Agents and tool use · MLD-0040
Agent containment
Technical and procedural restrictions limiting an agent's actions, resources, and escape routes.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Constrain network, file, and tool access during testing.
Original caveat
Containment strength must be tested against the actual threat model.
Context and aliases
Level: Intermediate. Stages: Inference · Deployment · Evaluation.
Tags: SLM · LLM · RL · Agents.
Aliases: None recorded.
Related concepts
Concepts linking here
Original references
- Anthropic: Building effective agents ↗ · Reference link
- Model Context Protocol Python SDK: first steps ↗ · Consulted
- ReAct: Synergizing Reasoning and Acting in Language Models ↗ · Reference link
- Original reference URL ↗