CrewAI Quick Start: Build Your First Research Crew in 10 Minutes

The goal of this post is simple: if you follow along, you will generate your first AI research report.
We take the shortest path and skip fancy tricks.

Step 1: Create a project

crewai create crew latest-ai-notes
cd latest-ai-notes

This creates the base structure, including:

• src/latest_ai_notes/config/agents.yaml
• src/latest_ai_notes/config/tasks.yaml
• src/latest_ai_notes/crew.py
• src/latest_ai_notes/main.py

Step 2: Install dependencies

crewai install

This command reads project settings, creates a virtual environment, and installs packages automatically.
You do not need to manually chain a long pip install list.

Step 3: Configure agents

Edit agents.yaml:

researcher:
  role: >
    {topic} Researcher
  goal: >
    Find useful and current information about {topic}
  backstory: >
    You are good at collecting reliable information and summarizing key points.
 
reporter:
  role: >
    {topic} Reporter
  goal: >
    Convert research notes into a readable markdown report
  backstory: >
    You explain technical topics with simple language and clear structure.

Step 4: Configure tasks

Edit tasks.yaml:

research_task:
  description: >
    Research {topic}. Focus on trends, tools, and practical examples in 2026.
  expected_output: >
    10 bullet points with short explanations.
  agent: researcher
 
report_task:
  description: >
    Expand the research notes into a complete markdown article for beginners.
  expected_output: >
    A beginner-friendly markdown report with sections and conclusion.
  agent: reporter
  context:
    - research_task
  output_file: output/report.md

💡 context is important: it tells the second task to consume results from the first task.

Step 5: Run the crew

crewai run

If successful, you will see output in output/report.md.
A delay on the first run is normal. Model calls are like a cat waking up: it takes a moment before it responds to you.

Common issues

Next step

You have completed your first workflow.
Next, we cover the most critical splitting skill:
👉 Agents and Tasks