AI engineering glossary · Evals guardrails AI security
What is sandboxing?
Sandboxing (also called code sandbox): Running code or tools in an isolated environment with strict limits on files, network and resources, so that harmful behaviour cannot spread to the host system. It is standard practice when an AI agent executes generated code.
Sandboxing: an example
An agent's Python code runs inside a container with no internet and a read-only file system, so a malicious script cannot steal data.
Related terms
More Evals guardrails AI security terms
- Schema validation
- Self-preference bias
- Sensitive information disclosure
- Sleeper agents
- Spotlighting
- STRIDE threat model
- Structured output validation
- SWE-bench
Where you learn it
Sandboxing is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.