Skip to content

Reference

AI glossary

The words you meet when you build software with coding agents like Claude Code, Codex, Cursor and Grok Build. Each entry explains what the term means, how each tool handles it, and when it's worth using.

Every tool-specific detail comes from the vendor's own documentation, and each entry shows when I last updated it.

69 terms

#

A

ACP
ACP is how an editor drives a coding agent over stdin and stdout. Cursor and Grok Build speak it. Claude Code and Codex document a different programmatic path.
Agent harness
An agent harness is the program around a model: files, a shell, permissions, and the loop. How Claude Code defines it, and what Codex, Cursor and Grok document.
Agent loop
The agent loop is the cycle a coding agent repeats: look, act, check, and go again. How Claude Code names that cycle, and what the other tools document.
Agent memory
Agent memory is notes a coding agent keeps between sessions. How Claude Code, Codex and Grok Build store them, and what Cursor documents instead.
Agent SDK
An agent SDK is a library that runs an agent from your own program. How Claude Code, the Codex SDK, Cursor's two packages, and Grok Build differ.
Agent skills
An agent skill is a SKILL.md folder that teaches a coding agent one task. Where Claude Code, Codex, Cursor and Grok Build load it, and when to skip one.
Agent teams
Agent teams coordinate several coding agents through shared tasks and messages. Learn how they differ from subagents and when parallel work helps.
Agent work log
An agent work log records completed changes across coding sessions. See how it differs from chat history, what to record, and how Git can supply the entries.
Agent-readable CLI
An agent-readable CLI explains its tasks, commands, and output so a coding agent can use it. See a real capabilities command and where permissions apply.
Agentic coding
Agentic coding means directing an agent that reads your repo, edits files and runs commands. How that loop works in Claude Code, Codex, Cursor and Grok Build.
AI (artificial intelligence)
Artificial intelligence covers software that performs tasks associated with human intelligence. See how models and agents fit into everyday coding work.
AI code review
AI code review is an agent reading a diff for bugs. How Claude Code, Codex, Cursor Bugbot and Grok Build run that review.
AI slop
AI slop is generic writing or code a model repeats until drafts sound the same. Claude Code, Codex, Cursor and Grok Build ship no filter for it.

B

Browser agents
Browser agents open pages and use controls to test web apps. Learn how coding tools connect to a browser, what to ask them to check, and common pitfalls.

C

Checkpoints
Checkpoints let you undo a coding agent's edits inside a session. How rewind works in Claude Code, Cursor and Grok Build, and what Codex documents instead.
CLAUDE.md
CLAUDE.md is the Markdown file of project instructions Claude Code loads at the start of a session. How Codex, Cursor and Grok Build treat that same filename.
Cloud agents
Cloud agents run a coding task on a remote machine instead of your laptop. How Claude Code, Codex, Cursor and Grok Bot start one, and what they cannot see.
Coding agent
A coding agent uses a model and tools to read a repo, edit files and run commands in a loop. How Claude Code, Codex, Cursor and Grok Build each do that job.
Compaction
Compaction replaces older chat turns with a shorter summary so a coding agent can keep going. How Claude Code, Codex, Cursor and Grok Build each run it.
Context engineering
Context engineering is choosing what an agent sees before it edits. How Claude Code, Codex, Cursor and Grok Build load rules, files and skills.
Context window
The context window is everything a coding agent can see at once. How to check it, free it and keep it small in Claude Code, Codex, Cursor and Grok Build.
Cursor Tab
Cursor Tab suggests the next edit as gray text while you type. How Tab, Escape, and jump-in-file work, and the next-message predictions in Codex and Grok.

D

Deep links
A deep link is a URL that opens a coding agent with a prompt waiting in the box. How claude-cli, cursor, and codex links work, and what Grok documents.

E

Embeddings
An embedding is a list of numbers that puts similar text close together. How OpenAI and xAI build them, and why Cursor search says it does not store them.
Evals
An eval is a fixed prompt, a real agent run, and a check you can repeat. How Claude Code, Codex, Cursor and the Grok API score that run.

F

Fast mode
Fast mode makes a supported model answer sooner and charges more for that speed. How Claude Code, Codex, and Cursor turn it on, and what Grok Build documents.
Fine-tuning
Fine-tuning trains an existing model a little more on your examples, for a narrow job. OpenAI's platform is closed to new users. The local path is posted here.
Frontier model
A frontier model is one of the most capable models right now, and the label moves. How Claude Code, Codex, Cursor and Grok name the model they point you at.

G

Generative AI
Generative AI produces text, code, images and other content from learned patterns. See how it fits coding tools, when to use it, and what to check.
Git worktrees
A git worktree is a second checkout of one repo, so an agent can edit while your checkout stays put. How Claude Code, Codex, Cursor and Grok Build start one.
Goal mode
Goal mode keeps a coding agent working until a condition holds. How /goal works in Claude Code, Codex, the Cursor CLI and Grok Build.
Grounding
Grounding connects an AI answer to source material. Learn how code searches, documentation, and test results help coding agents support their claims.

H

Hallucination
An AI hallucination is a plausible but false answer. Learn how to catch invented APIs, verify coding-agent claims, and separate output from evidence.
Headless mode
Headless mode runs a coding agent from a script, with no chat UI. How claude -p, codex exec, the Cursor CLI and grok -p differ on permissions.
Hooks
Hooks run your own scripts when a coding agent calls a tool or stops. How hooks work in Claude Code, Codex, Cursor and Grok Build, with examples.

I

Inference
Inference is running a trained model on new input. Learn where coding models run, how inference differs from training, and what a local agent needs.

J

K

L

LLM
An LLM generates text and code from learned patterns. Learn how the model fits inside a coding agent, with a small example and links to hands-on guides.
llms.txt
llms.txt is a Markdown guide to a website's useful content for AI agents. See a real file, how agents follow its links, and how it differs from robots.txt.

M

Model routing
Model routing chooses which model handles a request. Learn how automatic routing differs from manual model selection and fallback in coding agents.
Model weights
Model weights are the learned numbers inside a neural network. Understand how they differ from prompts, model settings, and the tools around a coding agent.
Multimodal model
A multimodal model takes more than text, such as a screenshot, in the same request as the prompt. How Claude Code, Codex, Cursor and Grok accept an image.

N

O

Output styles
Output styles guide a coding agent's tone and response format. Learn how they differ from verbosity, reasoning summaries, and project instructions.

P

Permission modes
Permission modes decide what a coding agent can do without asking. The modes in Claude Code, Codex, Cursor and Grok Build, and what YOLO mode really skips.
Plan mode
Plan mode makes a coding agent research and propose a plan before it edits code. How it works in Claude Code, Codex, Cursor and Grok Build, and when to use it.
Plugins
A plugin bundles skills, hooks and tools you install together. How plugins and marketplaces work in Claude Code, Codex, Cursor and Grok Build.
Prompt caching
Prompt caching reuses processing for a matching prompt prefix. Learn what it saves in coding sessions, what stays in context, and how to check usage.
Prompt engineering
Prompt engineering is writing the request on purpose, so an agent edits the right files. What Claude Code, Codex, Cursor and Grok Build tell you to include.
Prompt injection
Prompt injection is instructions hidden in text a coding agent reads. How Claude Code, Codex, Cursor and Grok Build limit what that text can make the agent do.

R

RAG
RAG fetches relevant passages and puts them in the prompt so the model answers from those passages. How that differs from search in the coding agents.
Reasoning effort
Reasoning effort sets how long a model thinks before it answers. The levels in Claude Code and Codex, what Cursor's plans fix, and how Grok sets effort.
Rules
Project rules are durable instructions a coding agent loads for a repo. How they work in Cursor, Claude Code, Codex and Grok Build, and when to skip them.

S

Sandbox
An agent sandbox limits which files and hosts a coding agent's commands can reach. How the boundary works in Claude Code, Codex, Cursor and Grok Build.
Scheduled agent tasks
A scheduled agent task reruns a saved prompt on a clock or an event, without you in the chat. How Claude Code, Codex, Cursor, and Grok set that up.
Sessions
A session is a saved coding-agent conversation you can resume later. How Claude Code, Codex, the Cursor CLI and Grok Build store, name, resume and fork one.
Side chats
A side chat is a question beside the main coding session so the answer stays out of that transcript. How Claude Code, Codex, Cursor, and Grok Build open one.
Slash commands
Slash commands are the /name controls inside a coding agent session. How they work in Claude Code, Codex, Cursor and Grok Build, and how to add your own.
Slopsquatting
Slopsquatting is registering a package name a language model invented, so a later install of that name runs someone else's code. What a 2025 study measured.
Software factory
A software factory organizes AI coding into repeatable stages, with project context, bounded tasks, checks, and review before changes reach the product.
Spec-driven development
Spec-driven development writes the behavior and the check before an agent edits. How plan mode and goals support that in these four tools.
Status line
A status line is the row under a coding session that shows the model, context, or a script you wrote. How Claude Code, Codex, Cursor, and Grok Build set it.
Structured outputs
Structured outputs are answers that follow a JSON Schema you send with the request. How that differs from JSON mode in Claude Code, Codex, Cursor and Grok.
Subagents
A subagent is a helper your coding agent starts with its own context window. How subagents work in Claude Code, Codex, Cursor and Grok Build.
Subscription vs API key
A subscription includes an allowance; an API key connects usage to a provider account. See how coding agents handle the two and avoid billing surprises.
System prompt
A system prompt is the instruction layer a coding agent sends ahead of your chat. How Claude Code, Codex, Cursor and Grok Build set that layer.

T

Temperature
Temperature changes how a language model samples its next token. Learn what it affects, when to adjust it, and why lower values do not ensure correct code.
Tokens and usage limits
A token is the unit a model reads and writes. A usage limit is how much of that work a plan includes. How Claude Code, Codex, Cursor and Grok count it.
Tool calling
Tool calling is when a model names a function and its arguments, and the app runs it. How Claude Code, Codex, Cursor and Grok Build take that step.
Training data
Training data is what a model learned from, and it stops at a cutoff. Dates on the Grok 4.7, GPT-6.1 Terra and Claude cards, and how an agent reads your repo.

U

V

Vibe coding
Vibe coding is describing an app to a tool that scaffolds it while you stay out of the repo. How that differs from Claude Code, Codex, Cursor and Grok Build.

Y