By AI Surface · CrewAI
CrewAI + Connect AI
Orchestrate multi-agent crews that coordinate across business data sources via shared Connect AI tools. One agent per data dimension, all grounded in live data.
from crewai import Agent, Task, Crew, Process
from crewai.tools import tool
@tool("query_data")
def query_data(query: str) -> str:
"""Execute SQL against Connect AI."""
return mcp_client.query_data(query)
researcher = Agent(
role="Account Researcher",
goal="Gather enterprise account data",
tools=[query_data]
)
crew = Crew(
agents=[researcher, analyst, writer],
tasks=[research, analysis, brief],
process=Process.sequential
)
result = crew.kickoff(inputs={"account": "Acme"})
Developer guide
Full step-by-step guide to building a multi-agent research crew with Connect AI MCP.
Sources for CrewAI
Common CrewAI + source patterns. Tap any combination to see the tutorial.
Sample agent
A polished CrewAI reference. Looking for a quick start in a different framework? See the npx scaffold (LangChain, Google ADK, or Vercel AI SDK).
CDataSoftware/connectai-crewai-account-research
View on GitHub
Three-agent crew (Researcher, Analyst, Writer) that generates Markdown account briefs from live enterprise data.
Evaluating Connect AI for your team? Learn more about Connect AI.
Connect AI documentation
View docs
Full API reference, authentication guides, and configuration details.