ChatGPT

Sandbox

A boundary that limits which files and network resources an AI agent can reach, so it can work without free rein over your computer.

Inside the fence, or at the gate Left: inside the sandbox, the agent works freely in your folder. Right: at the edge, going to the internet or other files needs your approval. Inside the sandbox Your project folder. Works freely. At the border Internet, other files. Asks you first. vs Start on Ask for approval.

A sandbox is the fence an agent works inside. For Codex, it usually means the workspace folder you opened: it can read and change files there, and needs permission to go beyond it.

On top of the sandbox sits the permission mode. Ask for approval asks you before Codex edits files outside the workspace or uses the internet, and is where OpenAI recommends starting. Approve for me keeps the same fence but sends border crossings to an automatic review. Full access removes the fence. Changing who approves never widens the sandbox itself.

Often confused with: A test environment. A test environment is a copy of a system to try things safely; a sandbox is the limit on what the agent can touch, wherever it runs.

See it in a lesson: Codex

Further reading

← All terms

Rollo AI AcademyWant your whole team speaking this language?Knowing the words is a start. Rollo Academy gets teams genuinely working with AI, through hands-on, in-company training built around your own work.Discover Rollo Academy →