Website & app development, A to Z.
345 plain-English definitions covering web, mobile, backend, SEO, fintech, ecommerce, ERP, CRM, and AI — written by working engineers, for founders and operators.
Recently added
LLM
Large language model — a neural network trained on massive text corpora that generates and understands human language. Examples: GPT-5, Claude Sonnet, Gemini, Llama.
Read definition → AIRAG
Retrieval-augmented generation — an AI pattern that grounds LLM outputs in retrieved documents so answers cite real sources instead of hallucinating.
Read definition → AIEmbeddings
Numeric vector representations of text, images, or other data — used for semantic search, clustering, and retrieval-augmented generation.
Read definition → AIVector Database
A database purpose-built for storing high-dimensional vector embeddings and running fast nearest-neighbour similarity searches.
Read definition → AIPrompt Engineering
The practice of designing, testing, and iterating on prompts to reliably get high-quality outputs from large language models.
Read definition → AIFine-Tuning
Adapting a pre-trained large language model to a specific domain, task, or style by continuing training on a smaller, targeted dataset.
Read definition → AITokenization
The process of splitting text into smaller units (tokens) that a language model can process — typically subwords, not full words.
Read definition → AIContext Window
The maximum number of tokens a language model can process at once — including prompt, retrieved documents, chat history, and output.
Read definition → AIHallucination
When a language model generates plausible-sounding but factually incorrect information — often citing fake sources, dates, or quotes.
Read definition → AIAI Agent
An LLM-driven system that can plan, use tools, take actions, and iterate toward a goal — beyond simple question answering.
Read definition → AIChatbot
A conversational software interface — from simple rule-based menus to modern LLM-powered assistants that hold multi-turn conversations.
Read definition → AITransformer
The neural network architecture that powers modern LLMs — introduced in the 2017 "Attention Is All You Need" paper, based on self-attention.
Read definition →