Skip to content

openai-agent-sdk-guardrails.mdx

Latest commit

 

History

History
63 lines (44 loc) · 3.68 KB

openai-agent-sdk-guardrails.mdx

File metadata and controls

63 lines (44 loc) · 3.68 KB
title OpenAI Agent SDK guardrails examples
sidebarTitle OpenAI Agent SDK guardrails
description This example project demonstrates how to implement different types of guardrails using the OpenAI Agent SDK with Trigger.dev for AI safety and control.

import RealtimeLearnMore from "/snippets/realtime-learn-more.mdx";

The OpenAI Agent SDK is a Python library.

Overview

This demo is a practical guide that demonstrates:

  • Three types of AI guardrails: Input validation, output checking, and real-time streaming monitoring
  • Integration of the OpenAI Agent SDK with Trigger.dev for production AI workflows
  • Educational examples of implementing guardrails for AI safety and control mechanisms
  • Real-world scenarios like math tutoring agents with content validation and complexity monitoring

Guardrails are safety mechanisms that run alongside AI agents to validate input, check output, monitor streaming content in real-time, and prevent unwanted or harmful behavior.

GitHub repo

<Card title="View the OpenAI Agent SDK Guardrails repo" icon="GitHub" href="https://github.com/triggerdotdev/examples/tree/main/openai-agent-sdk-guardrails-examples"

Click here to view the full code for this project in our examples repository on GitHub. You can fork it and use it as a starting point for your own project.

Video

<video controls className="w-full aspect-video" src="https://github.com/user-attachments/assets/9b1e55c7-467d-4aca-8b4a-a018014c0827"

Relevant code

Trigger.dev Tasks

  • inputGuardrails.ts - Passes user prompts to Python script and handles InputGuardrailTripwireTriggered exceptions
  • outputGuardrails.ts - Runs agent generation and catches OutputGuardrailTripwireTriggered exceptions with detailed error info
  • streamingGuardrails.ts - Executes streaming Python script and parses JSON output containing guardrail metrics

Python Implementations

  • input-guardrails.py - Agent with @input_guardrail decorator that validates user input before processing (example: math tutor that only responds to math questions)
  • output-guardrails.py - Agent with @output_guardrail decorator that validates generated responses using a separate guardrail agent
  • streaming-guardrails.py - Processes ResponseTextDeltaEvent streams with async guardrail checks at configurable intervals (example: stops streaming if language is too complex for a 10-year-old)

Configuration

Learn more