Glossary › Agents

Sandboxing

Running agent code/actions in an isolated environment with restricted permissions. Prevents unintended side effects. Methods: Docker containers, WASM, firecracker microVMs, E2B sandboxes.

Where this is taught

• Sandboxing & Safety for Browser Agents — Phase 6: Computer Use & Browser Agents
• Human Approval, Tool Permissions, and Sandboxing — Phase 7: AI Agents & Tool-Using Systems
• Building Custom Guardrail Pipelines — Phase 5: Guardrails & Defensive Controls
• MCP Security & Computer Use / Browser Agent Safety — Phase 4: RAG & Agent Security
• LLM02 & LLM04: Insecure Output Handling & Model Denial of Service — Phase 1: OWASP Top 10 for LLM Applications

Related terms

Agent

More in Agents

Agent · ReAct · Tool Use · MCP (Model Context Protocol) · Multi-Agent System · Orchestration

Learn this by building

DeVenture Academy teaches AI engineering through projects, with hands-on labs you run on your own machine using real tools.

Create a free account — the opening phases of 29 of 35 courses are free, no credit card. Or see Pro pricing.

All courses · Pricing · About · FAQ · Glossary