From 600fff7acc792c96b3a01c50e1f1c6bc6277dbc3 Mon Sep 17 00:00:00 2001 From: kirtiupacharya Date: Mon, 23 Jun 2025 14:52:36 +0530 Subject: [PATCH] docs: correct step 1 of Output guardrails to use agent's output (#890) --- docs/guardrails.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/guardrails.md b/docs/guardrails.md index 2f0be0f2a..339f4018c 100644 --- a/docs/guardrails.md +++ b/docs/guardrails.md @@ -11,7 +11,7 @@ There are two kinds of guardrails: Input guardrails run in 3 steps: -1. First, the guardrail receives the same input passed to the agent. +1. First, the guardrail receives the same output produced by the agent. 2. Next, the guardrail function runs to produce a [`GuardrailFunctionOutput`][agents.guardrail.GuardrailFunctionOutput], which is then wrapped in an [`InputGuardrailResult`][agents.guardrail.InputGuardrailResult] 3. Finally, we check if [`.tripwire_triggered`][agents.guardrail.GuardrailFunctionOutput.tripwire_triggered] is true. If true, an [`InputGuardrailTripwireTriggered`][agents.exceptions.InputGuardrailTripwireTriggered] exception is raised, so you can appropriately respond to the user or handle the exception.