Skip to main content

​
Prerequisites

Install dependencies: 
pip install "quotientai>=0.4.6" "openai-agents>=0.1.0" "openinference-instrumentation-openai-agents==1.1.1"
Set environment variables: 
export OPENAI_API_KEY=your-openai-api-key
export QUOTIENT_API_KEY=your-quotient-api-key

​
Sample Integration

quotient_trace_openai_agents.py
from openinference.instrumentation.openai_agents import OpenAIAgentsInstrumentor

from quotientai import QuotientAI

quotient = QuotientAI()
quotient.tracer.init(
    app_name="openai-agents-search-app",
    environment="dev",
    instruments=[OpenAIAgentsInstrumentor()],
)

import asyncio
from agents import Agent, Runner

@quotient.trace('haiku-agent')
async def main() -> None:
    agent = Agent(
        name="haiku-assistant",
        instructions="You only respond in haikus.",
    )

    result = await Runner.run(agent, "Tell me about recursion in programming.")
    print(result.final_output)

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

​
Notes

  • The instrumentor emits spans for tool calls, actions, and final responses so you can replay the agent’s reasoning.
  • Use asyncio.run (as shown) or integrate directly into your existing event loop.
Next: LangGraph
⌘I