What is AI? Artificial intelligence in coding tools

By

Artificial intelligence covers software that performs tasks associated with human intelligence. See how models and agents fit into everyday coding work.

AI (artificial intelligence) is the field of building software that performs tasks associated with human intelligence, such as recognizing patterns, understanding language, and solving problems.

AI fundamentals introduces the vocabulary through local runs. For the practical choices between coding products, start with the AI coding landscape.

How AI fits coding

AI is the broad term. A large language model generates text and code. A coding agent adds tools around a model so it can read a project, change files, and check results.

From an AI model to coding workA coding request reaches a language model, which can answer directly or request tools through an agent.Coding requestLanguage modelText answerAgent runs toolsFiles and commandresults

In coding tools

Claude Code combines a model with tools that read files, edit code, and run commands. Cursor Agent can also edit code and run terminal commands.

For Codex, OpenAI’s agents guide explains the distinction between the model and the tools around it. Grok Build is a coding agent with an interactive terminal and headless operation.

Details checked against each vendor’s documentation in November 2026.

A concrete example

Ask a coding assistant:

Explain what this JavaScript expression returns:
['apple', 'pear'].filter(word => word.length > 4)

The result is ['apple']. Generating an explanation uses the model. Running the expression through a JavaScript tool adds an execution result you can check.

When to use AI for coding

Use it to explain unfamiliar code, draft a focused change, or write a test with a clear expected outcome. Give it the relevant files and decide how you will check the result before asking for the change.

Pitfalls

The word AI tells you little about a product’s permissions. An assistant that answers questions and an agent that can run shell commands need different review. Read about coding agents before granting access to a repository.

A fluent answer can still contain a hallucination. Check factual claims and run the code you intend to use.

Language Model Builder lets you explore training a small model. It gives the broad term AI a concrete example you can inspect.

  • 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.
  • 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.
  • 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.

All AI glossary entries →

Want me to talk about your product? You can sponsor this site.