Anthropic says delete most subagents: one agent loop beats multi-agent setups

gerardsans · x · 2026-11-17

Anthropic's Applied AI team found that a single agent loop with skills and tools often beats complex multi-agent setups on quality, cost and speed — one company cut runtime roughly in half by collapsing its multi-agent harness into one loop.

Gerard Sans criticizes Anthropic for contradicting itself: it previously told builders to split work into subagents, and the literature pointed this way months ago while the industry endured the '10K swarm' narrative. 'You can't trust anything AI labs say,' he writes.

Related event: Anthropic Advises Developers to Fold Subagents into Single-Agent Loops(4 posts)→

Original post →

More from coding & agent

coding & agent channel →