Anthropic Says Delete Your Subagents

Sub agents are great. Sub agents are bad. It is kind of hard to keep up. And Tropic just told companies to get rid of their unnecessary sub agents and fold them into one agent with skills. And this kind of reduction is a trend we've been seeing over the last few weeks and months. We've seen people reducing their

agents.mmd files and also callulling their skills. The fact here is the models are getting better and the complicated harnesses we've been developing around them are not required in every instance at least. You can actually see this with Claude Code itself. They have cut the system prompt by over 80% for their stronger models.

Notice the way I said stronger models and that's because this isn't going to work for every type of model strength. So with this new research and guidance from Antropic and others, should we be turning off our sub agents as well? I'm Rob from Switch Dimension. I'm going to go through what Antropic said, why all

this is happening now, and I'm going to show you how to apply this yourself when it comes to your skills, your Claude MD, and your sub agents. So, this is all coming from Antropics Applied AI team and it came out on the 22nd of October. So, they're saying one agent with a set

of skills was frequently beating both one giant prompt and a team of sub agents on quality and it was often cheaper and faster, too. And who doesn't want fast and cheap? In one case, a customer tested their multi-agent setup against a single loop and the single loop ran about twice as fast. So, how

are we ending up with so many sub aents in the first place? Well, when it comes to software factories and running processes for companies, each team is building out its own set of agents and then someone holds an orchestrator on top to manage all these agents and before long you've got this agent team