docs/en/observability/braintrust.mdx
This guide demonstrates how to integrate Braintrust with CrewAI using OpenTelemetry for comprehensive tracing and evaluation. By the end of this guide, you will be able to trace your CrewAI agents, monitor their performance, and evaluate their outputs using Braintrust's powerful observability platform.
What is Braintrust? Braintrust is an AI evaluation and observability platform that provides comprehensive tracing, evaluation, and monitoring for AI applications with built-in experiment tracking and performance analytics.
We'll walk through a simple example of using CrewAI and integrating it with Braintrust via OpenTelemetry for comprehensive observability and evaluation.
uv add braintrust[otel] crewai crewai-tools opentelemetry-instrumentation-openai opentelemetry-instrumentation-crewai python-dotenv
Setup Braintrust API keys and configure OpenTelemetry to send traces to Braintrust. You'll need a Braintrust API key and your OpenAI API key.
import os
from getpass import getpass
# Get your Braintrust credentials
BRAINTRUST_API_KEY = getpass("🔑 Enter your Braintrust API Key: ")
# Get API keys for services
OPENAI_API_KEY = getpass("🔑 Enter your OpenAI API key: ")
# Set environment variables
os.environ["BRAINTRUST_API_KEY"] = BRAINTRUST_API_KEY
os.environ["BRAINTRUST_PARENT"] = "project_name:crewai-demo"
os.environ["OPENAI_API_KEY"] = OPENAI_API_KEY
Initialize the Braintrust OpenTelemetry instrumentation to start capturing traces and send them to Braintrust.
import os
from typing import Any, Dict
from braintrust.otel import BraintrustSpanProcessor
from crewai import Agent, Crew, Task
from crewai.llm import LLM
from opentelemetry import trace
from opentelemetry.instrumentation.crewai import CrewAIInstrumentor
from opentelemetry.instrumentation.openai import OpenAIInstrumentor
from opentelemetry.sdk.trace import TracerProvider
def setup_tracing() -> None:
"""Setup OpenTelemetry tracing with Braintrust."""
current_provider = trace.get_tracer_provider()
if isinstance(current_provider, TracerProvider):
provider = current_provider
else:
provider = TracerProvider()
trace.set_tracer_provider(provider)
provider.add_span_processor(BraintrustSpanProcessor())
CrewAIInstrumentor().instrument(tracer_provider=provider)
OpenAIInstrumentor().instrument(tracer_provider=provider)
setup_tracing()
We'll create a CrewAI application where two agents collaborate to research and write a blog post about AI advancements, with comprehensive tracing enabled.
from crewai import Agent, Crew, Process, Task
from crewai_tools import SerperDevTool
def create_crew() -> Crew:
"""Create a crew with multiple agents for comprehensive tracing."""
llm = LLM(model="gpt-4o-mini")
search_tool = SerperDevTool()
# Define agents with specific roles
researcher = Agent(
role="Senior Research Analyst",
goal="Uncover cutting-edge developments in AI and data science",
backstory="""You work at a leading tech think tank.
Your expertise lies in identifying emerging trends.
You have a knack for dissecting complex data and presenting actionable insights.""",
verbose=True,
allow_delegation=False,
llm=llm,
tools=[search_tool],
)
writer = Agent(
role="Tech Content Strategist",
goal="Craft compelling content on tech advancements",
backstory="""You are a renowned Content Strategist, known for your insightful and engaging articles.
You transform complex concepts into compelling narratives.""",
verbose=True,
allow_delegation=True,
llm=llm,
)
# Create tasks for your agents
research_task = Task(
description="""Conduct a comprehensive analysis of the latest advancements in {topic}.
Identify key trends, breakthrough technologies, and potential industry impacts.""",
expected_output="Full analysis report in bullet points",
agent=researcher,
)
writing_task = Task(
description="""Using the insights provided, develop an engaging blog
post that highlights the most significant {topic} advancements.
Your post should be informative yet accessible, catering to a tech-savvy audience.
Make it sound cool, avoid complex words so it doesn't sound like AI.""",
expected_output="Full blog post of at least 4 paragraphs",
agent=writer,
context=[research_task],
)
# Instantiate your crew with a sequential process
crew = Crew(
agents=[researcher, writer],
tasks=[research_task, writing_task],
verbose=True,
process=Process.sequential
)
return crew
def run_crew():
"""Run the crew and return results."""
crew = create_crew()
result = crew.kickoff(inputs={"topic": "AI developments"})
return result
# Run your crew
if __name__ == "__main__":
# Instrumentation is already initialized above in this module
result = run_crew()
print(result)
After running your crew, you can view comprehensive traces in Braintrust through different perspectives:
<Tabs> <Tab title="Trace"> <Frame></Frame>
</Frame>
</Frame>
You can also run evaluations using Braintrust's Eval SDK. This is useful for comparing versions or scoring outputs offline. Below is a Python example using the Eval class with the crew we created above:
# eval_crew.py
from braintrust import Eval
from autoevals import Levenshtein
def evaluate_crew_task(input_data):
"""Task function that wraps our crew for evaluation."""
crew = create_crew()
result = crew.kickoff(inputs={"topic": input_data["topic"]})
return str(result)
Eval(
"AI Research Crew", # Project name
{
"data": lambda: [
{"topic": "artificial intelligence trends 2024"},
{"topic": "machine learning breakthroughs"},
{"topic": "AI ethics and governance"},
],
"task": evaluate_crew_task,
"scores": [Levenshtein],
},
)
Setup your API key and run:
export BRAINTRUST_API_KEY="YOUR_API_KEY"
braintrust eval eval_crew.py
See the Braintrust Eval SDK guide for more details.