Skip to content
learn
  1. Learn
  2. Learning paths

Build production LLM apps

Transformers, prompting, RAG, agents, evaluation and serving, end to end.

63 lessonsabout 14 hours

  1. 1 Multi-layer networks Machine Learning . ML-08.02 . Beginner . 14 min
  2. 2 Backpropagation Machine Learning . ML-08.06 . Intermediate . 20 min
  3. 3 From symbols to vectors AI . AI-04.01 . Beginner . 10 min
  4. 4 Sentence and document embeddings AI . AI-04.02 . Intermediate . 12 min
  5. 5 Semantic search basics AI . AI-04.03 . Beginner . 10 min
  6. 6 Tokenization AI . AI-05.01 . Beginner . 14 min
  7. 7 Embeddings and positional encoding AI . AI-05.02 . Intermediate . 12 min
  8. 8 Self-attention, step by step AI . AI-05.03 . Intermediate . 22 min
  9. 9 Multi-head attention AI . AI-05.04 . Intermediate . 10 min
  10. 10 The transformer block AI . AI-05.05 . Intermediate . 14 min
  11. 11 Encoder, decoder and decoder-only models AI . AI-05.06 . Intermediate . 10 min
  12. 12 Pretraining: next-token prediction AI . AI-05.07 . Intermediate . 14 min
  13. 13 Decoding and sampling AI . AI-05.08 . Beginner . 12 min
  14. 14 Context windows and the KV cache AI . AI-05.09 . Advanced . 14 min
  15. 15 Parameter-efficient fine-tuning: LoRA and QLoRA AI . AI-06.06 . Intermediate . 14 min
  16. 16 Prompting vs RAG vs fine-tuning: choosing AI . AI-06.07 . Intermediate . 10 min
  17. 17 Prompting fundamentals AI . AI-07.01 . Beginner . 12 min
  18. 18 Few-shot prompting and examples AI . AI-07.02 . Beginner . 8 min
  19. 19 Chain of thought and step-by-step reasoning AI . AI-07.03 . Intermediate . 10 min
  20. 20 Structured outputs AI . AI-07.04 . Intermediate . 10 min
  21. 21 System prompts and personas AI . AI-07.05 . Beginner . 8 min
  22. 22 Context engineering AI . AI-07.06 . Intermediate . 14 min
  23. 23 Prompt caching and cost control AI . AI-07.07 . Intermediate . 8 min
  24. 24 Why RAG? AI . AI-08.01 . Beginner . 10 min
  25. 25 Document ingestion and chunking AI . AI-08.02 . Intermediate . 14 min
  26. 26 Embedding and indexing AI . AI-08.03 . Intermediate . 10 min
  27. 27 Vector databases and ANN indexes AI . AI-08.04 . Advanced . 16 min
  28. 28 Hybrid search and reranking AI . AI-08.05 . Intermediate . 12 min
  29. 29 Contextual retrieval and query transformation AI . AI-08.06 . Advanced . 12 min
  30. 30 GraphRAG and structured retrieval AI . AI-08.07 . Advanced . 10 min
  31. 31 Evaluating RAG AI . AI-08.08 . Intermediate . 12 min
  32. 32 Production RAG architecture AI . AI-08.09 . Advanced . 15 min
  33. 33 Function calling and tool use AI . AI-09.01 . Beginner . 12 min
  34. 34 The agent loop (ReAct) AI . AI-09.02 . Intermediate . 12 min
  35. 35 Workflows vs agents: the patterns AI . AI-09.03 . Intermediate . 16 min
  36. 36 Model Context Protocol (MCP) AI . AI-09.04 . Intermediate . 14 min
  37. 37 Memory for agents AI . AI-09.05 . Intermediate . 10 min
  38. 38 Multi-agent systems AI . AI-09.06 . Advanced . 12 min
  39. 39 Coding agents and computer-use agents AI . AI-09.07 . Advanced . 12 min
  40. 40 Making agents reliable AI . AI-09.08 . Advanced . 12 min
  41. 41 Why evals are the core skill AI . AI-10.01 . Beginner . 10 min
  42. 42 Building an eval set AI . AI-10.02 . Intermediate . 12 min
  43. 43 Error analysis AI . AI-10.03 . Intermediate . 10 min
  44. 44 LLM-as-judge AI . AI-10.04 . Intermediate . 12 min
  45. 45 Benchmarks and their limits AI . AI-10.05 . Beginner . 10 min
  46. 46 Online evaluation and monitoring AI . AI-10.06 . Intermediate . 10 min
  47. 47 How LLM inference works AI . AI-11.01 . Intermediate . 14 min
  48. 48 GPU memory math AI . AI-11.02 . Intermediate . 12 min
  49. 49 Batching and PagedAttention AI . AI-11.03 . Advanced . 14 min
  50. 50 Quantization for inference AI . AI-11.04 . Advanced . 12 min
  51. 51 Speculative decoding and other speedups AI . AI-11.05 . Advanced . 12 min
  52. 52 Routing, cascades and cost optimization AI . AI-11.06 . Intermediate . 10 min
  53. 53 Streaming responses to users AI . AI-11.07 . Beginner . 8 min
  54. 54 Hallucinations AI . AI-13.01 . Beginner . 10 min
  55. 55 Prompt injection and data exfiltration AI . AI-13.02 . Intermediate . 14 min
  56. 56 Guardrails AI . AI-13.03 . Intermediate . 10 min
  57. 57 Anatomy of an LLM application AI . AI-14.01 . Beginner . 12 min
  58. 58 UX patterns for AI AI . AI-14.02 . Beginner . 10 min
  59. 59 LLM observability and tracing AI . AI-14.03 . Intermediate . 10 min
  60. 60 Latency and cost budgets AI . AI-14.04 . Intermediate . 10 min
  61. 61 LLMOps: shipping and iterating AI . AI-14.05 . Intermediate . 10 min
  62. 62 Capstone: chat with your documents (RAG) AI . AI-15.01 . Intermediate . 60 min
  63. 63 Capstone: a tool-using agent with MCP AI . AI-15.02 . Advanced . 60 min