Glossary
NOENTRYCATEGORYLEVEL
001What Is an LLM?Term●○○002Tokens (and Why They Cost Money)Term●○○003Context WindowTerm●○○004What Is a Prompt?Term●○○005System Prompt vs. User PromptTerm●●○006Hallucination: Why AI Confidently LiesTerm●○○007What Is an API? (Explained Without Jargon)Term●○○008MCP (Model Context Protocol): How AI Tools ConnectTerm●●○009What Is an AI Agent? (vs. a Chatbot)Concept●○○010The Agent Loop: Think → Act → Check → RepeatConcept●●○011Vibe Coding: When It Works, When It Bites YouConcept●○○012Claude Code: Anthropic's CLI AgentGuide●●○013CLAUDE.md / AGENTS.md: Give Your Agent Memory & RulesGuide●●○014Pattern: Plan First, Then CodePrompt pattern●●○015Pattern: Feed Context Instead of Asking VaguelyPrompt pattern●○○016Loops for Agents: Letting AI Iterate AutonomouslyConcept●●●017Hermes: An Agent That Grows With YouTerm●●●018OpenClaw: An Open-Source Personal AI AssistantTerm●●●019Model Lifecycle: Models Launch, Change, and Get RetiredConcept●●○020Cost Control for AI AgentsGuide●●○021Security in Vibe CodingGuide●●○022What Are Subagents?Concept●●○023Guardrails for Autonomous AgentsConcept●●●024Installing Claude Code (Step by Step)Guide●○○025Which Model, Which Plan?Guide●○○026Git & GitHub for Vibe CodersGuide●○○027Agent Stuck? Here's How to Get UnstuckGuide●●○028Getting Your Project Online (Deployment)Guide●●○029Slash Commands, Hooks & More: Steering Claude CodeGuide●●○030Skills: Knowledge Your Agent Can LoadTerm●●○031Reading Benchmarks Without Getting FooledGuide●●○032RAG (Retrieval-Augmented Generation)Concept●●○033Embeddings – text as numbersTerm●●○034Fine-tuning – training a model furtherConcept●●○035Prompt injectionConcept●●●036Structured outputsTerm●●○037Evals – systematically testing prompts and modelsConcept●●○038Git worktrees for parallel AI agentsGuide●●○039Hooks in Claude CodeGuide●●○040Multi-agent patternsConcept●●●041Context strategies for agentsConcept●●●042Tool Use: How LLMs Call ToolsConcept●●○043Computer Use: When AI Controls Mouse and KeyboardConcept●●●044Sandboxing: Why Agents Should Run IsolatedConcept●●○045Securing Agents in PracticeGuide●●○046Model Routing: The Right Model for the Right TaskConcept●●○047Caching Strategies: Prompt Caching & Context CachingConcept●●○048Plugins: Extensions for AI Coding ToolsTerm●○○049Headless Mode: Running Agents Without InteractionGuide●●○050Permission Modes for AgentsGuide●●○051Artifacts: Generated DeliverablesTerm●○○052Writing Your Own Commands: Save Recurring PromptsGuide●●○053Agent Teams: Multiple Agents, One ProjectConcept●●●054CI/CD with Agents: AI in the PipelineGuide●●○055Prompt Structures: Layout That Improves ResultsPrompt pattern●○○056Code Review with AI: Fresh Eyes Instead of Self-GradingGuide●●○057Debugging with AI Agents: Systematic, Not GuessworkGuide●●○058Testing with Agents: Generate Tests and Use Them as a GateGuide●●○059Maintaining Documentation with AIGuide●○○060Batch Processing: Automating Many Similar TasksConcept●●○061Managing API Keys SecurelyGuide●○○062Running AI Agents in Large MonoreposGuide●●●063Safe Refactoring with AI AgentsGuide●●●064Understanding and Modernizing Old Codebases with AIGuide●●●065How AI Agents Remember ThingsConcept●●○066Cutting Agent Costs: A Practical ChecklistGuide●●○067Security Audits with AI: Checking Code for VulnerabilitiesGuide●●●068Databases with Agents: Safe, Not RiskyGuide●●●069Understanding Unfamiliar Code with AIGuide●●○070Frontend with AI: Screenshots as FeedbackGuide●●○071Pair Programming Patterns with AIConcept●●○072Building Your Own Agents with the Claude Agent SDKGuide●●●073Writing Your Own MCP ServerGuide●●●074What Is Google Antigravity?Term●●○075Agent Observability: Seeing What Your Agent Actually DoesGuide●●●076Running Open Models Locally (Ollama & Co.)Guide●●○077Defending Against Prompt Injection in PracticeGuide●●●078Rolling Out AI Coding Tools to a TeamGuide●●○079Building a Simple RAG System YourselfGuide●●●080Getting Data from Websites with AgentsGuide●●○081Finding and Fixing Performance Problems with AI AgentsGuide●●●082Terminal Basics for BeginnersGuide●○○083AI Coding IDE vs. CLI: Two Ways to Work With an AgentConcept●○○084Rate Limits and Quotas: Why AI Tools Sometimes Say Slow DownTerm●○○085Temperature and Sampling: Why the Same Prompt Gives Different AnswersTerm●●○086Vector Databases: Where Embeddings Actually LiveTerm●●○087Chunking Strategies: How to Split Text for RAGConcept●●○088Human-in-the-Loop: Where People Should Still Check the WorkConcept●●○089Data Privacy and AI Tools: What Actually Leaves Your MachineGuide●●○090MCP Security: The Risks of Connecting Tools to an AgentConcept●●●091SWE-bench, Terminal-Bench & Co.: Reading Coding-Agent BenchmarksConcept●●●092Few-Shot Examples: Show, Don't Just TellPrompt pattern●○○093Role Prompts: What "You Are an Expert..." Actually ChangesPrompt pattern●○○094Self-Critique Loops: Have the Model Check Its Own WorkPrompt pattern●●○095Forcing Output Formats: From Prompt Tricks to Guaranteed SchemasPrompt pattern●●○096Reasoning Models: When a Model Thinks Before It AnswersTerm●●○097Mixture of Experts: Huge Models That Only Use a Slice of ThemselvesTerm●●●098Streaming: Why Answers Appear Word by WordTerm●○○099Quantization: Squeezing Model Weights Down to FitTerm●●○100From GitHub Issue to Pull Request: Letting an Agent Do the WorkGuide●●○101Checkpoints and Rollbacks: Your Undo Button for Agent WorkGuide●●○102Web Search and Grounding: Letting Agents Fetch Current FactsConcept●●○103Knowledge Distillation: Training a Small Model to Copy a Big OneTerm●●●104Speculative Decoding: A Small Model Guesses, the Big One ChecksTerm●●●105Optimizing Latency: Making Agents Feel FastGuide●●○106AI-Generated Code and Licensing: Who Actually Owns It?Concept●●○107Retrieval Evaluation: Is Your RAG System Finding the Right Thing?Concept●●●108Agents Across Multiple RepositoriesGuide●●●109Fine-Tuning or Prompting? A Decision GuideGuide●●○110Red-Teaming Your Own Agent SetupGuide●●●111Prompt Versioning: Treating Prompts Like CodeGuide●●○Showing 111 of 111 entries