Skip to main content

Agent Guardrails and Triage Logic

In this lesson, you'll learn how to use InputGuardrail and agent handoffs to build a triaging agent that routes queries to specialized assistants, with logic to block off-topic input.

Prerequisites​

Install the latest OpenAI SDK with agent support:

pip install --upgrade openai

The Code​

from agents import Agent, InputGuardrail, GuardrailFunctionOutput, Runner
from pydantic import BaseModel
import asyncio

class HomeworkOutput(BaseModel):
    is_homework: bool
    reasoning: str

guardrail_agent = Agent(
    name="Guardrail check",
    instructions="Check if the user is asking about homework.",
    output_type=HomeworkOutput,
)

math_tutor_agent = Agent(
    name="Math Tutor",
    handoff_description="Specialist agent for math questions",
    instructions="You provide help with math problems. Explain your reasoning at each step and include examples",
)

history_tutor_agent = Agent(
    name="History Tutor",
    handoff_description="Specialist agent for historical questions",
    instructions="You provide assistance with historical queries. Explain important events and context clearly.",
)

async def homework_guardrail(ctx, agent, input_data):
    result = await Runner.run(guardrail_agent, input_data, context=ctx.context)
    final_output = result.final_output_as(HomeworkOutput)
    return GuardrailFunctionOutput(
        output_info=final_output,
        tripwire_triggered=not final_output.is_homework,
    )

triage_agent = Agent(
    name="Triage Agent",
    instructions="You determine which agent to use based on the user's homework question",
    handoffs=[history_tutor_agent, math_tutor_agent],
    input_guardrails=[
        InputGuardrail(guardrail_function=homework_guardrail),
    ],
)

async def main():
    result = await Runner.run(triage_agent, "who was the first president of the united states?")
    print(result.final_output)

    result = await Runner.run(triage_agent, "what is life")
    print(result.final_output)

if __name__ == "__main__":
    asyncio.run(main())

Explanation​

  • guardrail_agent: Classifies input as homework or not.
  • InputGuardrail: Prevents irrelevant input from triggering a handoff.
  • handoffs: Automatically routes to the appropriate subject tutor.
  • final_output_as(...): Parses the guardrail’s structured output.

Use Case​

Perfect for:

  • Education platforms with specialized tutors
  • Preventing off-topic input from triggering resource-intensive logic
  • Rule-based AI delegation in multi-agent systems