Quickstart

Watch: Building CrewAI Agents & Flows with Coding Agent Skills

Install our coding agent skills (Claude Code, Codex, …) to quickly get your coding agents up and running with CrewAI.

You can install it with npx skills add crewaiinc/skills

In this guide you will create a Flow that sets a research topic, runs a crew with one agent (a researcher using web search), and ends with a markdown report on disk. Flows are the recommended way to structure production apps: they own state and execution order, while agents do the work inside a crew step.

If you have not installed CrewAI yet, follow the installation guide first.

Prerequisites

• Python environment and the CrewAI CLI (see installation)
• An LLM configured with the right API keys — see LLMs
• A Serper.dev API key (SERPER_API_KEY) for web search in this tutorial

Build your first Flow

1. Create a Flow project

   From your terminal, scaffold a Flow project (the folder name uses underscores, e.g. latest_ai_flow):

   Code

   crewai create flow latest-ai-flow
   cd latest_ai_flow

   This creates a Flow app under src/latest_ai_flow/, including a starter crew under crews/content_crew/ that you will replace with a minimal single-agent research crew in the next steps.

2. Configure one agent in JSONC

   Create src/latest_ai_flow/crews/content_crew/agents/researcher.jsonc (create the agents/ directory if needed). Variables like {topic} are filled from crew.kickoff(inputs=...).

   {
     "role": "{topic} Senior Data Researcher",
     "goal": "Uncover cutting-edge developments in {topic}",
     "backstory": "You're a seasoned researcher who finds relevant information and presents it clearly.",
     "tools": ["SerperDevTool"],
     "settings": {
       "verbose": true
     }
   }

3. Configure the crew in `crew.jsonc`

   Create src/latest_ai_flow/crews/content_crew/crew.jsonc:

   {
     "name": "Research Crew",
     "agents": ["researcher"],
     "tasks": [
       {
         "name": "research_task",
         "description": "Conduct thorough research about {topic}. Use web search to find recent, credible information.",
         "expected_output": "A markdown report with clear sections: key trends, notable tools or companies, and implications. Aim for 800-1200 words. No fenced code blocks around the whole document.",
         "agent": "researcher",
         "output_file": "output/report.md",
         "markdown": true
       }
     ],
     "process": "sequential",
     "verbose": true
   }

4. Load the JSON crew (`content_crew.py`)

   Replace the generated content_crew.py with a small loader that turns crew.jsonc into a Crew.

   src/latest_ai_flow/crews/content_crew/content_crew.py

   from pathlib import Path
   
   from crewai.project import load_crew
   
   
   def kickoff_content_crew(inputs: dict):
     crew, default_inputs = load_crew(Path(__file__).with_name("crew.jsonc"))
     return crew.kickoff(inputs={**default_inputs, **inputs})

5. Define the Flow in `main.py`

   Connect the crew to a Flow: a @start() step sets the topic in state, and a @listen step runs the crew. The task’s output_file still writes output/report.md.

   src/latest_ai_flow/main.py

   from pydantic import BaseModel
   
   from crewai.flow import Flow, listen, start
   
   from latest_ai_flow.crews.content_crew.content_crew import kickoff_content_crew
   
   
   class ResearchFlowState(BaseModel):
     topic: str = ""
     report: str = ""
   
   
   class LatestAiFlow(Flow[ResearchFlowState]):
     @start()
     def prepare_topic(self, crewai_trigger_payload: dict | None = None):
       if crewai_trigger_payload:
         self.state.topic = crewai_trigger_payload.get("topic", "AI Agents")
       else:
         self.state.topic = "AI Agents"
       print(f"Topic: {self.state.topic}")
   
     @listen(prepare_topic)
     def run_research(self):
       result = kickoff_content_crew(inputs={"topic": self.state.topic})
       self.state.report = result.raw
       print("Research crew finished.")
   
     @listen(run_research)
     def summarize(self):
       print("Report path: output/report.md")
   
   
   def kickoff():
     LatestAiFlow().kickoff()
   
   
   def plot():
     LatestAiFlow().plot()
   
   
   if __name__ == "__main__":
     kickoff()

   Tip

   If your package name differs from latest_ai_flow, change the kickoff_content_crew import to match your project’s module path.

6. Set environment variables

   In .env at the project root, set:

   • SERPER_API_KEY — from Serper.dev
   • Your model provider keys as required — see LLM setup
7. Install and run
   Code

   crewai install
   crewai run

   crewai run executes the Flow entrypoint defined in your project (same command as for crews; project type is "flow" in pyproject.toml).

8. Check the output

   You should see logs from the Flow and the crew. Open output/report.md for the generated report (excerpt):

   Code

   # AI Agents: Recent Landscape and Trends
   
   ## Executive summary
   …
   
   ## Key trends
   - **Tool use and orchestration** — …
   - **Enterprise adoption** — …
   
   ## Implications
   …

   Your actual file will be longer and reflect live search results.

How this run fits together

1. Flow — LatestAiFlow runs prepare_topic first, then run_research, then summarize. State (topic, report) lives on the Flow.
2. Crew — kickoff_content_crew loads crew.jsonc and runs one task with one agent: the researcher uses Serper to search the web, then writes the structured report.
3. Artifact — The task’s output_file writes the report under output/report.md.

To go deeper on Flow patterns (routing, persistence, human-in-the-loop), see Build your first Flow and Flows. For crews without a Flow, see Crews. For a single Agent and kickoff() without tasks, see Agents.

You now have an end-to-end Flow with an agent crew and a saved report — a solid base to add more steps, crews, or tools.

Naming consistency

The names in crew.jsonc must match the files and task references you use:

• agents: ["researcher"] loads agents/researcher.jsonc
• tasks[].agent: "researcher" assigns the task to that agent

Deploying

Push your Flow to CrewAI AMP once it runs locally and your project is in a GitHub repository. From the project root:

Code

crewai login

crewai deploy create

crewai deploy status
crewai deploy logs

crewai deploy push

crewai deploy list
crewai deploy remove <deployment_id>

Tip

The first deploy usually takes around 1 minute. Full prerequisites and the web UI flow are in Deploy to AMP.

Deploy guide

Step-by-step AMP deployment (CLI and dashboard).

Join the Community

Discuss ideas, share projects, and connect with other CrewAI developers.