Back to Knowledge Base
MapNetwork

Knowledge Graph

109 lessons across 12 phases, linked by 97 prerequisite, 131 builds-on, and 29 related edges. Hover a lesson to trace its dependency path; click to open it.

prerequisite
builds-on
related
upstream
downstream
Hover or focus a lesson to trace its prerequisites (blue, upstream) and what it unlocks (green, downstream). Click to open. Drag to pan · ⌘/Ctrl+scroll to zoom.
🧠Phase 1Foundations & Model I…📐System Design Foundat…💬Phase 2Prompting & Structure…🔍Phase 3Embeddings & RAG🤖Phase 4Agents & Orchestration🧠Phase 5Long-Term Memory⛓Phase 6LangChain & LangGraph🛡Phase 7Evals, Safety & Obser…🚀Phase 8Ship to Production🔧AppendixFine-tuning & Training☁AppendixOther Clouds & Platfo…🏗AppendixEngineering & Communi…The AI Engineer's Ro…The AI Engineer's Roadmap: Skills, Tools & Career PathTransformer Architec…Transformer Architecture: Attention, Positional Encoding & ScaleTokenization: BPE, S…Tokenization: BPE, SentencePiece & Vocabulary DesignLLM Architectures Co…LLM Architectures Compared: GPT, Claude, Llama, Gemini, Mistral, and BeyondScaling Laws: Chinch…Scaling Laws: Chinchilla, Emergent Abilities & Compute-Optimal TrainingInference Optimizati…Inference Optimization: KV Cache, Quantization & Speculative DecodingPre-training: Data C…Pre-training: Data Curation, Objectives & CurriculumScaling & Load Balan…Scaling & Load Balancing: GPU Clusters, Model Parallelism & RoutingProduction AI Patter…Production AI Patterns: Workflows, Pipelines & ArchitectureMicroservicesMicroservicesSOLID PrinciplesSOLID PrinciplesACID PropertiesACID PropertiesPostgreSQL JOINs: In…PostgreSQL JOINs: Inner, Outer, Cross, Self, Lateral & PerformanceForeign Keys: Refere…Foreign Keys: Referential Integrity, Cascades & Migration PatternsPrompt Engineering F…Prompt Engineering Fundamentals: Principles & PatternsFew-Shot & Chain-of-…Few-Shot & Chain-of-Thought PromptingSystem Prompt Design…System Prompt Design: Instructions, Personas & GuardrailsStructured Output: J…Structured Output: JSON Mode, Tool Schemas & Constrained DecodingFunction Calling & T…Function Calling & Tool Integration: APIs, Schemas & ExecutionTool Use: Function C…Tool Use: Function Calling as an Agentic PatternPrompt Optimization:…Prompt Optimization: DSPy, Automatic Prompt Engineering & Meta-PromptingPrompt Caching: KV C…Prompt Caching: KV Cache Mechanics, Prefix Caching & Cost OptimizationAdversarial Promptin…Adversarial Prompting: Jailbreaks, Injections & Defense StrategiesSpec-Driven Developm…Spec-Driven Development: Specs as the Durable Contract for Coding AgentsEmbeddingsEmbeddingsEmbedding Models: Re…Embedding Models: Representations, Similarity & Fine-tuningVector Databases: In…Vector Databases: Indexing, ANN Search & Production PatternsLanceDB: Embedded Mu…LanceDB: Embedded Multimodal Vector LakehouseChunking Strategies:…Chunking Strategies: Splitting, Overlap & Semantic BoundariesRetrieval Strategies…Retrieval Strategies: Hybrid Search, Reranking & HyDERAG: Retrieval-Augme…RAG: Retrieval-Augmented Generation as an Agentic PatternAdvanced RAG: Agenti…Advanced RAG: Agentic, Graph-Based & Multi-Hop RetrievalRAG Evaluation: Fait…RAG Evaluation: Faithfulness, Relevance & Failure ModesAgent Architectures:…Agent Architectures: ReAct, Plan-and-Execute & Cognitive FrameworksMulti-Agent Systems:…Multi-Agent Systems: Orchestration, Delegation & CommunicationAgent Orchestration:…Agent Orchestration: Routing, Handoffs & Supervisor PatternsAgent Harnesses: Eve…Agent Harnesses: Event Loops, Permission Models & Tool SandboxingAgent SDKs: Claude, …Agent SDKs: Claude, OpenAI, Vercel AI SDK & Framework ComparisonCode Generation Agen…Code Generation Agents: Sandboxing, Iteration & Self-RepairAgent Debugging & Ob…Agent Debugging & Observability: Tracing, Replay & Root Cause AnalysisReAct Agents Lab: Bu…ReAct Agents Lab: Building the Reason-Act-Observe LoopReflexion: Self-Impr…Reflexion: Self-Improving Agents via Verbal ReinforcementPlan-and-Execute Age…Plan-and-Execute Agents: Decompose First, Then ActLATS: Tree Search Ag…LATS: Tree Search Agents with Monte-Carlo Tree SearchSupervisor Multi-Age…Supervisor Multi-Agent Lab: Routing Work Across Specialist WorkersTree of Thoughts: De…Tree of Thoughts: Deliberate Search Over Reasoning StepsSelf-Refine: Iterati…Self-Refine: Iterative Refinement with Self-FeedbackReWOO and LLMCompile…ReWOO and LLMCompiler: Efficient Tool PlanningMulti-Agent Debate: …Multi-Agent Debate: Convergence Through CritiqueGenerative Agents: T…Generative Agents: The Memory StreamAgent Persistence & …Agent Persistence & Human-in-the-Loop: Making Agents ShippableBenchmarking Agents:…Benchmarking Agents: Suites, Trajectory Metrics, and a Regression GateAgent Memory: Short-…Agent Memory: Short-term, Long-term & Episodic Memory SystemsMemory: Persistence …Memory: Persistence as an Agentic PatternContext Engineering:…Context Engineering: Designing What LLMs SeeContext Window Manag…Context Window Management: Token Budgets, Prioritization & Overflow StrategiesMemory Architectures…Memory Architectures for LLM Systems: Working, Episodic & Semantic MemoryDynamic Context Asse…Dynamic Context Assembly: Runtime Composition for LLM ApplicationsContext Compression:…Context Compression: Fitting More Signal into Fewer TokensLong-Term Agent Memo…Long-Term Agent Memory with LangMem & Cloudflare VectorizeLangChain Fundamenta…LangChain Fundamentals: Runnables, LCEL & Composable Chains on the EdgeLangChain Tools & Re…LangChain Tools & Retrievers: Grounding Chains in Your Own DataLangGraph: Stateful …LangGraph: Stateful Multi-Agent Graphs for Production AILangGraph Human-in-t…LangGraph Human-in-the-Loop: Interrupts, Approval Gates & Time TravelLangGraph Multi-Agen…LangGraph Multi-Agent Topologies: Supervisor, Swarm & Hierarchical TeamsLangGraph Checkpoint…LangGraph Checkpointing on Cloudflare D1: Durable State & Resumable GraphsStreaming & Observab…Streaming & Observability for LangGraph: SSE, Stream Modes & LangSmith TracingDeploying LangGraph …Deploying LangGraph in Production: Platform, Self-Host & the Cloudflare EdgeRed-Teaming LLM Appl…Red-Teaming LLM Applications with LangGraph: Graph-Based Adversarial PipelinesLLM Evaluation Funda…LLM Evaluation Fundamentals: Metrics, Datasets & MethodologyBenchmark Design: Co…Benchmark Design: Contamination, Saturation & Domain-Specific EvalsLLM-as-Judge: Automa…LLM-as-Judge: Automated Evaluation, Calibration & BiasHuman Evaluation: An…Human Evaluation: Annotation Design, Inter-Rater Reliability & ScaleEval Frameworks Comp…Eval Frameworks Comparison: DeepEval, Promptfoo, RAGAS, Braintrust, LangSmith & MoreDeepEval Synthesizer…DeepEval Synthesizer: Synthetic Golden Generation for LLM EvaluationAgent Evaluation: Re…Agent Evaluation: Reliability, Tool Use Accuracy & Trajectory AnalysisRed Teaming & Advers…Red Teaming & Adversarial Testing: Automated & Manual ApproachesGuardrails & Content…Guardrails & Content Filtering: Input/Output Safety LayersHallucination Detect…Hallucination Detection & Mitigation: Grounding & VerificationConstitutional AI & …Constitutional AI & RLHF for SafetyBias, Fairness & Res…Bias, Fairness & Responsible AI in ProductionAI Governance: Compl…AI Governance: Compliance, Auditing & Risk ManagementInterpretability & E…Interpretability & Explainability: Mechanistic & Feature-Level AnalysisObservability: Traci…Observability: Tracing, Logging & LLM MonitoringOnline Evaluation: P…Online Evaluation: Production Sampling, Drift Detection & Feedback LoopsAI Gateways: Rate Li…AI Gateways: Rate Limiting, Fallbacks & Multi-Provider RoutingEdge Deployment: On-…Edge Deployment: On-Device Models, ONNX & WebLLMCost Optimization: T…Cost Optimization: Token Economics, Caching & Model SelectionLLM Serving: API Des…LLM Serving: API Design, Batching & StreamingCI/CD for AI: Regres…CI/CD for AI: Regression Testing, Monitoring & Continuous EvalSearch & Recommendat…Search & Recommendations with LLMsConversational AI: C…Conversational AI: Chatbot Design, Dialogue Management & UXVision-Language Mode…Vision-Language Models: Architecture, Training & ApplicationsAudio & Speech AI: A…Audio & Speech AI: ASR, TTS & Voice AgentsAI for Code: Copilot…AI for Code: Copilots, Code Review & Program SynthesisFine-tuning Fundamen…Fine-tuning Fundamentals: Full, Freeze & Transfer LearningLoRA, QLoRA & Adapte…LoRA, QLoRA & Adapter Methods: Parameter-Efficient Fine-tuningRLHF & Preference Op…RLHF & Preference Optimization: DPO, ORPO & PPODataset Curation: Sy…Dataset Curation: Synthetic Data, Quality Filtering & AnnotationContinual Learning: …Continual Learning: Catastrophic Forgetting & Knowledge RetentionDistillation & Model…Distillation & Model Compression: Pruning, Quantization & Student ModelsGoogle Cloud PlatformGoogle Cloud PlatformDockerDockerKubernetesKubernetesCI/CDCI/CDNode.jsNode.jsLlamaIndexLlamaIndexPublic Speaking: Str…Public Speaking: Structure, Delivery, and Audience EngagementLanding an AI Engine…Landing an AI Engineering Role: Interviews, Negotiation & the Search