BEGINNER
AI agents explained: Build your first agent in 8 minutes
Learn to build your own ai agent in no time
1 topics0.13 hrs
FREE AI COURSES
Learn AI. Get Certified.
Structured courses with video lessons, hands-on exercises, and assessments. Complete a course to earn a verifiable certificate you can share anywhere.
3 Courses
3 Topics
Free Certificates
All Levels:
Beginner
Intermediate
Advanced
INTERMEDIATE
Introduction to RAG
RAG (Retrieval-Augmented Generation) RAG enables AI assistants to answer questions using large document collections that exceed an LLM's context window. Instead of reading all documents at once, it retrieves only the most relevant information. How it works: 1. Retrieval: Convert documents into vector embeddings and use semantic search to find relevant content. 2. Augmentation: Add the retrieved information to the AI's prompt. 3. Generation: The AI generates an accurate response based on the retrieved context. For good performance, RAG requires proper chunking, embedding model selection, and retrieval settings.
1 topicsCertificate
BEGINNER
Learn Basic of AI
This video, presented by Andrej Karpathy, provides a comprehensive, hands-on tutorial on building a Generatively Pretrained Transformer (GPT) from scratch using Python and PyTorch. The lecture demystifies the technology behind systems like ChatGPT by walking through the implementation of a decoder-only Transformer architecture. Key Highlights of the Tutorial: Foundations of Language Modeling (0:07:52 - 0:34:53): The process begins with setting up the environment, exploring the Tiny Shakespeare dataset, and implementing a simple bigram language model as a baseline. Building Self-Attention (0:42:13 - 1:19:11): This is the core of the video, where the viewer learns how tokens communicate. It progresses from simple averaging (bag of words) to scaled self-attention using matrices, explaining how queries, keys, and values enable data-dependent interactions. Constructing the Transformer (1:19:11 - 1:42:39): The model is scaled up by implementing multi-headed attention, feedforward layers, residual connections, and layer normalization to stabilize training. Context and Theory (1:42:39 - 1:56:20): Karpathy discusses the difference between encoder and decoder blocks, briefly walks through the nanoGPT codebase, and explains the two-stage process (pre-training followed by fine-tuning/RLHF) required to create a production-ready assistant like ChatGPT.
1 topics2 hrsCertificate
Already have a certificate?
Enter your certificate ID to verify its authenticity and share it with employers.
How Our Courses Work
Learning AI shouldn't feel like drinking from a firehose. Our courses are structured into logical topics that build on each other — starting from fundamentals and progressively introducing more advanced concepts. Each topic includes a mix of video lessons, written explanations, and practical exercises so you can learn in the style that suits you best.
Every course culminates in a final assessment that tests your understanding of the material. Pass the assessment and you'll earn a unique, verifiable certificate with a permanent ID — proof of competence you can share with employers, clients, or on LinkedIn. You get up to three attempts per month, with scores tracked so you can see your improvement over time.
Courses span beginner to advanced levels and cover topics from basic prompt engineering to complex multi-tool automation systems. All content is free — our goal is to build a structured community of AI-literate professionals who can implement these tools in real work, not just talk about them.
We strive to bring you the best free learning content available. Some videos and materials featured here are created by independent creators and remain subject to their respective copyrights. TRONLAB does not claim ownership of third-party content. If you are a content owner and would like your material removed, please contact us.