# Bounded Tool-Using Agents

> The ability to run agents that use external tools within defined, safe limits.

Record: `lexicon:bounded-tool-using-agents`
Kind: capability
Layer: [Correctness Core](https://banes-lab.com/records/layer/correctness-core.md)
Canonical: https://banes-lab.com/ontology/lexicon#lexicon-bounded-tool-using-agents

Listed in [Lexicon terms](https://banes-lab.com/api/records/lexicon.md), after [Audit and Debugging](https://banes-lab.com/records/lexicon/audit-and-debugging.md) and before [Contextual Generation](https://banes-lab.com/records/lexicon/contextual-generation.md).

## Category

- [Model Architecture](https://banes-lab.com/records/lexicon-category/model-architecture.md)

## Enabled by

- [Agentic Architecture](https://banes-lab.com/records/architecture/agentic-architecture.md)

## Linked from

- [Model Architecture](https://banes-lab.com/ontology/principles/architecture-category-model-architecture.md)