https://judyailab.com/en/glossary/ Recent content in AI Glossary on Judy AI Lab https://judyailab.com/logo.jpg https://judyailab.com/logo.jpg Hugo -- 0.147.4 en https://judyailab.com/en/glossary/access-control/ Mon, 01 Jan 0001 00:00:00 +0000 https://judyailab.com/en/glossary/access-control/ What is Access Control? Security mechanisms controlling who can access what resources. Especially critical in AI Agent systems — the more autono — Judy AI Lab AI Glossary https://judyailab.com/en/glossary/adversarial-attack/ Mon, 01 Jan 0001 00:00:00 +0000 https://judyailab.com/en/glossary/adversarial-attack/ What is Adversarial Attack? Making small but carefully crafted modifications to AI model inputs, causing completely different outputs. In image reco — Judy AI Lab AI Glossary https://judyailab.com/en/glossary/agent-executor/ Mon, 01 Jan 0001 00:00:00 +0000 https://judyailab.com/en/glossary/agent-executor/ What is Agent Executor? A framework component that manages Agent lifecycles — starting, executing tasks, handling errors, stopping. Like an OS m — Judy AI Lab AI Glossary https://judyailab.com/en/glossary/agentic-ai/ Mon, 01 Jan 0001 00:00:00 +0000 https://judyailab.com/en/glossary/agentic-ai/ What is Agentic AI? A paradigm where AI doesn't just passively answer questions but proactively plans, executes, reflects, and improves its — Judy AI Lab AI Glossary https://judyailab.com/en/glossary/ai-agent/ Mon, 01 Jan 0001 00:00:00 +0000 https://judyailab.com/en/glossary/ai-agent/ What is AI Agent? An AI program that can autonomously perceive its environment, make decisions, and take actions. Unlike chatbots that jus — Judy AI Lab AI Glossary https://judyailab.com/en/glossary/alignment/ Mon, 01 Jan 0001 00:00:00 +0000 https://judyailab.com/en/glossary/alignment/ What is AI Alignment? The research field of ensuring AI behavior aligns with human intentions and values. Misaligned AI might 'follow instruct — Judy AI Lab AI Glossary https://judyailab.com/en/glossary/api-gateway/ Mon, 01 Jan 0001 00:00:00 +0000 https://judyailab.com/en/glossary/api-gateway/ What is API Gateway? A unified entry point managing all API requests, handling authentication, rate limiting, routing, and monitoring. In AI — Judy AI Lab AI Glossary https://judyailab.com/en/glossary/api-key-security/ Mon, 01 Jan 0001 00:00:00 +0000 https://judyailab.com/en/glossary/api-key-security/ What is API Key Security? Practices for protecting API keys from leakage and abuse. Use .env files, never hardcode, rotate regularly, set usage li — Judy AI Lab AI Glossary https://judyailab.com/en/glossary/api-rate-limiting/ Mon, 01 Jan 0001 00:00:00 +0000 https://judyailab.com/en/glossary/api-rate-limiting/ What is API Rate Limiting? Limiting the number of API requests a client can make within a specific timeframe. Protects servers from overload and ab — Judy AI Lab AI Glossary https://judyailab.com/en/glossary/attention-mechanism/ Mon, 01 Jan 0001 00:00:00 +0000 https://judyailab.com/en/glossary/attention-mechanism/ What is Attention Mechanism? Allows models to 'pay attention' to other relevant words in the input when processing each word. Like when reading 'bank — Judy AI Lab AI Glossary https://judyailab.com/en/glossary/backtesting/ Mon, 01 Jan 0001 00:00:00 +0000 https://judyailab.com/en/glossary/backtesting/ What is Backtesting? Testing trading strategies against historical market data. The key is avoiding overfitting — a strategy working well on — Judy AI Lab AI Glossary https://judyailab.com/en/glossary/bollinger-bands/ Mon, 01 Jan 0001 00:00:00 +0000 https://judyailab.com/en/glossary/bollinger-bands/ What is Bollinger Bands? A channel formed by a middle line (SMA) and upper/lower standard deviation bands. Price touching the upper band may sign — Judy AI Lab AI Glossary https://judyailab.com/en/glossary/chain-of-thought/ Mon, 01 Jan 0001 00:00:00 +0000 https://judyailab.com/en/glossary/chain-of-thought/ What is Chain-of-Thought (CoT)? A technique that makes LLMs reason step-by-step instead of jumping to answers. Like showing your work on a math test, Co — Judy AI Lab AI Glossary https://judyailab.com/en/glossary/cicd/ Mon, 01 Jan 0001 00:00:00 +0000 https://judyailab.com/en/glossary/cicd/ What is CI/CD? Automated code testing and deployment workflows. CI runs tests automatically after every code commit, CD deploys to prod — Judy AI Lab AI Glossary https://judyailab.com/en/glossary/claude-code/ Mon, 01 Jan 0001 00:00:00 +0000 https://judyailab.com/en/glossary/claude-code/ What is Claude Code? Anthropic's official CLI tool that lets Claude work directly in your terminal — reading/writing files, executing command — Judy AI Lab AI Glossary https://judyailab.com/en/glossary/constitutional-ai/ Mon, 01 Jan 0001 00:00:00 +0000 https://judyailab.com/en/glossary/constitutional-ai/ What is Constitutional AI? An AI alignment method by Anthropic that uses a set of explicit principles (a 'constitution') to guide AI behavior, redu — Judy AI Lab AI Glossary https://judyailab.com/en/glossary/context-window/ Mon, 01 Jan 0001 00:00:00 +0000 https://judyailab.com/en/glossary/context-window/ What is Context Window? The maximum number of tokens an LLM can process at once. Claude's context window is 200K tokens (~150K words), GPT-4 Tur — Judy AI Lab AI Glossary https://judyailab.com/en/glossary/cron-job/ Mon, 01 Jan 0001 00:00:00 +0000 https://judyailab.com/en/glossary/cron-job/ What is Cron Job? Linux's scheduled task mechanism that automatically runs scripts at specified times. The unsung hero of AI Agent systems — Judy AI Lab AI Glossary https://judyailab.com/en/glossary/data-poisoning/ Mon, 01 Jan 0001 00:00:00 +0000 https://judyailab.com/en/glossary/data-poisoning/ What is Data Poisoning? Injecting malicious data into model training data, making the model learn wrong patterns or backdoors. Like sneaking inc — Judy AI Lab AI Glossary https://judyailab.com/en/glossary/docker/ Mon, 01 Jan 0001 00:00:00 +0000 https://judyailab.com/en/glossary/docker/ What is Docker? Technology that packages applications with all dependencies into 'containers', ensuring consistent runs across any envir — Judy AI Lab AI Glossary https://judyailab.com/en/glossary/edge-ai/ Mon, 01 Jan 0001 00:00:00 +0000 https://judyailab.com/en/glossary/edge-ai/ What is Edge AI? Running AI inference on local devices (phones, IoT) instead of the cloud. Advantages: low latency, privacy protection, o — Judy AI Lab AI Glossary https://judyailab.com/en/glossary/ema/ Mon, 01 Jan 0001 00:00:00 +0000 https://judyailab.com/en/glossary/ema/ What is EMA (Exponential Moving Average)? A weighted moving average that gives more weight to recent data. We use 4 EMAs (20/50/100/200) alignment to determine tr — Judy AI Lab AI Glossary https://judyailab.com/en/glossary/embedding/ Mon, 01 Jan 0001 00:00:00 +0000 https://judyailab.com/en/glossary/embedding/ What is Embedding? A technique that converts text, images, etc. into numerical vectors. Distance between vectors represents semantic simila — Judy AI Lab AI Glossary https://judyailab.com/en/glossary/embodied-ai/ Mon, 01 Jan 0001 00:00:00 +0000 https://judyailab.com/en/glossary/embodied-ai/ What is Embodied AI? Giving AI a 'body' to perceive and act in the physical world. In 2026, VLA models let robots simultaneously understand l — Judy AI Lab AI Glossary https://judyailab.com/en/glossary/extended-thinking/ Mon, 01 Jan 0001 00:00:00 +0000 https://judyailab.com/en/glossary/extended-thinking/ What is Extended Thinking? A feature that lets LLMs perform deep internal reasoning before answering. Claude's Extended Thinking produces a thinkin — Judy AI Lab AI Glossary https://judyailab.com/en/glossary/federated-learning/ Mon, 01 Jan 0001 00:00:00 +0000 https://judyailab.com/en/glossary/federated-learning/ What is Federated Learning? A technique where multiple parties collaboratively train a model without sharing raw data. Each participant trains local — Judy AI Lab AI Glossary https://judyailab.com/en/glossary/fine-tuning/ Mon, 01 Jan 0001 00:00:00 +0000 https://judyailab.com/en/glossary/fine-tuning/ What is Fine-tuning? Training a pre-trained LLM with domain-specific data to specialize it for particular tasks. Requires much less data and — Judy AI Lab AI Glossary https://judyailab.com/en/glossary/foundation-model/ Mon, 01 Jan 0001 00:00:00 +0000 https://judyailab.com/en/glossary/foundation-model/ What is Foundation Model? Large AI models pre-trained on massive datasets that can be adapted to various downstream tasks through fine-tuning. GPT — Judy AI Lab AI Glossary https://judyailab.com/en/glossary/function-calling/ Mon, 01 Jan 0001 00:00:00 +0000 https://judyailab.com/en/glossary/function-calling/ What is Function Calling? An LLM API feature that lets models output structured function call requests instead of plain text. You define available — Judy AI Lab AI Glossary https://judyailab.com/en/glossary/gpu/ Mon, 01 Jan 0001 00:00:00 +0000 https://judyailab.com/en/glossary/gpu/ What is GPU (Graphics Processing Unit)? Core hardware for AI model training and inference. NVIDIA A100/H100 are currently the most popular AI GPUs. GPUs determi — Judy AI Lab AI Glossary https://judyailab.com/en/glossary/hallucination/ Mon, 01 Jan 0001 00:00:00 +0000 https://judyailab.com/en/glossary/hallucination/ What is Hallucination? When an LLM confidently generates content that looks correct but is actually wrong. Like a student who answers everythin — Judy AI Lab AI Glossary https://judyailab.com/en/glossary/hooks/ Mon, 01 Jan 0001 00:00:00 +0000 https://judyailab.com/en/glossary/hooks/ What is Hooks (Claude Code)? Claude Code's event interception system that auto-runs custom scripts before/after tool execution. Like Git Hooks — secu — Judy AI Lab AI Glossary https://judyailab.com/en/glossary/inference/ Mon, 01 Jan 0001 00:00:00 +0000 https://judyailab.com/en/glossary/inference/ What is Inference? The process of using a trained model to process new inputs and produce outputs. Every time you chat with ChatGPT, that's — Judy AI Lab AI Glossary https://judyailab.com/en/glossary/jailbreak/ Mon, 01 Jan 0001 00:00:00 +0000 https://judyailab.com/en/glossary/jailbreak/ What is Jailbreak? Techniques to bypass AI safety restrictions, making models output content they should refuse. Unlike Prompt Injection, j — Judy AI Lab AI Glossary https://judyailab.com/en/glossary/knowledge-base/ Mon, 01 Jan 0001 00:00:00 +0000 https://judyailab.com/en/glossary/knowledge-base/ What is Knowledge Base? An organized information repository for Agents to query and reference. Can be document collections, FAQ databases, or st — Judy AI Lab AI Glossary https://judyailab.com/en/glossary/live-trading/ Mon, 01 Jan 0001 00:00:00 +0000 https://judyailab.com/en/glossary/live-trading/ What is Live Trading? Trading with real money. The biggest differences from paper trading are psychological pressure and slippage (difference — Judy AI Lab AI Glossary https://judyailab.com/en/glossary/llm/ Mon, 01 Jan 0001 00:00:00 +0000 https://judyailab.com/en/glossary/llm/ What is LLM (Large Language Model)? An AI model trained on massive text data that can understand and generate human language. GPT-4, Claude, and Gemini are — Judy AI Lab AI Glossary https://judyailab.com/en/glossary/macd/ Mon, 01 Jan 0001 00:00:00 +0000 https://judyailab.com/en/glossary/macd/ What is MACD (Moving Average Convergence Divergence)? Uses the difference between two EMAs of different periods to judge trend strength and direction changes. MACD histogram — Judy AI Lab AI Glossary https://judyailab.com/en/glossary/market-regime/ Mon, 01 Jan 0001 00:00:00 +0000 https://judyailab.com/en/glossary/market-regime/ What is Market Regime? The current market state — trending, ranging, or high volatility. Different regimes need different strategies: ADX > 25 — Judy AI Lab AI Glossary https://judyailab.com/en/glossary/mcp/ Mon, 01 Jan 0001 00:00:00 +0000 https://judyailab.com/en/glossary/mcp/ What is MCP (Model Context Protocol)? An open protocol by Anthropic that standardizes how AI Agents connect to external tools and data sources. Like USB-C uni — Judy AI Lab AI Glossary https://judyailab.com/en/glossary/memory-system/ Mon, 01 Jan 0001 00:00:00 +0000 https://judyailab.com/en/glossary/memory-system/ What is Memory System? A mechanism that lets Agents retain information across conversations. Divided into short-term (current chat), long-term — Judy AI Lab AI Glossary https://judyailab.com/en/glossary/model-serving/ Mon, 01 Jan 0001 00:00:00 +0000 https://judyailab.com/en/glossary/model-serving/ What is Model Serving? Deploying trained AI models as services that accept API requests. Many options: run locally with Ollama, use vLLM for hi — Judy AI Lab AI Glossary https://judyailab.com/en/glossary/multi-agent-system/ Mon, 01 Jan 0001 00:00:00 +0000 https://judyailab.com/en/glossary/multi-agent-system/ What is Multi-Agent System? An architecture where multiple AI Agents collaborate, each handling different specialties. Like a company with a CEO, en — Judy AI Lab AI Glossary https://judyailab.com/en/glossary/owasp-llm-top10/ Mon, 01 Jan 0001 00:00:00 +0000 https://judyailab.com/en/glossary/owasp-llm-top10/ What is OWASP Top 10 for LLM? A list of the top 10 security risks for LLM applications, maintained by OWASP. Includes Prompt Injection, Insecure Outpu — Judy AI Lab AI Glossary https://judyailab.com/en/glossary/paper-trading/ Mon, 01 Jan 0001 00:00:00 +0000 https://judyailab.com/en/glossary/paper-trading/ What is Paper Trading? Simulating trades with virtual funds on real market data, testing strategies without real risk. A validation stage betwe — Judy AI Lab AI Glossary https://judyailab.com/en/glossary/parameters/ Mon, 01 Jan 0001 00:00:00 +0000 https://judyailab.com/en/glossary/parameters/ What is Parameters? Learnable values inside a model that determine its 'knowledge'. GPT-4 reportedly has 1.8 trillion parameters, Llama 3 ha — Judy AI Lab AI Glossary https://judyailab.com/en/glossary/position-sizing/ Mon, 01 Jan 0001 00:00:00 +0000 https://judyailab.com/en/glossary/position-sizing/ What is Position Sizing? Methods for determining how much capital to allocate per trade. No matter how good the strategy, oversized positions can — Judy AI Lab AI Glossary https://judyailab.com/en/glossary/prompt-caching/ Mon, 01 Jan 0001 00:00:00 +0000 https://judyailab.com/en/glossary/prompt-caching/ What is Prompt Caching? Caching repeated prompt prefixes to avoid reprocessing the same system prompt and context every time. Claude's Prompt Ca — Judy AI Lab AI Glossary https://judyailab.com/en/glossary/prompt-engineering/ Mon, 01 Jan 0001 00:00:00 +0000 https://judyailab.com/en/glossary/prompt-engineering/ What is Prompt Engineering? Designing input instructions that get the best results from LLMs. Good prompts can make the same model perform 10x bette — Judy AI Lab AI Glossary https://judyailab.com/en/glossary/prompt-injection/ Mon, 01 Jan 0001 00:00:00 +0000 https://judyailab.com/en/glossary/prompt-injection/ What is Prompt Injection? Attackers craft malicious inputs to make AI ignore its original instructions and perform harmful actions. Like SQL injec — Judy AI Lab AI Glossary https://judyailab.com/en/glossary/quantitative-trading/ Mon, 01 Jan 0001 00:00:00 +0000 https://judyailab.com/en/glossary/quantitative-trading/ What is Quantitative Trading? Using mathematical models and code to automate trading decisions, replacing human intuition and emotions. Core flow: dat — Judy AI Lab AI Glossary https://judyailab.com/en/glossary/rag/ Mon, 01 Jan 0001 00:00:00 +0000 https://judyailab.com/en/glossary/rag/ What is RAG (Retrieval-Augmented Generation)? A technique that lets an LLM search for relevant data before answering, rather than relying solely on training knowledge — Judy AI Lab AI Glossary https://judyailab.com/en/glossary/red-teaming/ Mon, 01 Jan 0001 00:00:00 +0000 https://judyailab.com/en/glossary/red-teaming/ What is Red Teaming? Testing AI system security by simulating attacker perspectives. Professional red teams try prompt injection, jailbreakin — Judy AI Lab AI Glossary https://judyailab.com/en/glossary/rest-api/ Mon, 01 Jan 0001 00:00:00 +0000 https://judyailab.com/en/glossary/rest-api/ What is REST API? The most common Web API design style, using HTTP methods (GET/POST/PUT/DELETE) to operate on resources. Most AI service — Judy AI Lab AI Glossary https://judyailab.com/en/glossary/risk-management/ Mon, 01 Jan 0001 00:00:00 +0000 https://judyailab.com/en/glossary/risk-management/ What is Risk Management? Systematic methods for controlling trading losses. Our risk control includes: max 2% loss per trade, 3% daily loss limit — Judy AI Lab AI Glossary https://judyailab.com/en/glossary/rlhf/ Mon, 01 Jan 0001 00:00:00 +0000 https://judyailab.com/en/glossary/rlhf/ What is RLHF (Reinforcement Learning from Human Feedback)? A method where humans rate AI responses, then use those ratings to train the AI to improve. ChatGPT's success is largely — Judy AI Lab AI Glossary https://judyailab.com/en/glossary/rsi/ Mon, 01 Jan 0001 00:00:00 +0000 https://judyailab.com/en/glossary/rsi/ What is RSI (Relative Strength Index)? An indicator measuring overbought/oversold conditions, ranging 0-100. RSI > 70 typically signals overbought (may pull ba — Judy AI Lab AI Glossary https://judyailab.com/en/glossary/sandbox/ Mon, 01 Jan 0001 00:00:00 +0000 https://judyailab.com/en/glossary/sandbox/ What is Sandbox? A security mechanism that restricts programs to operate within specific boundaries. In AI Agent deployment, sandboxes pr — Judy AI Lab AI Glossary https://judyailab.com/en/glossary/sdk/ Mon, 01 Jan 0001 00:00:00 +0000 https://judyailab.com/en/glossary/sdk/ What is SDK (Software Development Kit)? A library and toolset that lets developers quickly integrate specific services. For example, the Anthropic SDK lets you — Judy AI Lab AI Glossary https://judyailab.com/en/glossary/skills-claude-code/ Mon, 01 Jan 0001 00:00:00 +0000 https://judyailab.com/en/glossary/skills-claude-code/ What is Skills (Claude Code)? Reusable instruction templates for Claude Code, defined in Markdown with workflows and rules. Triggered via /skill comma — Judy AI Lab AI Glossary https://judyailab.com/en/glossary/stop-loss/ Mon, 01 Jan 0001 00:00:00 +0000 https://judyailab.com/en/glossary/stop-loss/ What is Stop Loss? A preset exit price that automatically closes a position when losses reach a threshold. Set dynamically using ATR (Avera — Judy AI Lab AI Glossary https://judyailab.com/en/glossary/strategy-engine/ Mon, 01 Jan 0001 00:00:00 +0000 https://judyailab.com/en/glossary/strategy-engine/ What is Strategy Engine? The core module that scans market data, calculates indicators, and generates trading signals. Our strategy engine suppor — Judy AI Lab AI Glossary https://judyailab.com/en/glossary/streaming/ Mon, 01 Jan 0001 00:00:00 +0000 https://judyailab.com/en/glossary/streaming/ What is Streaming? LLM returns results as they're generated, rather than waiting until completion. Better UX (users see text appear gradual — Judy AI Lab AI Glossary https://judyailab.com/en/glossary/structured-output/ Mon, 01 Jan 0001 00:00:00 +0000 https://judyailab.com/en/glossary/structured-output/ What is Structured Output? Making LLMs output data in a specified JSON Schema instead of free-form text. Critical for Agent development — you need — Judy AI Lab AI Glossary https://judyailab.com/en/glossary/supply-chain-attack/ Mon, 01 Jan 0001 00:00:00 +0000 https://judyailab.com/en/glossary/supply-chain-attack/ What is Supply Chain Attack? Compromising target systems through third-party packages, plugins, or dependencies. In the AI ecosystem, 340+ malicious — Judy AI Lab AI Glossary https://judyailab.com/en/glossary/take-profit/ Mon, 01 Jan 0001 00:00:00 +0000 https://judyailab.com/en/glossary/take-profit/ What is Take Profit? A preset profit-taking exit price. We use staged take profits: TP1 (1.5:1 R:R) closes 25%, TP2 (3:1) closes another 25%, — Judy AI Lab AI Glossary https://judyailab.com/en/glossary/tokenization/ Mon, 01 Jan 0001 00:00:00 +0000 https://judyailab.com/en/glossary/tokenization/ What is Tokenization? The process of breaking text into small units (tokens) that models can process. English: ~1 word ≈ 1.3 tokens. Chinese: — Judy AI Lab AI Glossary https://judyailab.com/en/glossary/tool-use/ Mon, 01 Jan 0001 00:00:00 +0000 https://judyailab.com/en/glossary/tool-use/ What is Tool Use / Function Calling? Allowing LLMs to call external tools (search engines, databases, APIs) to complete tasks. This is the key difference bet — Judy AI Lab AI Glossary https://judyailab.com/en/glossary/training/ Mon, 01 Jan 0001 00:00:00 +0000 https://judyailab.com/en/glossary/training/ What is Training? The process of having a model learn patterns and knowledge from data. Pre-training an LLM requires thousands of GPUs run — Judy AI Lab AI Glossary https://judyailab.com/en/glossary/transformer/ Mon, 01 Jan 0001 00:00:00 +0000 https://judyailab.com/en/glossary/transformer/ What is Transformer? A deep learning architecture proposed by Google in 2017 that uses 'attention mechanism' to understand relationships betw — Judy AI Lab AI Glossary https://judyailab.com/en/glossary/vector-database/ Mon, 01 Jan 0001 00:00:00 +0000 https://judyailab.com/en/glossary/vector-database/ What is Vector Database? A database specialized for storing and searching embedding vectors. Traditional databases search by keywords, vector dat — Judy AI Lab AI Glossary https://judyailab.com/en/glossary/walk-forward-optimization/ Mon, 01 Jan 0001 00:00:00 +0000 https://judyailab.com/en/glossary/walk-forward-optimization/ What is Walk-Forward Optimization (WFO)? A validation method to prevent backtesting overfitting. Data is split into segments — train on earlier portions, validat — Judy AI Lab AI Glossary https://judyailab.com/en/glossary/websocket/ Mon, 01 Jan 0001 00:00:00 +0000 https://judyailab.com/en/glossary/websocket/ What is WebSocket? A protocol enabling bidirectional real-time communication between server and client. Unlike HTTP which requires reconnec — Judy AI Lab AI Glossary https://judyailab.com/en/glossary/weights/ Mon, 01 Jan 0001 00:00:00 +0000 https://judyailab.com/en/glossary/weights/ What is Weights? The specific values of model parameters, continuously adjusted during training. Open-source models (like Llama) publish — Judy AI Lab AI Glossary