The sweet spot for me is 2 agents on different projects. Surprisingly the context switch is easy. It's harder when doing 2 tasks on the same project.

▲

merlincorey 2 days ago | parent | next [-]

> on different projects

This seems like an important caveat the author of the article failed to mention when they described this:

> you can have several agents running simultaneously - one building a user interface, another writing API endpoints, and a third creating database schemas.

If these are all in the same project then there has to be some required ordering to it or you get a frontend written to make use of a backend that doesn't have the endpoints used, and you get a backend that makes use of a different database schema than the separately generated database schema.

	▲	kasey_junk 2 days ago \| parent \| next [-]
		This is just project management. Teams of software devs have been doing this for decades. And it’s easier with agents because there is no harm in letting one sit idle.
	▲	furyofantares 2 days ago \| parent \| prev [-]
		On the same project you can use worktrees or otherwise separate clones of the repo - that part is not that bad. My comment was just about my own context switch.

▲

rcarr 2 days ago | parent | prev [-]

A technique I have found that works well is to have it working on one feature and then to have another session planning the next. Whilst it's busy generating some code, I open up another instance, tell it the next task and instruct it to create a gherkin feature file with an implementation plan. I then go back and forth between reviewing the code for the current feature and the plan for the next one.