Core Concepts

Agentic AI

What is Agentic AI?

A paradigm where AI doesn’t just passively answer questions but proactively plans, executes, …

beginner

AI Agent

What is AI Agent?

An AI program that can autonomously perceive its environment, make decisions, and take actions. Unlike …

beginner

AI Alignment

What is AI Alignment?

The research field of ensuring AI behavior aligns with human intentions and values. Misaligned AI …

intermediate

Attention Mechanism

What is Attention Mechanism?

Allows models to ‘pay attention’ to other relevant words in the input when …

advanced

Chain-of-Thought (CoT)

What is Chain-of-Thought (CoT)?

A technique that makes LLMs reason step-by-step instead of jumping to answers. Like …

intermediate

Constitutional AI

What is Constitutional AI?

An AI alignment method by Anthropic that uses a set of explicit principles (a …

advanced

Context Window

What is Context Window?

The maximum number of tokens an LLM can process at once. Claude’s context window is 200K …

beginner

Embedding

What is Embedding?

A technique that converts text, images, etc. into numerical vectors. Distance between vectors …

intermediate

Embodied AI

What is Embodied AI?

Giving AI a ‘body’ to perceive and act in the physical world. In 2026, VLA models let …

intermediate

Fine-tuning

What is Fine-tuning?

Training a pre-trained LLM with domain-specific data to specialize it for particular tasks. …

intermediate

Foundation Model

What is Foundation Model?

Large AI models pre-trained on massive datasets that can be adapted to various downstream …

beginner

Hallucination

What is Hallucination?

When an LLM confidently generates content that looks correct but is actually wrong. Like a …

beginner

Inference

What is Inference?

The process of using a trained model to process new inputs and produce outputs. Every time you chat …

beginner

LLM (Large Language Model)

What is LLM (Large Language Model)?

An AI model trained on massive text data that can understand and generate human …

beginner

Multi-Agent System

What is Multi-Agent System?

An architecture where multiple AI Agents collaborate, each handling different specialties. …

intermediate

Parameters

What is Parameters?

Learnable values inside a model that determine its ‘knowledge’. GPT-4 reportedly has 1.8 …

intermediate

Prompt Engineering

What is Prompt Engineering?

Designing input instructions that get the best results from LLMs. Good prompts can make the …

beginner

RAG (Retrieval-Augmented Generation)

What is RAG (Retrieval-Augmented Generation)?

A technique that lets an LLM search for relevant data before answering, …

intermediate

RLHF (Reinforcement Learning from Human Feedback)

What is RLHF (Reinforcement Learning from Human Feedback)?

A method where humans rate AI responses, then use those …

advanced

Tokenization

What is Tokenization?

The process of breaking text into small units (tokens) that models can process. English: ~1 word β‰ˆ …

beginner

Tool Use / Function Calling

What is Tool Use / Function Calling?

Allowing LLMs to call external tools (search engines, databases, APIs) to complete …

beginner

Training

What is Training?

The process of having a model learn patterns and knowledge from data. Pre-training an LLM requires …

intermediate

Transformer

What is Transformer?

A deep learning architecture proposed by Google in 2017 that uses ‘attention mechanism’ …

intermediate

Vector Database

What is Vector Database?

A database specialized for storing and searching embedding vectors. Traditional databases …

intermediate

Weights

What is Weights?

The specific values of model parameters, continuously adjusted during training. Open-source models …

intermediate

Frameworks & Tools

Agent Executor

What is Agent Executor?

A framework component that manages Agent lifecycles β€” starting, executing tasks, handling …

intermediate

API Gateway

What is API Gateway?

A unified entry point managing all API requests, handling authentication, rate limiting, routing, …

intermediate

Claude Code

What is Claude Code?

Anthropic’s official CLI tool that lets Claude work directly in your terminal β€” …

beginner

Extended Thinking

What is Extended Thinking?

A feature that lets LLMs perform deep internal reasoning before answering. Claude’s …

intermediate

Function Calling

What is Function Calling?

An LLM API feature that lets models output structured function call requests instead of plain …

intermediate

Hooks (Claude Code)

What is Hooks (Claude Code)?

Claude Code’s event interception system that auto-runs custom scripts before/after …

intermediate

Knowledge Base

What is Knowledge Base?

An organized information repository for Agents to query and reference. Can be document …

beginner

MCP (Model Context Protocol)

What is MCP (Model Context Protocol)?

An open protocol by Anthropic that standardizes how AI Agents connect to external …

beginner

Memory System

What is Memory System?

A mechanism that lets Agents retain information across conversations. Divided into short-term …

intermediate

Prompt Caching

What is Prompt Caching?

Caching repeated prompt prefixes to avoid reprocessing the same system prompt and context every …

intermediate

SDK (Software Development Kit)

What is SDK (Software Development Kit)?

A library and toolset that lets developers quickly integrate specific services. …

beginner

Skills (Claude Code)

What is Skills (Claude Code)?

Reusable instruction templates for Claude Code, defined in Markdown with workflows and …

intermediate

Streaming

What is Streaming?

LLM returns results as they’re generated, rather than waiting until completion. Better UX …

intermediate

Structured Output

What is Structured Output?

Making LLMs output data in a specified JSON Schema instead of free-form text. Critical for …

intermediate

Infrastructure

API Rate Limiting

What is API Rate Limiting?

Limiting the number of API requests a client can make within a specific timeframe. Protects …

intermediate

CI/CD

What is CI/CD?

Automated code testing and deployment workflows. CI runs tests automatically after every code commit, CD …

intermediate

Cron Job

What is Cron Job?

Linux’s scheduled task mechanism that automatically runs scripts at specified times. The unsung …

beginner

Docker

What is Docker?

Technology that packages applications with all dependencies into ‘containers’, ensuring …

beginner

Edge AI

What is Edge AI?

Running AI inference on local devices (phones, IoT) instead of the cloud. Advantages: low latency, …

intermediate

Federated Learning

What is Federated Learning?

A technique where multiple parties collaboratively train a model without sharing raw data. …

advanced

GPU (Graphics Processing Unit)

What is GPU (Graphics Processing Unit)?

Core hardware for AI model training and inference. NVIDIA A100/H100 are …

beginner

Model Serving

What is Model Serving?

Deploying trained AI models as services that accept API requests. Many options: run locally with …

intermediate

REST API

What is REST API?

The most common Web API design style, using HTTP methods (GET/POST/PUT/DELETE) to operate on …

beginner

WebSocket

What is WebSocket?

A protocol enabling bidirectional real-time communication between server and client. Unlike HTTP …

intermediate

Security

Access Control

What is Access Control?

Security mechanisms controlling who can access what resources. Especially critical in AI Agent …

beginner

Adversarial Attack

What is Adversarial Attack?

Making small but carefully crafted modifications to AI model inputs, causing completely …

advanced

API Key Security

What is API Key Security?

Practices for protecting API keys from leakage and abuse. Use .env files, never hardcode, …

beginner

Data Poisoning

What is Data Poisoning?

Injecting malicious data into model training data, making the model learn wrong patterns or …

intermediate

Jailbreak

What is Jailbreak?

Techniques to bypass AI safety restrictions, making models output content they should refuse. Unlike …

beginner

OWASP Top 10 for LLM

What is OWASP Top 10 for LLM?

A list of the top 10 security risks for LLM applications, maintained by OWASP. Includes …

intermediate

Prompt Injection

What is Prompt Injection?

Attackers craft malicious inputs to make AI ignore its original instructions and perform …

beginner

Red Teaming

What is Red Teaming?

Testing AI system security by simulating attacker perspectives. Professional red teams try prompt …

intermediate

Sandbox

What is Sandbox?

A security mechanism that restricts programs to operate within specific boundaries. In AI Agent …

beginner

Supply Chain Attack

What is Supply Chain Attack?

Compromising target systems through third-party packages, plugins, or dependencies. In the …

intermediate

Quantitative Trading

Backtesting

What is Backtesting?

Testing trading strategies against historical market data. The key is avoiding overfitting β€” a …

beginner

Bollinger Bands

What is Bollinger Bands?

A channel formed by a middle line (SMA) and upper/lower standard deviation bands. Price …

beginner

EMA (Exponential Moving Average)

What is EMA (Exponential Moving Average)?

A weighted moving average that gives more weight to recent data. We use 4 EMAs …

beginner

Live Trading

What is Live Trading?

Trading with real money. The biggest differences from paper trading are psychological pressure and …

beginner

MACD (Moving Average Convergence Divergence)

What is MACD (Moving Average Convergence Divergence)?

Uses the difference between two EMAs of different periods to judge …

intermediate

Market Regime

What is Market Regime?

The current market state β€” trending, ranging, or high volatility. Different regimes need …

advanced

Paper Trading

What is Paper Trading?

Simulating trades with virtual funds on real market data, testing strategies without real risk. A …

beginner

Position Sizing

What is Position Sizing?

Methods for determining how much capital to allocate per trade. No matter how good the …

intermediate

Quantitative Trading

What is Quantitative Trading?

Using mathematical models and code to automate trading decisions, replacing human …

beginner

Risk Management

What is Risk Management?

Systematic methods for controlling trading losses. Our risk control includes: max 2% loss per …

beginner

RSI (Relative Strength Index)

What is RSI (Relative Strength Index)?

An indicator measuring overbought/oversold conditions, ranging 0-100. RSI > 70 …

beginner

Stop Loss

What is Stop Loss?

A preset exit price that automatically closes a position when losses reach a threshold. Set …

beginner

Strategy Engine

What is Strategy Engine?

The core module that scans market data, calculates indicators, and generates trading signals. …

intermediate

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 …

beginner

Walk-Forward Optimization (WFO)

What is Walk-Forward Optimization (WFO)?

A validation method to prevent backtesting overfitting. Data is split into …

advanced
Get new posts by email: