# AI Design Patterns (MoC) ## Overview Design patterns for building effective AI systems. These patterns address recurring challenges in [[Context Engineering]], [[AI Agent Orchestration]], and [[Large Language Models (LLMs)|LLM]] application design. Many draw from established software engineering principles like [[Separation of Concerns]], [[Lazy Loading]], and [[Progressive Disclosure]], adapted for the unique constraints of AI context and token budgets. ## Notes <!-- QueryToSerialize: LIST FROM (#ai/context OR #ai/engineering OR #ai/safety OR #ai/retrieval OR #ai/agents/orchestration OR #ai/llms/patterns OR #ai/llms/techniques) AND #type/permanent_note AND !#type/quote AND !#type/creation/quote WHERE public_note = true SORT file.name ASC --> <!-- SerializedQuery: LIST FROM (#ai/context OR #ai/engineering OR #ai/safety OR #ai/retrieval OR #ai/agents/orchestration OR #ai/llms/patterns OR #ai/llms/techniques) AND #type/permanent_note AND !#type/quote AND !#type/creation/quote WHERE public_note = true SORT file.name ASC --> - [[Agent Development Lifecycle (ADLC)]] - [[Agent System Engineering]] - [[Agent-Native Product Decomposition]] - [[Agentic Context Engineering]] - [[Agentic Engineering]] - [[Agentic loops]] - [[Agentic TDD]] - [[AI Agent Memory]] - [[AI Agent Orchestration]] - [[AI Agent Permissions]] - [[AI Agent Routing]] - [[AI Alignment]] - [[AI and Context Engineering Glossary]] - [[AI and the Shifting Role of Developers]] - [[AI and Trust]] - [[AI API prices are rising]] - [[AI Bias]] - [[AI Context Governance]] - [[AI Context Rot]] - [[AI Cost Management]] - [[AI Data Security]] - [[AI Engineering]] - [[AI Ethics]] - [[AI Evaluation]] - [[AI Fine-Tuning]] - [[AI Guardrails]] - [[AI Hallucination]] - [[AI Instruction Drift]] - [[AI Instruction Tuning]] - [[AI Interoperability]] - [[AI Major Techniques]] - [[AI Model Selection]] - [[AI Observability]] - [[AI Privacy]] - [[AI Red Teaming]] - [[AI Retrieval Patterns]] - [[AI Risks and Fears]] - [[AI Safety]] - [[AI Skill Supply Chain Security]] - [[AI Subagents]] - [[AI Sustainability]] - [[AI Training Data Collection]] - [[AI Verifiability]] - [[AI Verifiability as a Capability Ceiling]] - [[AI-assisted code comprehension]] - [[AI-Assisted Development Workflow]] - [[AI-Ready Second Brain]] - [[CocoIndex]] - [[CocoIndexCode]] - [[Code is cheap, quality is not]] - [[CodeGraph]] - [[Cognitive debt]] - [[Constitutional AI]] - [[Context Anchoring]] - [[Context Bloat]] - [[Context Budget]] - [[Context Compression]] - [[Context Confusion]] - [[Context Distraction]] - [[Context Drift]] - [[Context Engineering]] - [[Context Engineering for Non-Developers]] - [[Context Entropy]] - [[Context File Hierarchy]] - [[Context Hygiene]] - [[Context Inheritance]] - [[Context Isolation]] - [[Context Layering]] - [[Context Lifecycle]] - [[Context Management Maturity Model]] - [[Context Poisoning]] - [[Context Provenance]] - [[Context Reduces AI Entropy]] - [[Context Signal-to-Noise Ratio]] - [[Context Window]] - [[Context-as-Code]] - [[Data Poisoning]] - [[Dify]] - [[Embeddings]] - [[Enterprise AI Deployment]] - [[Enterprise Context Management (ECM)]] - [[EU AI Act]] - [[FAISS]] - [[FastContext]] - [[Gas City]] - [[Gas Town]] - [[Harness Engineering]] - [[Headroom]] - [[Helicone]] - [[Herdr]] - [[Hoard things you know how to do]] - [[Human-in-the-Loop]] - [[Intent Engineering]] - [[Jagged Intelligence]] - [[Kanbots]] - [[Knowledge-Context Pipeline]] - [[LangFlow]] - [[Langfuse]] - [[LangSmith]] - [[Lethal Trifecta for AI Agents]] - [[Levels of AI Context Management]] - [[Levels of AI use]] - [[llms.txt convention]] - [[Menugen Architecture Pattern]] - [[MenuGen Deployment Gap]] - [[Microsoft AI Agent Governance Toolkit]] - [[Model routing]] - [[Multica]] - [[Open WebUI]] - [[Personal Context Management (PCM)]] - [[PKM-to-AI Readiness]] - [[Progressive Disclosure]] - [[Project Context Management (PCM)]] - [[Prompt injection]] - [[Prompt Lazy Loading AI Design Pattern (PLL)]] - [[RAG Pipelines]] - [[Ralph Loop]] - [[Ralph Wiggum Technique]] - [[Receptionist AI Design Pattern]] - [[Reinforcement Learning From Human Feedback (RLHF)]] - [[Responsible AI]] - [[Retrieval-Augmented Generation (RAG)]] - [[Reward Hacking]] - [[Semantic chunking]] - [[Semantic Search]] - [[SentenceTransformers]] - [[Slopsquatting]] - [[Software 2.0]] - [[Software 3.0]] - [[Software Design Patterns for AI Skills and Agents]] - [[Superset]] - [[SWE-Bench]] - [[Team Context Management (TCM)]] - [[Token Budget]] - [[TurboQuant]] - [[Turbovec]] - [[Types of Context for AI Agents]] - [[Understanding Bottleneck]] - [[Unreviewed AI code anti-pattern]] - [[Vibe Engineering]] <!-- SerializedQuery END --> ## Quotes <!-- QueryToSerialize: LIST FROM (#ai/context OR #ai/engineering OR #ai/safety OR #ai/retrieval OR #ai/agents/orchestration OR #ai/llms/patterns OR #ai/llms/techniques) AND (#type/quote OR #type/creation/quote) WHERE public_note = true SORT file.name ASC -->