the first multi-agent system anyone builds is a toy, and the toy should not cost an afternoon of setup.
you define the agents, the tasks and the crew, wire them together, and run them with the output streaming back as it happens. all of it can be done from a script. what the app removes is the afternoon of boilerplate between understanding what a multi-agent system is and having one running.
a crew is a graph of agents with dependencies, and most people's first instinct is to build it as a list. the ui mostly exists to make the graph visible before you run it.