The whole encyclopedia

The A-Z index

All 78 entries in one alphabetical list. Each line is the term, its one-sentence definition, and the category it lives in - click through for the full entry.

A

  • Agent frameworks Libraries and SDKs that handle the agent loop, tool wiring, and state so you build behavior instead of plumbing. Agents & Orchestration
  • Agent memory Mechanisms that let an AI agent carry information across steps and sessions beyond what fits in the context window. Agents & Orchestration
  • Agentic workflow A multi-step process that chains, branches, or loops model calls so an AI system can complete tasks too big for one prompt. Agents & Orchestration
  • AGENTS.md A Markdown file in a repository that gives AI coding agents project-specific instructions, conventions, and commands. AI Coding
  • AI agent A system where a language model plans, calls tools, and loops on results to finish a task with minimal supervision. Agents & Orchestration
  • AI app builder A platform that turns a natural-language description into a working, deployable application without hand-written code. AI Coding
  • AI code review Using AI to read a code change and flag bugs, security issues, and style problems before or alongside human review. AI Coding
  • AI coding agent Software that plans and executes multi-step coding tasks - reading files, editing code, and running tests with minimal supervision. AI Coding
  • AI pair programming A working style where a developer and an AI assistant write code together, with the human reviewing every change as it lands. AI Coding
  • AI regulation Laws and frameworks that govern how AI systems can be built and deployed, usually scaled to the risk they pose. Safety & Governance
  • AI safety The practice of preventing AI systems from causing harm, from everyday failures to large-scale misuse. Safety & Governance
  • Alignment Training AI models so their behavior matches human intent and values, not just the literal words of an instruction. Safety & Governance

B

  • Batching Grouping multiple requests into one GPU pass so serving hardware stays fully utilized. Inference & Serving

C

  • Choosing a model A framework for weighing capability, latency, cost, privacy, and openness when picking a model for a task. Models & Providers
  • Chunking Splitting documents into smaller pieces so each one can be embedded and retrieved on its own. Retrieval & Data
  • Claude Anthropic's family of language models, accessed through an API and major cloud platforms rather than downloadable weights. Models & Providers
  • Computer use An agent capability where the model reads the screen and issues clicks and keystrokes to operate software built for humans. Agents & Orchestration
  • Context management Keeping an AI agent's working context relevant and small through compaction, memory files, and delegating work to subagents. AI Coding
  • Context window The maximum amount of text, measured in tokens, that a model can consider in a single request. Core Concepts

D

  • Data pipelines for AI The ingestion, cleaning, chunking, and embedding steps that turn raw data into a searchable index. Retrieval & Data
  • DeepSeek A Chinese AI lab known for open-weight models with strong reasoning and unusually low training costs. Models & Providers
  • Distillation Training a smaller model to imitate a larger one, keeping much of the capability at far lower cost. Core Concepts

E

  • Embedding A list of numbers capturing a piece of content's meaning, so similar things sit close together in vector space. Core Concepts
  • Embedding models A model that converts text into a vector of numbers so similar meanings land near each other. Retrieval & Data
  • Evals (AI evaluations) Structured tests that score an AI system's outputs so teams can measure quality and catch regressions. Evals & Observability

F

  • Fine-tuning Further training a pretrained model on your own examples to specialize its behavior for a task. Core Concepts

G

  • Gemini Google's multimodal model family, accessed through the Gemini API, Vertex AI, and Google's own products. Models & Providers
  • GPT OpenAI's family of closed-weight language models, served through its API, Azure, and the ChatGPT products. Models & Providers
  • GPUs for AI The parallel processors that run neural networks, where memory size matters as much as raw speed. Inference & Serving
  • Guardrails Programmatic checks on an AI system's inputs, outputs, and actions that block or correct behavior outside defined limits. Agents & Orchestration

H

  • Hallucination When a model states false information fluently and confidently because it generates plausible text, not verified facts. Core Concepts
  • Human in the loop A design pattern where a person reviews, approves, or corrects an AI system's actions at defined checkpoints. Agents & Orchestration
  • Hybrid search Running keyword and vector search together and merging results, so exact terms and meaning both count. Retrieval & Data

I

  • Inference Running a trained model to produce output - the phase where every user request is actually served. Core Concepts
  • Inference provider A company that runs AI models on its own hardware and sells access through an API. Inference & Serving

J

  • Jailbreaking Crafting prompts that talk an AI model into ignoring its safety training and producing restricted output. Safety & Governance

K

  • Knowledge graph A network of entities and their relationships that lets AI systems follow facts instead of guessing at them. Retrieval & Data

L

  • Llama Meta's open-weight model family that developers can download, run locally, and fine-tune under a source-available license. Models & Providers
  • LLM (large language model) A neural network trained on huge amounts of text to predict the next token, which lets it generate and understand language. Core Concepts
  • LLM observability Collecting traces, metrics, and quality signals from a live AI system so problems surface before users complain. Evals & Observability
  • LLM-as-judge Using a language model to score another model's outputs against a rubric instead of human review. Evals & Observability
  • Local LLM Running a language model entirely on hardware you control instead of calling a hosted API. Inference & Serving

M

  • MCP (Model Context Protocol) An open protocol that lets AI applications connect to external tools and data through a standard client-server interface. Agents & Orchestration
  • Mistral A French AI lab whose model family spans open-weight downloads and a commercial API, with a focus on efficiency. Models & Providers
  • Mixture of experts An architecture that activates only a few specialist subnetworks per token, so a huge model runs at a smaller model's cost. Core Concepts
  • Model benchmarks Standardized tests that score model capabilities, useful for rough comparison but easy to overfit and game. Models & Providers
  • Model cards A structured document describing an AI model's intended use, training data, evaluations, and known limitations. Safety & Governance
  • Multi-agent systems An architecture where several AI agents split a task, each handling one role, coordinated by an orchestrator or a shared plan. Agents & Orchestration
  • Multimodal AI Models that accept and reason over more than text - images, audio, or video - within one system. Core Concepts

O

  • Ollama A tool that downloads open-weight models and runs them locally with a single command and a local API. Inference & Serving
  • Open-weights models Models whose trained weights are published for anyone to download, run locally, and fine-tune. Core Concepts

P

  • pgvector A Postgres extension that stores embeddings and runs similarity search inside the database you already have. Retrieval & Data
  • Prompt caching Reusing the computed state of a repeated prompt prefix so later requests skip that work. Inference & Serving
  • Prompt engineering Designing the instructions, examples, and context you give a model to get reliable, useful output. Core Concepts
  • Prompt injection An attack where malicious instructions hidden in content an LLM reads override what the developer told it to do. Safety & Governance
  • Prompt testing Running prompt changes against a fixed set of test cases so an edit cannot silently degrade quality. Evals & Observability

Q

  • Quantization Storing a model's weights in lower-precision numbers so it needs less memory and runs faster. Core Concepts
  • Qwen Alibaba's family of open-weight models spanning many sizes, strong in multilingual and coding tasks. Models & Providers

R

  • RAG (retrieval augmented generation) Fetching relevant documents at query time so a language model can answer from your data instead of memory alone. Retrieval & Data
  • Reasoning models Models trained to work through problems step by step before answering, trading time and tokens for accuracy. Core Concepts
  • Red teaming Deliberately attacking your own AI system to find jailbreaks and harmful failures before attackers do. Evals & Observability
  • Reranking A second scoring pass that reorders retrieved candidates so the most relevant results come first. Retrieval & Data
  • Responsible AI The organizational practice of building AI systems that are fair, transparent, and accountable. Safety & Governance
  • RLHF (reinforcement learning from human feedback) Training a model toward answers humans prefer by scoring its outputs and reinforcing the good ones. Core Concepts

S

  • Semantic search Search that ranks results by meaning, using embeddings, so matches do not require the exact words. Retrieval & Data
  • Spec-driven development Writing a detailed specification first so AI coding agents implement, and get reviewed, against an agreed plan. AI Coding
  • Streaming (token streaming) Sending each generated token to the user as it is produced instead of waiting for the full reply. Inference & Serving
  • Structured output Forcing a model's reply to match a schema, such as valid JSON, so software can parse it reliably. Inference & Serving
  • System prompt Hidden instructions sent before user messages that set a model's role, rules, and tone for the conversation. Core Concepts

T

  • Temperature A setting that controls how random a model's word choices are, from deterministic to creative. Core Concepts
  • Token The chunk of text - roughly three-quarters of a word - that a language model reads and writes one at a time. Core Concepts
  • Token cost tracking Counting tokens per request and pricing them per model so AI spend is a metric, not a surprise bill. Evals & Observability
  • Tool use (function calling) Letting a language model request actions by emitting structured calls that your code executes and whose results feed back in. Agents & Orchestration
  • Tracing Recording every step of an AI request as a tree of spans so you can see exactly what the system did. Evals & Observability
  • Transformer The neural network architecture, built on attention, that underpins nearly every modern language model. Core Concepts

V

  • Vector database A database that stores embeddings and finds nearest neighbors fast, powering semantic search and RAG. Retrieval & Data
  • Vibe coding Building software by describing intent to an AI and accepting code you judge by behavior rather than by reading it line by line. AI Coding
  • vLLM An open-source serving engine that squeezes high throughput out of GPUs with paged attention and continuous batching. Inference & Serving