Glossary

Plain-English definitions for common vibe-coding terms. Updated: September 17, 2025.

Diff

A preview of changes between two versions of a file. Lines starting with + will be added; lines starting with - will be removed. Read a diff like a pull request before applying it.

Patch

One or more diffs bundled together, typically the exact text you can apply to modify files.

Hunk

A contiguous block of changes within a diff. The header (e.g., @@ -1,4 +1,7 @@) shows the affected line ranges.

Repo-aware chat

Chat grounded in your repository’s files, not generic examples—answers reference your code, paths, and types.

Agent

A system that plans actions, calls tools (like file edits or web fetches), observes results, and iterates toward a goal.

Plan & Execute (plan-then-apply)

An agent workflow that first outlines steps (plan) and then performs them (execute), often safer for large changes.

Tool use

When an AI calls structured functions—e.g., “read file,” “write file,” “run tests”—instead of only producing text.

Multi-file edit

A coordinated set of changes across multiple files. Good assistants explain the plan and provide reviewable diffs.

RAG (Retrieval-Augmented Generation)

Supplying relevant documents or code snippets to the model at answer time so responses are grounded in the right context.

Context window

The maximum amount of text (tokens) the model can consider at once—larger windows can read more files but still benefit from focused prompts.

Embedding

A numeric representation of text or code used for semantic search (e.g., to find relevant files for RAG).

Prompt

Your instruction to the model. Clear prompts specify files, goals, constraints, and success checks.

System prompt

Hidden or fixed instructions that shape the assistant’s behavior (tone, safety, tools). You usually can’t see it in IDEs.

Temperature

Controls randomness. Lower values are more deterministic; higher values produce more varied text but can drift.

Hallucination

When a model outputs something that looks plausible but is false (e.g., inventing APIs or files that don’t exist).

Refactor

Change the structure of code without changing behavior—often across multiple files—with tests to confirm safety.

Test scaffolding

Minimal tests an assistant creates to verify a change. Start simple and extend by hand if needed.

Evals (evaluation, benchmarks (lightweight))

Small, repeatable checks (manual or automated) used to compare assistants—e.g., “add a route,” “rename a util,” “write a unit test.”

Latency budget

The time you’re willing to wait for a step or answer. Keeping tasks small helps stay under budget.

Token

A chunk of text the model processes (roughly ~4 characters in English). Context limits and costs are measured in tokens.

Chunking

Splitting large files/docs into smaller pieces for retrieval or processing. Good chunking improves relevance.

Grounding

Tying answers to verifiable sources—your repo, docs, or data—so outputs cite where things came from.

Guardrails

Rules or checks that constrain what a model can do (e.g., lint/test gates, file allowlists).