Run it and read the agents' reasoning

🎯Goal. Execute your crew and watch the agents think, hand off to each other, and produce a finished report.

1. 1From the project folder, run crewai run. The researcher agent starts first, reasoning out loud in the terminal about how to approach its task.
2. 2Watch the handoff: when the researcher finishes, its output is passed to the writer agent, which uses it to produce the final piece — this collaboration is the whole point of a crew.
3. 3Read the final output printed at the end (CrewAI also writes it to a file). Tweak a goal in agents.yaml, run again, and compare — small wording changes visibly steer the result.

✓You'll see. Two agents printing their step-by-step reasoning, passing work between them, and producing a short written report — from a single command.

💳Cost. This run spends real LLM tokens billed by your provider (a small report is typically a few cents). The CrewAI framework itself stays free.

💡Takeaway. Running a crew makes the abstraction concrete: you see agents reason, collaborate and deliver, not just a black-box answer.