AgentOps automatically tracks LLM interactions in your application. For more detailed tracking, especially in multi-agent systems, you can use additional features to associate operations with specific agents.

​
Basic Agent Tracking

For simple applications, AgentOps will automatically track your LLM calls without additional configuration:

import agentops
from openai import OpenAI

# Initialize AgentOps
agentops.init("your-api-key")

# Create a simple agent function
def research_agent(query):
    client = OpenAI()
    response = client.chat.completions.create(
        model="gpt-4o",
        messages=[{"role": "user", "content": f"Research about: {query}"}]
    )
    return response.choices[0].message.content

# Use your agent - all LLM calls will be tracked automatically
result = research_agent("quantum computing")

​
Advanced: Using the Agent Decorator

For more structured tracking in complex applications, you can use the @agent decorator to explicitly identify different agents in your system:

import agentops
from agentops.sdk.decorators import agent, operation
from openai import OpenAI

# Initialize AgentOps
agentops.init("your-api-key")

# Create a decorated agent class
@agent(name='ResearchAgent')
class MyAgent:
    def __init__(self):
        self.client = OpenAI()
        
    @operation
    def search(self, query):
        response = self.client.chat.completions.create(
            model="gpt-4o",
            messages=[{"role": "user", "content": f"Research about: {query}"}]
        )
        return response.choices[0].message.content

# Create and use the agent within a function
def research_workflow(topic):
    agent = MyAgent()
    result = agent.search(topic)
    return result

# Execute the function to properly register the agent span
result = research_workflow("quantum computing")

If you don’t specify a name, the agent will use the class name by default:

@agent
class ResearchAgent:
    # This agent will have the name "ResearchAgent"
    pass

​
Dashboard Visualization

All operations are automatically associated with the agent that originated them. Agents are given a name which is what you will see in the dashboard.

Operations are labeled with the name of the Agent that originated them

​
Best Practices

  1. Start Simple: For most applications, just using agentops.init() is sufficient.

  2. Use Decorators When Needed: Add the @agent decorator when you need to clearly distinguish between multiple agents in your system.

  3. Meaningful Names: Choose descriptive names for your agents to make them easier to identify in the dashboard.