Pick up where you left off?

Resume reading
AI Data Foundation
GitHub
Editorial Curriculum

1,000 practical titles for the AI & LLM ecosystem.

A structured, public curriculum covering foundational math, transformer architectures, agentic protocols, vector data engineering, and evaluation benchmarks.

170 Planned Guides
110 Hands-on Labs
4 Core Tracks
Structured Progression

One Ecosystem. Clear Learning Tracks.

Click on any learning track below to explore the detailed roadmap of scheduled blogs, technical breakdowns, and reproducible lab exercises.

01
LLM Architectures & Foundations From transformer attention mechanisms to fine-tuning, quantization, and local deployment.
45 blogs · 30 labs
45 Planned Articles & Architecture Guides
  1. Self-Attention and Multi-Head Attention: architecture and design guide
  2. Self-Attention and Multi-Head Attention: practical hands-on tutorial
  3. Self-Attention and Multi-Head Attention: production deployment playbook
  4. Self-Attention and Multi-Head Attention: benchmarks and evaluation report
  5. Self-Attention and Multi-Head Attention: troubleshooting and debugging field notes
  6. Self-Attention and Multi-Head Attention: security and safety checklist
  7. Transformer Decoder-Only Architectures: architecture and design guide
  8. Transformer Decoder-Only Architectures: practical hands-on tutorial
  9. Transformer Decoder-Only Architectures: production deployment playbook
  10. Transformer Decoder-Only Architectures: benchmarks and evaluation report
  11. Transformer Decoder-Only Architectures: troubleshooting and debugging field notes
  12. Transformer Decoder-Only Architectures: security and safety checklist
  13. RoPE (Rotary Position Embeddings): architecture and design guide
  14. RoPE (Rotary Position Embeddings): practical hands-on tutorial
  15. RoPE (Rotary Position Embeddings): production deployment playbook
  16. RoPE (Rotary Position Embeddings): benchmarks and evaluation report
  17. RoPE (Rotary Position Embeddings): troubleshooting and debugging field notes
  18. RoPE (Rotary Position Embeddings): security and safety checklist
  19. FlashAttention & Memory Optimization: architecture and design guide
  20. FlashAttention & Memory Optimization: practical hands-on tutorial
  21. FlashAttention & Memory Optimization: production deployment playbook
  22. FlashAttention & Memory Optimization: benchmarks and evaluation report
  23. FlashAttention & Memory Optimization: troubleshooting and debugging field notes
  24. FlashAttention & Memory Optimization: security and safety checklist
  25. LoRA and QLoRA Parameter-Efficient Fine-Tuning: architecture and design guide
  26. LoRA and QLoRA Parameter-Efficient Fine-Tuning: practical hands-on tutorial
  27. LoRA and QLoRA Parameter-Efficient Fine-Tuning: production deployment playbook
  28. LoRA and QLoRA Parameter-Efficient Fine-Tuning: benchmarks and evaluation report
  29. LoRA and QLoRA Parameter-Efficient Fine-Tuning: troubleshooting and debugging field notes
  30. LoRA and QLoRA Parameter-Efficient Fine-Tuning: security and safety checklist
  31. Quantization: GGUF, AWQ, and EXL2: architecture and design guide
  32. Quantization: GGUF, AWQ, and EXL2: practical hands-on tutorial
  33. Quantization: GGUF, AWQ, and EXL2: production deployment playbook
  34. Quantization: GGUF, AWQ, and EXL2: benchmarks and evaluation report
  35. Quantization: GGUF, AWQ, and EXL2: troubleshooting and debugging field notes
  36. Quantization: GGUF, AWQ, and EXL2: security and safety checklist
  37. Local Inference with Ollama and vLLM: architecture and design guide
  38. Local Inference with Ollama and vLLM: practical hands-on tutorial
  39. Local Inference with Ollama and vLLM: production deployment playbook
  40. Local Inference with Ollama and vLLM: benchmarks and evaluation report
  41. Local Inference with Ollama and vLLM: troubleshooting and debugging field notes
  42. Local Inference with Ollama and vLLM: security and safety checklist
  43. Inference Serving & Speculative Decoding: architecture and design guide
  44. Inference Serving & Speculative Decoding: practical hands-on tutorial
  45. Inference Serving & Speculative Decoding: production deployment playbook
30 Planned Hands-on Exercises
  1. Self-Attention and Multi-Head Attention: install, configure, and verify locally
  2. Self-Attention and Multi-Head Attention: build an end-to-end pipeline from scratch
  3. Self-Attention and Multi-Head Attention: debug and optimize performance under load
  4. Self-Attention and Multi-Head Attention: evaluate accuracy against open benchmarks
  5. Self-Attention and Multi-Head Attention: integrate with autonomous agent workflows
  6. Transformer Decoder-Only Architectures: install, configure, and verify locally
  7. Transformer Decoder-Only Architectures: build an end-to-end pipeline from scratch
  8. Transformer Decoder-Only Architectures: debug and optimize performance under load
  9. Transformer Decoder-Only Architectures: evaluate accuracy against open benchmarks
  10. Transformer Decoder-Only Architectures: integrate with autonomous agent workflows
  11. RoPE (Rotary Position Embeddings): install, configure, and verify locally
  12. RoPE (Rotary Position Embeddings): build an end-to-end pipeline from scratch
  13. RoPE (Rotary Position Embeddings): debug and optimize performance under load
  14. RoPE (Rotary Position Embeddings): evaluate accuracy against open benchmarks
  15. RoPE (Rotary Position Embeddings): integrate with autonomous agent workflows
  16. FlashAttention & Memory Optimization: install, configure, and verify locally
  17. FlashAttention & Memory Optimization: build an end-to-end pipeline from scratch
  18. FlashAttention & Memory Optimization: debug and optimize performance under load
  19. FlashAttention & Memory Optimization: evaluate accuracy against open benchmarks
  20. FlashAttention & Memory Optimization: integrate with autonomous agent workflows
  21. LoRA and QLoRA Parameter-Efficient Fine-Tuning: install, configure, and verify locally
  22. LoRA and QLoRA Parameter-Efficient Fine-Tuning: build an end-to-end pipeline from scratch
  23. LoRA and QLoRA Parameter-Efficient Fine-Tuning: debug and optimize performance under load
  24. LoRA and QLoRA Parameter-Efficient Fine-Tuning: evaluate accuracy against open benchmarks
  25. LoRA and QLoRA Parameter-Efficient Fine-Tuning: integrate with autonomous agent workflows
  26. Quantization: GGUF, AWQ, and EXL2: install, configure, and verify locally
  27. Quantization: GGUF, AWQ, and EXL2: build an end-to-end pipeline from scratch
  28. Quantization: GGUF, AWQ, and EXL2: debug and optimize performance under load
  29. Quantization: GGUF, AWQ, and EXL2: evaluate accuracy against open benchmarks
  30. Quantization: GGUF, AWQ, and EXL2: integrate with autonomous agent workflows
02
Agentic Systems & Model Context Protocol (MCP) Standardizing context, tool use, and multi-agent coordination across autonomous AI systems.
40 blogs · 25 labs
40 Planned Articles & Architecture Guides
  1. Model Context Protocol (MCP) Specification: architecture and design guide
  2. Model Context Protocol (MCP) Specification: practical hands-on tutorial
  3. Model Context Protocol (MCP) Specification: production deployment playbook
  4. Model Context Protocol (MCP) Specification: benchmarks and evaluation report
  5. Model Context Protocol (MCP) Specification: troubleshooting and debugging field notes
  6. Model Context Protocol (MCP) Specification: security and safety checklist
  7. Building MCP Servers in Python & TypeScript: architecture and design guide
  8. Building MCP Servers in Python & TypeScript: practical hands-on tutorial
  9. Building MCP Servers in Python & TypeScript: production deployment playbook
  10. Building MCP Servers in Python & TypeScript: benchmarks and evaluation report
  11. Building MCP Servers in Python & TypeScript: troubleshooting and debugging field notes
  12. Building MCP Servers in Python & TypeScript: security and safety checklist
  13. Tool Calling & Function Orchestration: architecture and design guide
  14. Tool Calling & Function Orchestration: practical hands-on tutorial
  15. Tool Calling & Function Orchestration: production deployment playbook
  16. Tool Calling & Function Orchestration: benchmarks and evaluation report
  17. Tool Calling & Function Orchestration: troubleshooting and debugging field notes
  18. Tool Calling & Function Orchestration: security and safety checklist
  19. ReAct Pattern & Planning Agents: architecture and design guide
  20. ReAct Pattern & Planning Agents: practical hands-on tutorial
  21. ReAct Pattern & Planning Agents: production deployment playbook
  22. ReAct Pattern & Planning Agents: benchmarks and evaluation report
  23. ReAct Pattern & Planning Agents: troubleshooting and debugging field notes
  24. ReAct Pattern & Planning Agents: security and safety checklist
  25. Multi-Agent Swarm Architectures: architecture and design guide
  26. Multi-Agent Swarm Architectures: practical hands-on tutorial
  27. Multi-Agent Swarm Architectures: production deployment playbook
  28. Multi-Agent Swarm Architectures: benchmarks and evaluation report
  29. Multi-Agent Swarm Architectures: troubleshooting and debugging field notes
  30. Multi-Agent Swarm Architectures: security and safety checklist
  31. Memory Systems: Working, Episodic & Semantic: architecture and design guide
  32. Memory Systems: Working, Episodic & Semantic: practical hands-on tutorial
  33. Memory Systems: Working, Episodic & Semantic: production deployment playbook
  34. Memory Systems: Working, Episodic & Semantic: benchmarks and evaluation report
  35. Memory Systems: Working, Episodic & Semantic: troubleshooting and debugging field notes
  36. Memory Systems: Working, Episodic & Semantic: security and safety checklist
  37. Human-in-the-Loop & Safety Guardrails: architecture and design guide
  38. Human-in-the-Loop & Safety Guardrails: practical hands-on tutorial
  39. Human-in-the-Loop & Safety Guardrails: production deployment playbook
  40. Human-in-the-Loop & Safety Guardrails: benchmarks and evaluation report
25 Planned Hands-on Exercises
  1. Model Context Protocol (MCP) Specification: install, configure, and verify locally
  2. Model Context Protocol (MCP) Specification: build an end-to-end pipeline from scratch
  3. Model Context Protocol (MCP) Specification: debug and optimize performance under load
  4. Model Context Protocol (MCP) Specification: evaluate accuracy against open benchmarks
  5. Model Context Protocol (MCP) Specification: integrate with autonomous agent workflows
  6. Building MCP Servers in Python & TypeScript: install, configure, and verify locally
  7. Building MCP Servers in Python & TypeScript: build an end-to-end pipeline from scratch
  8. Building MCP Servers in Python & TypeScript: debug and optimize performance under load
  9. Building MCP Servers in Python & TypeScript: evaluate accuracy against open benchmarks
  10. Building MCP Servers in Python & TypeScript: integrate with autonomous agent workflows
  11. Tool Calling & Function Orchestration: install, configure, and verify locally
  12. Tool Calling & Function Orchestration: build an end-to-end pipeline from scratch
  13. Tool Calling & Function Orchestration: debug and optimize performance under load
  14. Tool Calling & Function Orchestration: evaluate accuracy against open benchmarks
  15. Tool Calling & Function Orchestration: integrate with autonomous agent workflows
  16. ReAct Pattern & Planning Agents: install, configure, and verify locally
  17. ReAct Pattern & Planning Agents: build an end-to-end pipeline from scratch
  18. ReAct Pattern & Planning Agents: debug and optimize performance under load
  19. ReAct Pattern & Planning Agents: evaluate accuracy against open benchmarks
  20. ReAct Pattern & Planning Agents: integrate with autonomous agent workflows
  21. Multi-Agent Swarm Architectures: install, configure, and verify locally
  22. Multi-Agent Swarm Architectures: build an end-to-end pipeline from scratch
  23. Multi-Agent Swarm Architectures: debug and optimize performance under load
  24. Multi-Agent Swarm Architectures: evaluate accuracy against open benchmarks
  25. Multi-Agent Swarm Architectures: integrate with autonomous agent workflows
03
RAG & Vector Data Engineering Production retrieval pipelines, embeddings, hybrid search, and vector databases.
50 blogs · 35 labs
50 Planned Articles & Architecture Guides
  1. Chunking Strategies & Semantic Splitting: architecture and design guide
  2. Chunking Strategies & Semantic Splitting: practical hands-on tutorial
  3. Chunking Strategies & Semantic Splitting: production deployment playbook
  4. Chunking Strategies & Semantic Splitting: benchmarks and evaluation report
  5. Chunking Strategies & Semantic Splitting: troubleshooting and debugging field notes
  6. Chunking Strategies & Semantic Splitting: security and safety checklist
  7. Embedding Models: MTEB Benchmarks & Fine-tuning: architecture and design guide
  8. Embedding Models: MTEB Benchmarks & Fine-tuning: practical hands-on tutorial
  9. Embedding Models: MTEB Benchmarks & Fine-tuning: production deployment playbook
  10. Embedding Models: MTEB Benchmarks & Fine-tuning: benchmarks and evaluation report
  11. Embedding Models: MTEB Benchmarks & Fine-tuning: troubleshooting and debugging field notes
  12. Embedding Models: MTEB Benchmarks & Fine-tuning: security and safety checklist
  13. Vector Indexing: HNSW, IVF-Flat, and ScaNN: architecture and design guide
  14. Vector Indexing: HNSW, IVF-Flat, and ScaNN: practical hands-on tutorial
  15. Vector Indexing: HNSW, IVF-Flat, and ScaNN: production deployment playbook
  16. Vector Indexing: HNSW, IVF-Flat, and ScaNN: benchmarks and evaluation report
  17. Vector Indexing: HNSW, IVF-Flat, and ScaNN: troubleshooting and debugging field notes
  18. Vector Indexing: HNSW, IVF-Flat, and ScaNN: security and safety checklist
  19. Hybrid Search (Dense + Sparse BM25): architecture and design guide
  20. Hybrid Search (Dense + Sparse BM25): practical hands-on tutorial
  21. Hybrid Search (Dense + Sparse BM25): production deployment playbook
  22. Hybrid Search (Dense + Sparse BM25): benchmarks and evaluation report
  23. Hybrid Search (Dense + Sparse BM25): troubleshooting and debugging field notes
  24. Hybrid Search (Dense + Sparse BM25): security and safety checklist
  25. Reranking with Cross-Encoders: architecture and design guide
  26. Reranking with Cross-Encoders: practical hands-on tutorial
  27. Reranking with Cross-Encoders: production deployment playbook
  28. Reranking with Cross-Encoders: benchmarks and evaluation report
  29. Reranking with Cross-Encoders: troubleshooting and debugging field notes
  30. Reranking with Cross-Encoders: security and safety checklist
  31. GraphRAG: Knowledge Graphs for Context: architecture and design guide
  32. GraphRAG: Knowledge Graphs for Context: practical hands-on tutorial
  33. GraphRAG: Knowledge Graphs for Context: production deployment playbook
  34. GraphRAG: Knowledge Graphs for Context: benchmarks and evaluation report
  35. GraphRAG: Knowledge Graphs for Context: troubleshooting and debugging field notes
  36. GraphRAG: Knowledge Graphs for Context: security and safety checklist
  37. Weaviate, Qdrant, Milvus & pgvector: architecture and design guide
  38. Weaviate, Qdrant, Milvus & pgvector: practical hands-on tutorial
  39. Weaviate, Qdrant, Milvus & pgvector: production deployment playbook
  40. Weaviate, Qdrant, Milvus & pgvector: benchmarks and evaluation report
  41. Weaviate, Qdrant, Milvus & pgvector: troubleshooting and debugging field notes
  42. Weaviate, Qdrant, Milvus & pgvector: security and safety checklist
  43. Evaluation with RAGAS and TruLens: architecture and design guide
  44. Evaluation with RAGAS and TruLens: practical hands-on tutorial
  45. Evaluation with RAGAS and TruLens: production deployment playbook
  46. Evaluation with RAGAS and TruLens: benchmarks and evaluation report
  47. Evaluation with RAGAS and TruLens: troubleshooting and debugging field notes
  48. Evaluation with RAGAS and TruLens: security and safety checklist
  49. Chunking Strategies & Semantic Splitting: architecture and design guide
  50. Chunking Strategies & Semantic Splitting: practical hands-on tutorial
35 Planned Hands-on Exercises
  1. Chunking Strategies & Semantic Splitting: install, configure, and verify locally
  2. Chunking Strategies & Semantic Splitting: build an end-to-end pipeline from scratch
  3. Chunking Strategies & Semantic Splitting: debug and optimize performance under load
  4. Chunking Strategies & Semantic Splitting: evaluate accuracy against open benchmarks
  5. Chunking Strategies & Semantic Splitting: integrate with autonomous agent workflows
  6. Embedding Models: MTEB Benchmarks & Fine-tuning: install, configure, and verify locally
  7. Embedding Models: MTEB Benchmarks & Fine-tuning: build an end-to-end pipeline from scratch
  8. Embedding Models: MTEB Benchmarks & Fine-tuning: debug and optimize performance under load
  9. Embedding Models: MTEB Benchmarks & Fine-tuning: evaluate accuracy against open benchmarks
  10. Embedding Models: MTEB Benchmarks & Fine-tuning: integrate with autonomous agent workflows
  11. Vector Indexing: HNSW, IVF-Flat, and ScaNN: install, configure, and verify locally
  12. Vector Indexing: HNSW, IVF-Flat, and ScaNN: build an end-to-end pipeline from scratch
  13. Vector Indexing: HNSW, IVF-Flat, and ScaNN: debug and optimize performance under load
  14. Vector Indexing: HNSW, IVF-Flat, and ScaNN: evaluate accuracy against open benchmarks
  15. Vector Indexing: HNSW, IVF-Flat, and ScaNN: integrate with autonomous agent workflows
  16. Hybrid Search (Dense + Sparse BM25): install, configure, and verify locally
  17. Hybrid Search (Dense + Sparse BM25): build an end-to-end pipeline from scratch
  18. Hybrid Search (Dense + Sparse BM25): debug and optimize performance under load
  19. Hybrid Search (Dense + Sparse BM25): evaluate accuracy against open benchmarks
  20. Hybrid Search (Dense + Sparse BM25): integrate with autonomous agent workflows
  21. Reranking with Cross-Encoders: install, configure, and verify locally
  22. Reranking with Cross-Encoders: build an end-to-end pipeline from scratch
  23. Reranking with Cross-Encoders: debug and optimize performance under load
  24. Reranking with Cross-Encoders: evaluate accuracy against open benchmarks
  25. Reranking with Cross-Encoders: integrate with autonomous agent workflows
  26. GraphRAG: Knowledge Graphs for Context: install, configure, and verify locally
  27. GraphRAG: Knowledge Graphs for Context: build an end-to-end pipeline from scratch
  28. GraphRAG: Knowledge Graphs for Context: debug and optimize performance under load
  29. GraphRAG: Knowledge Graphs for Context: evaluate accuracy against open benchmarks
  30. GraphRAG: Knowledge Graphs for Context: integrate with autonomous agent workflows
  31. Weaviate, Qdrant, Milvus & pgvector: install, configure, and verify locally
  32. Weaviate, Qdrant, Milvus & pgvector: build an end-to-end pipeline from scratch
  33. Weaviate, Qdrant, Milvus & pgvector: debug and optimize performance under load
  34. Weaviate, Qdrant, Milvus & pgvector: evaluate accuracy against open benchmarks
  35. Weaviate, Qdrant, Milvus & pgvector: integrate with autonomous agent workflows
04
Evaluation, Benchmarks & AI Safety Measuring model accuracy, hallucination detection, prompt red-teaming, and bias mitigation.
35 blogs · 20 labs
35 Planned Articles & Architecture Guides
  1. Open LLM Leaderboard Evaluation Metrics: architecture and design guide
  2. Open LLM Leaderboard Evaluation Metrics: practical hands-on tutorial
  3. Open LLM Leaderboard Evaluation Metrics: production deployment playbook
  4. Open LLM Leaderboard Evaluation Metrics: benchmarks and evaluation report
  5. Open LLM Leaderboard Evaluation Metrics: troubleshooting and debugging field notes
  6. Open LLM Leaderboard Evaluation Metrics: security and safety checklist
  7. MMLU-Pro, GSM8K, and HumanEval Protocols: architecture and design guide
  8. MMLU-Pro, GSM8K, and HumanEval Protocols: practical hands-on tutorial
  9. MMLU-Pro, GSM8K, and HumanEval Protocols: production deployment playbook
  10. MMLU-Pro, GSM8K, and HumanEval Protocols: benchmarks and evaluation report
  11. MMLU-Pro, GSM8K, and HumanEval Protocols: troubleshooting and debugging field notes
  12. MMLU-Pro, GSM8K, and HumanEval Protocols: security and safety checklist
  13. LLM-as-a-Judge Design & Calibration: architecture and design guide
  14. LLM-as-a-Judge Design & Calibration: practical hands-on tutorial
  15. LLM-as-a-Judge Design & Calibration: production deployment playbook
  16. LLM-as-a-Judge Design & Calibration: benchmarks and evaluation report
  17. LLM-as-a-Judge Design & Calibration: troubleshooting and debugging field notes
  18. LLM-as-a-Judge Design & Calibration: security and safety checklist
  19. Hallucination Detection & Groundedness Checks: architecture and design guide
  20. Hallucination Detection & Groundedness Checks: practical hands-on tutorial
  21. Hallucination Detection & Groundedness Checks: production deployment playbook
  22. Hallucination Detection & Groundedness Checks: benchmarks and evaluation report
  23. Hallucination Detection & Groundedness Checks: troubleshooting and debugging field notes
  24. Hallucination Detection & Groundedness Checks: security and safety checklist
  25. Automated Red-Teaming & Prompt Injection Defense: architecture and design guide
  26. Automated Red-Teaming & Prompt Injection Defense: practical hands-on tutorial
  27. Automated Red-Teaming & Prompt Injection Defense: production deployment playbook
  28. Automated Red-Teaming & Prompt Injection Defense: benchmarks and evaluation report
  29. Automated Red-Teaming & Prompt Injection Defense: troubleshooting and debugging field notes
  30. Automated Red-Teaming & Prompt Injection Defense: security and safety checklist
  31. Synthetic Data Validation & Quality Metrics: architecture and design guide
  32. Synthetic Data Validation & Quality Metrics: practical hands-on tutorial
  33. Synthetic Data Validation & Quality Metrics: production deployment playbook
  34. Synthetic Data Validation & Quality Metrics: benchmarks and evaluation report
  35. Synthetic Data Validation & Quality Metrics: troubleshooting and debugging field notes
20 Planned Hands-on Exercises
  1. Open LLM Leaderboard Evaluation Metrics: install, configure, and verify locally
  2. Open LLM Leaderboard Evaluation Metrics: build an end-to-end pipeline from scratch
  3. Open LLM Leaderboard Evaluation Metrics: debug and optimize performance under load
  4. Open LLM Leaderboard Evaluation Metrics: evaluate accuracy against open benchmarks
  5. Open LLM Leaderboard Evaluation Metrics: integrate with autonomous agent workflows
  6. MMLU-Pro, GSM8K, and HumanEval Protocols: install, configure, and verify locally
  7. MMLU-Pro, GSM8K, and HumanEval Protocols: build an end-to-end pipeline from scratch
  8. MMLU-Pro, GSM8K, and HumanEval Protocols: debug and optimize performance under load
  9. MMLU-Pro, GSM8K, and HumanEval Protocols: evaluate accuracy against open benchmarks
  10. MMLU-Pro, GSM8K, and HumanEval Protocols: integrate with autonomous agent workflows
  11. LLM-as-a-Judge Design & Calibration: install, configure, and verify locally
  12. LLM-as-a-Judge Design & Calibration: build an end-to-end pipeline from scratch
  13. LLM-as-a-Judge Design & Calibration: debug and optimize performance under load
  14. LLM-as-a-Judge Design & Calibration: evaluate accuracy against open benchmarks
  15. LLM-as-a-Judge Design & Calibration: integrate with autonomous agent workflows
  16. Hallucination Detection & Groundedness Checks: install, configure, and verify locally
  17. Hallucination Detection & Groundedness Checks: build an end-to-end pipeline from scratch
  18. Hallucination Detection & Groundedness Checks: debug and optimize performance under load
  19. Hallucination Detection & Groundedness Checks: evaluate accuracy against open benchmarks
  20. Hallucination Detection & Groundedness Checks: integrate with autonomous agent workflows
Propose a Topic

Want a specific lab or guide written?

Open a GitHub issue with the title or tool you would like added to the foundation curriculum.

Suggest a Roadmap Title ↗