Controls & Audit

Review agent safety-rule evaluations.

Keep agents safe and accountable. Review guardrail results.

Protect agent activity

Review screened inputs and outputs.

At a glance

Area	Use it to	Start here
Guardrails	Review safety-rule evaluations	Guardrails

Use this area to answer one question: what did guardrails catch?

Guardrails

Guardrails screens agent executions against safety rules and records the result. Open Controls & Audit → Guardrails to see recent evaluations.

Guardrails, listing recent safety-rule evaluations.

This screen currently displays sample data — its title reads Guardrails (Mock). Treat the figures and rows as illustrative until it's connected to live guardrail evaluations.

You can narrow by agent and search by agent or guardrail. The page summarizes recent activity: Evaluations (24h), how many were Blocked and their share of traffic, the Pass Rate, and the number of Active Rules. Each row is one guardrail evaluation:

Field	What it shows
Timestamp	When the evaluation ran.
Agent	The agent whose input or output was screened.
Guardrail	The rule applied — for example, PII Filter, Toxicity, Topic Policy, Prompt Injection, Hallucination Guard, or Jailbreak Detection.
Type	Whether the guardrail ran on the Input (before the model) or the Output (after).
Result	Passed or Blocked.

Related

Control CenterEvalsObserveAdmin

---

Maintained by Abhishek Paul AI-assisted, human-approved