Learn AI Create the Future — with Pranay
Main site

All sections

The whole curriculum, grouped into 14 areas. Start at the top if you are new. If you came here for one thing, filter to its area or search — everything is on this page or one click from it.

Every lesson here is written by .

14 areas 117 sections 1,162 of 1,167 lessons published 10 new lessons every day

Showing Generative AI and LLMs — 4 sections, 44 lessons. Show all 14 areas

Generative AI and LLMs

Models that write, draw and answer questions — and how to build a real product on top of them.

4 sections 44 of 44 lessons published

Generative AI

LLMs, prompts, RAG and agents — the AI everyone is talking about.

12 published

  1. What is a large language model?
  2. How LLMs actually work
  3. Prompt engineering
  4. Context windows
  5. Temperature and sampling
  6. What is RAG?
  7. Vector databases
  8. Fine-tuning
  9. LoRA
  10. AI agents
  11. Diffusion models
  12. Hallucination

LLM Development

The tools you use to actually build things with language models.

8 published

  1. Hugging Face
  2. Ollama — run LLMs locally
  3. vLLM
  4. LangChain
  5. LlamaIndex
  6. Function calling and tools
  7. Structured output
  8. Model deployment

Multimodal AI

Models that handle text, images, audio and video together instead of one at a time.

12 published

  1. What is multimodal AI?
  2. Multimodal embeddings
  3. CLIP
  4. Vision-language models
  5. Image captioning
  6. Visual question answering
  7. Text to image
  8. Text to video
  9. Document AI
  10. Cross-modal retrieval
  11. Audio-visual learning
  12. Multimodal RAG

Agentic Frameworks

The frameworks people build real agents with — LangGraph, MCP, multi-agent systems — and how to evaluate what you built.

12 published

  1. LangGraph — agents as graphs
  2. State and checkpoints in LangGraph
  3. CrewAI — role-based agent teams
  4. AutoGen — conversational multi-agent systems
  5. MCP — the Model Context Protocol
  6. DSPy — programming, not prompting
  7. smolagents — code-acting agents
  8. Designing good tools for agents
  9. Agent memory
  10. Human-in-the-loop agents
  11. Evaluating agents
  12. Orchestrating multiple agents

Other ways to use this site

Learning paths

An ordered route through the lessons for one job: ML developer, AI engineer, computer vision engineer.

Projects

Build real things with full code, a dataset and a deployment guide.

AI glossary

Every term you keep seeing, defined in one plain sentence first.

Error database

Paste the error you got. Find out what it means and how to fix it.