Skip to content
CrewAI Documentation

Build Your First Crew

Build a Research Crew

Section titled “Build a Research Crew”

In this guide, you will create a two-agent research crew that gathers information about a topic and writes a markdown report. New crew projects are JSON-first: agents are defined in agents/*.jsonc, tasks and crew settings are defined in crew.jsonc, and crewai run loads the JSON definition directly.

Prerequisites

Section titled “Prerequisites”

Before starting, make sure you have:

  1. Installed CrewAI following the installation guide
  2. Set up your LLM API key following the LLM setup guide
  3. A Serper.dev API key if you want the researcher to use web search

Step 1: Create a New Crew

Section titled “Step 1: Create a New Crew”
Terminal window
crewai create crew research_crew
cd research_crew

The CLI creates a JSON-first project:

research_crew/
├── .gitignore
├── .env
├── agents/
│   └── researcher.jsonc
├── crew.jsonc
├── knowledge/
├── pyproject.toml
├── README.md
├── skills/
└── tools/

Step 2: Define Your Agents

Section titled “Step 2: Define Your Agents”

Replace the generated agents/researcher.jsonc file and add agents/analyst.jsonc. The file names are the names you reference from crew.jsonc.

{
  "role": "Senior Research Specialist for {topic}",
  "goal": "Find comprehensive and accurate information about {topic}, with a focus on recent developments and key insights.",
  "backstory": "You are an experienced research specialist who organizes complex information into clear, useful notes.",
  // Replace with your model, for example "openai/gpt-4o".
  "llm": "provider/model-id",
  "tools": ["SerperDevTool"],
  "settings": {
    "verbose": true,
    "allow_delegation": false
  }
}
{
  "role": "Report Analyst for {topic}",
  "goal": "Turn research findings into a clear, well-structured report.",
  "backstory": "You are a careful analyst with strong technical writing skills and a talent for extracting useful insights.",
  // Replace with your model, for example "openai/gpt-4o".
  "llm": "provider/model-id",
  "settings": {
    "verbose": true,
    "allow_delegation": false
  }
}

Replace provider/model-id with the model you use, for example openai/gpt-4o, anthropic/claude-sonnet-4-6, or gemini/gemini-2.0-flash-001.

Step 3: Define Tasks and Crew Settings

Section titled “Step 3: Define Tasks and Crew Settings”

Replace crew.jsonc with:

{
  "name": "Research Crew",
  "agents": ["researcher", "analyst"],
  "tasks": [
    {
      "name": "research_task",
      "description": "Conduct thorough research on {topic}. Focus on key concepts, recent developments, major challenges, notable applications, and future outlook.",
      "expected_output": "A comprehensive research document with organized sections, specific facts, and useful examples about {topic}.",
      "agent": "researcher"
    },
    {
      "name": "analysis_task",
      "description": "Analyze the research findings and create a polished report on {topic}. Include an executive summary, key insights, trend analysis, and recommendations.",
      "expected_output": "A professional markdown report with clear headings, a concise summary, main findings, and recommendations.",
      "agent": "analyst",
      "context": ["research_task"],
      "output_file": "output/report.md",
      "markdown": true
    }
  ],
  "process": "sequential",
  "verbose": true,
  "memory": true,
  "inputs": {
    "topic": "Artificial Intelligence in Healthcare"
  }
}

context points to prior task names, so the analyst receives the research task output. The inputs object provides default values for {topic}. If you remove a default, crewai run prompts for it.

Step 4: Set Environment Variables

Section titled “Step 4: Set Environment Variables”

Open .env and add the keys your model and tools need:

Terminal window
SERPER_API_KEY=your_serper_api_key
# Add your model provider API key here too.

See the LLM setup guide for provider-specific keys.

Step 5: Install and Run

Section titled “Step 5: Install and Run”
Terminal window
crewai install
crewai run

crewai run detects crew.jsonc, loads the agents from agents/, prompts for missing placeholders, and runs the crew. When the run finishes, open output/report.md.

How It Works

Section titled “How It Works”
  1. crew.jsonc defines the crew, task order, process, memory, and runtime inputs.
  2. agents/researcher.jsonc and agents/analyst.jsonc define the agents.
  3. The researcher runs first.
  4. The analyst runs second with context: ["research_task"].
  5. The final task writes output/report.md.

Extending Your Crew

Section titled “Extending Your Crew”

You can add:

  • More agents by creating new agents/<name>.jsonc files and listing them in crew.jsonc
  • More tasks by appending objects to the tasks array
  • Built-in tools by adding tool class names such as "FileReadTool" or "SerperDevTool"
  • Custom tools with "custom:<name>", which loads tools/<name>.py
  • Hierarchical execution with "process": "hierarchical" and a manager_llm or manager_agent