How to beginner · 3 min read

AgentOps dashboard explained

Q: AgentOps dashboard explained

The AgentOps dashboard provides real-time observability and monitoring for AI agents by automatically tracking all LLM calls after agentops.init(). It offers session management, logs, and performance metrics to help developers debug and optimize AI workflows.

Quick answer

The AgentOps dashboard provides real-time observability and monitoring for AI agents by automatically tracking all LLM calls after agentops.init(). It offers session management, logs, and performance metrics to help developers debug and optimize AI workflows.

PREREQUISITES

Python 3.8+
AgentOps API key
pip install agentops

Setup

Install the agentops Python package and set your API key as an environment variable. Initialize agentops in your Python script to enable automatic tracking of AI agent calls.

bash

pip install agentops

# In your shell
export AGENTOPS_API_KEY="your_agentops_api_key"

output

Collecting agentops
  Downloading agentops-1.0.0-py3-none-any.whl (10 kB)
Installing collected packages: agentops
Successfully installed agentops-1.0.0

Step by step

Use agentops.init() to start tracking. Wrap your AI agent calls, then view the dashboard online to monitor sessions, logs, and metrics.

python

import os
import agentops
from openai import OpenAI

# Initialize AgentOps with your API key
agentops.init(api_key=os.environ["AGENTOPS_API_KEY"])

client = OpenAI(api_key=os.environ["OPENAI_API_KEY"])

# Start a session (optional)
session = agentops.start_session(tags=["example-agent"])

# Make a chat completion call
response = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[{"role": "user", "content": "Explain AgentOps dashboard."}]
)
print("Response:", response.choices[0].message.content)

# End the session
agentops.end_session("Success")

output

Response: The AgentOps dashboard provides real-time monitoring and detailed logs of your AI agent's interactions, helping you optimize and debug your workflows.

Common variations

You can use agentops with asynchronous code, other LLM providers, or integrate it with frameworks that support OpenAI-compatible clients. Automatic tracking works after agentops.init() without code changes.

python

import asyncio
import os
import agentops
from openai import OpenAI

agentops.init(api_key=os.environ["AGENTOPS_API_KEY"])
client = OpenAI(api_key=os.environ["OPENAI_API_KEY"])

async def async_call():
    response = await client.chat.completions.create(
        model="gpt-4o-mini",
        messages=[{"role": "user", "content": "Async AgentOps demo."}]
    )
    print("Async response:", response.choices[0].message.content)

asyncio.run(async_call())

output

Async response: This demonstrates AgentOps tracking with asynchronous OpenAI calls.

Troubleshooting

If you see no data in the dashboard, ensure agentops.init() is called before any AI client calls.
Verify your AGENTOPS_API_KEY environment variable is set correctly.
Check network connectivity to agentops servers.

✅

Key Takeaways

Call agentops.init() early to enable automatic AI call tracking.
Use agentops.start_session() and agentops.end_session() to group related calls.
The dashboard provides logs, metrics, and session views for debugging AI agents.
AgentOps supports synchronous and asynchronous OpenAI-compatible clients.
Ensure environment variables for API keys are correctly set to avoid tracking failures.

Verified 2026-04 · gpt-4o-mini

Verify ↗