Tag

#Safety

Every article tagged Safety, in one place.

2 articles
2 min of reading
10 Jul, 2026 last updated

Showing 2 articles

Tool Use & Agent Loops 1 min read

Human-in-the-Loop: Approving Agent Actions Before They Run

Reading data is low-risk. Sending emails, moving money or deleting records is not. A human-in-the-loop step pauses the agent and asks for approval before risky tools run. Classify your tools Read-only (search, get_*): run automatically. Reversible writes (draf...

10 Jul, 2026 Author 1.17K 24

Read article

Tool Use & Agent Loops 1 min read

Guardrails for AI Agents: Permissions, Sandboxing and Budgets

An agent can only do what its tools allow. Good guardrails assume the model will sometimes make mistakes or be manipulated, and limit the damage when it does. 1. Least privilege Give each agent only the tools its job needs. Scope credentials: a read-only datab...

22 Jun, 2026 Author 156 43

Read article