Most work does not need many agents. If it fits in one session, or the parts share files, or you can't check the output, use one. If you could do it in the time it takes to write the brief, use none. Add more only once you have measured a gain.
Every idea in this chapter adds something to run, pay for and understand. Many agents can feel productive because a lot is happening. The test is whether more correct work reached users, per hour of your attention. Very often it did not.
Say it to your agent
“Before you plan anything: would one agent in one session be enough for this? Say yes unless you can name the parts that are truly independent, the files each one touches, and how I would check each result.”