Claude Code
Anthropic's agentic coding tool, which reads a codebase, edits files and runs commands from the terminal or an IDE.
In more detail
Its sandboxed Bash tool restricts writes to the project and network access to allowed domains, enforced by the operating system. Like any coding agent, it should run without production credentials, and its changes still go through review and CI.
Related terms
- AI coding assistant — A model-driven tool that writes, edits and runs code in your project, from autocomplete to agents that make whole changes.
- Claude Agent SDK — Anthropic's framework for building agents on the same loop, tools and context management that power Claude Code.
- sandbox — A locked-down environment in which a program runs with very few permissions, so that damage from a bug or attack stays contained.
Taught in
- Designing Tools A Model Can Use — AI Engineering: LLM Apps, RAG & Agents
References
- Claude Code docs: Configure the sandboxed Bash tool (filesystem and network isolation)
- Claude Agent SDK: How the agent loop works