for retrieval quality. It is aimed at people preparing data for an AI system.
Open on YouTubeLesson 20: The AI Masterclass | Part 20 | Vector Databases for People Who Hate Math | #artificialintelligence
This lesson explains vector databases without heavy math. It covers where and how semantic data is stored for retrieval. It compares the idea to traditional databases in simple terms.
Open on YouTubeLesson 21: The AI Masterclass | Part 21 | Hybrid Search for People Who Hate Math | #artificialintelligence
This lesson covers hybrid search, which combines keyword matching with semantic search. It explains why this can improve search results in AI applications. It is presented without requiring math background.
Open on YouTubeLesson 22: The AI Masterclass | Part 22 | Finally Understand AI Reranking | #artificialintelligence
This lesson explains reranking, a second stage in the search pipeline. It shows how results are reordered from best to worst before being passed to the model. It addresses why AI sometimes misses relevant context.
Open on YouTubeLesson 23: The AI Masterclass | Part 23 | GraphRAG Explained for Complete Beginners | #artificialintelligence
This lesson introduces GraphRAG for beginners. It explains how graph-based retrieval helps AI understand relationships between pieces of information. It is positioned as a more advanced retrieval technique.
Open on YouTubeLesson 24: Autonomous AI Agents & Agentic RAG Explained (AI Explained #24)
This lesson introduces autonomous AI agents and agentic RAG. It explains what makes an agent different from a standard chatbot. It is written for people who are new to the topic.
Open on YouTubeLesson 25: How AI Agents Use Tools - ReAct Loop Explained (AI Explained #25)
This lesson explains how AI agents use tools through the ReAct loop. It shows how an agent can use a browser, calculator, or database. It covers the basic pattern behind tool use.
Open on YouTubeLesson 26: AI Explained: Multi-Agent AI Systems for Complete Beginners (Part 26)
This lesson introduces multi-agent AI systems. It explains how several specialized agents can work together on a large problem. It is aimed at beginners who want to understand the concept.
Open on YouTubeLesson 27: How AI Agents Remember - Agent Memory Explained (AI Explained #27)
This lesson covers agent memory and state tracking. It explains how advanced AI systems keep a persistent record of user preferences and past interactions. It focuses on the design ideas rather than code.
Open on YouTubeLesson 28: AI Explained: Short-Term vs Long-Term AI Memory Demystified (Part 28)
This lesson compares short-term and long-term AI memory. It explains the difference between fast context and larger persistent storage. It helps clarify how memory layers work together in an agent.
Open on YouTubeLesson 29: Semantic Caching for AI Agents Explained (AI Explained #29)
This lesson explains semantic caching for AI agents. It shows how caching similar requests can reduce cost and latency. It is presented as a practical optimization technique.
Open on YouTubeLesson 30: AI Errors & Human-in-the-Loop (HITL) Explained (AI Explained #30)
This lesson covers AI errors and the human-in-the-loop approach. It explains how to use autonomous agents more safely by keeping a person for final approval. It is aimed at reducing risk in agent workflows.
Open on YouTubeLesson 31: AI Explained: Securing AI Agents from Doing Bad Things (Part 31)
This final lesson covers securing AI agents, including sandboxing. It explains how to limit what an autonomous agent can do so it cannot cause damage. It closes the course with a focus on safety.
Open on YouTube0 of 31 lessons completed (0%).
Complete this learning path to become eligible for your DigitalSkillX certificate.
Cloud AI
AWS Certified Generative AI Developer Professional (AIP-C01) Free Learning Path
A free, hands-on path through Amazon Bedrock, RAG, vector stores, guardrails, and AI agents, built from Pratik Joshi's AIP-C01 course playlist.
Generative AI
Generative AI for JavaScript Developers: LangChain, RAG, Pinecone and LangSmith
A free video course that takes JavaScript developers from Generative AI basics to building AI apps with LangChain, RAG, Pinecone and LangSmith.
Generative AI
Generative AI Foundations with igmGuru
A beginner-friendly video path through Generative AI basics, large language models, and practical use cases, built from igmGuru's Gen AI tutorial playlist.
Artificial Intelligence
Mastering Generative AI: From Foundations to Real-World Applications
A free learning path covering the core concepts, models, and practical skills in generative AI, from prompt engineering to building real applications.