Skip to main content

Learning Paths

136 topics is a lot. These paths cut across the existing sections and give you a focused trail based on what you're trying to do — not what section something lives in.

Your original sections are untouched. These paths are an overlay.

PathTopicsTimeGoal
⚡ Quick Start7~2 daysMental models before anything else
🧱 Essentials22~2 weeksWhat every AI engineer must know
🔨 For Builders28~3 weeksShip AI apps and integrations
⚙️ Systems Depth~79OngoingInfra, ops, and safety at scale

⚡ Quick Start

Mental models before anything else. You don't need to understand transformers to build with AI — but you do need to know what a token is, why context windows matter, and what an embedding actually does.

~2 days. 5 of these 7 are already written.

#TopicSectionStatus
1LLM, SLM & Foundation Models01✅ Done
2Tokenization01✅ Done
3Embeddings01✅ Done
4Context Window01✅ Done
5Autoregressive Decoding01✅ Done
6Prompt Engineering02✅ Done
7Temperature, Top-p & Sampling02✅ Done

🧱 Essentials

The unavoidable core. If you're building anything serious with AI — apps, integrations, agents — these are the topics you'll hit walls without.

~2 weeks. Prerequisite: Quick Start.

Prompting & Control

#TopicSectionStatus
1System Prompt02✅ Done
2Structured Output & JSON Mode02✅ Done
3Few-shot & Zero-shot02✅ Done
4Prompt Versioning02✅ Done

RAG & Retrieval

#TopicSectionStatus
5RAG05🔴 Not started
6Embedding Models05🔴 Not started
7Vector Databases05🔴 Not started
8Chunking Strategies05🔴 Not started
9Hybrid Search (BM25 + Dense)05🔴 Not started
10Re-ranking05🔴 Not started

Agents

#TopicSectionStatus
11AI Agent Fundamentals06🔴 Not started
12Tool / Function Calling06🔴 Not started
13ReAct Pattern06🔴 Not started
14MCP — Model Context Protocol06🔴 Not started

Safety Baseline

#TopicSectionStatus
15Prompt Injection07🔴 Not started
16Input Guardrails07🔴 Not started
17Output Guardrails07🔴 Not started

Eval Basics

#TopicSectionStatus
18LLM-as-judge08🔴 Not started
19Hallucination Rate08🔴 Not started

🔨 For Builders

Everything you need to actually build and integrate AI into products — APIs, streaming, agents, observability, and how to connect AI to your existing stack.

~3 weeks. Prerequisite: Essentials.

Integration Layer

#TopicSectionStatus
1Streaming (SSE)10🔴 Not started
2AI Gateway10🔴 Not started
3Auth & Rate Limiting10🔴 Not started
4Model Router10🔴 Not started
5Fallback Chain10🔴 Not started
6Open-weight vs Managed Endpoints10🔴 Not started
7OpenAI-compatible API03🔴 Not started
8Managed Inference — Groq, Baseten, Modal10🔴 Not started

Agents & Orchestration (Builder Focus)

#TopicSectionStatus
9Chain of Thought (CoT)06🔴 Not started
10Human-in-the-loop06🔴 Not started
11LangChain & LlamaIndex06🔴 Not started
12LangGraph06🔴 Not started
13Tool Registry06🔴 Not started
14Idempotent Tool Calls06🔴 Not started
15Working & Episodic Memory05🔴 Not started
16Agentic RAG05🔴 Not started

Observability for Builders

#TopicSectionStatus
17LLMOps Overview09🔴 Not started
18Tracing & Spans09🔴 Not started
19Langfuse & LangSmith09🔴 Not started
20Cost per Token09🔴 Not started

Eval for Builders

#TopicSectionStatus
21RAGAS08🔴 Not started
22A/B Prompt Testing08🔴 Not started
23Offline vs Online Eval08🔴 Not started
24Golden Dataset08🔴 Not started

New Patterns

#TopicSectionStatus
25AI SDK Patterns10🔴 Not started
26Webhook vs Streaming vs Polling10🔴 Not started
27Context Management Patterns02🔴 Not started
28PII Redaction07🔴 Not started

⚙️ Systems Depth

The remaining ~79 topics from the original map. These don't go away — they're the ones that separate engineers who use AI from engineers who design AI systems. Work through them in the original section order once you've completed For Builders.

  • 01 Model Inference Core (remaining 10) — KV cache, continuous batching, paged attention, FlashAttention, chunked prefill, speculative decoding, MoE, multimodal LLMs, reasoning models
  • 02 Model Optimization (all 11) — Quantization, FP8/INT8/INT4, GPTQ/AWQ/GGUF, pruning, distillation, LoRA/QLoRA, adapters, fine-tuning/SFT, RLHF, DPO/GRPO, model merging
  • 03 Serving Infrastructure (all 15) — vLLM, TGI, TensorRT-LLM, SGLang, llama.cpp/Ollama, Triton, P/D disaggregation, tensor/pipeline/expert parallelism, serving metrics, batch inference, edge inference, NVIDIA Dynamo
  • 04 Retrieval & Memory (remaining 6) — Semantic search, knowledge graph, GraphRAG, long-context retrieval
  • 05 Agents & Orchestration (remaining 7) — Plan & execute, Agent SDK, multi-agent systems, handoff A2A, A2A protocol
  • 06 Prompting & Control (remaining 3) — In-context learning, constitutional AI, system card
  • 07 Evaluation & Quality (remaining 9) — Faithfulness metrics, DeepEval, benchmark evals, regression testing, trajectory eval, CI/CD gates, PROMOTE/HOLD/ROLLBACK
  • 08 Observability & Ops (remaining 10) — OpenTelemetry, latency percentiles, prompt/semantic drift, toxicity scoring, RBAC/IAM, audit logs, Arize/Datadog, data residency, model versioning, spans & traces
  • 09 Integration & Cloud (remaining 7) — KV cache-aware routing, prefix-aware routing, cloud platforms, Hugging Face endpoints, data sovereignty, VPC/private endpoints, on-prem/hybrid
  • 10 Safety & Governance (remaining 12) — Content filtering, red-teaming, adversarial inputs, safety alignment, bias detection, fairness metrics, human approval gate, policy-as-code, AI RMF, EU AI Act, responsible AI