See what your agents actually do once they're in production

We've added an observability integration with The Context Company, so you can trace Agno agent runs and understand how they behave in the wild. Setup is one line. Call instrument_agno() before you import Agno, and your runs start streaming over OpenTelemetry, capturing model calls, tool arguments and results, prompts, token usage, and latency.

from contextcompany.agno import instrument_agno

instrument_agno()

from agno.agent import Agent
from agno.models.openai import OpenAIChat
from agno.tools.yfinance import YFinanceTools

agent = Agent(model=OpenAIChat(id="gpt-5.2"), tools=[YFinanceTools()])
agent.print_response("What is the current price of NVIDIA?")

‍

Plain tracing shows you one run at a time. What The Context Company adds is analysis across all of them, surfacing recurring patterns and account-level insight and then linking back to the specific runs behind each one. So instead of scrolling traces hoping to spot a problem, you find out where your agents are consistently going wrong and can go straight to the evidence.

View Agno’s The Context Company docs to learn more.