Claude Code Subagents Now Nest Five Levels Deep — Anthropic Is Building a Recursive Workforce

Claude Code can now spawn subagent chains five levels deep, running full end-to-end workflows. Combined with aggressive hiring for RL and reward design, Anthropic is signaling a bet on recursive autonomy over incremental model improvements.

Claude Code's subagent architecture has quietly reached a new level of depth: agents can now spawn subagents that themselves spawn subagents, nesting up to five levels deep with full chain execution running end to end. As @dani_avila7 documented, the entire recursive chain completes without manual intervention, with each level capable of invoking tools, reading files, and making decisions independently.

Unlock the full briefing

Get every story in today's briefing, the full archive, and the daily AI intelligence brief.

All stories today

Full archive

Daily brief

Cancel anytime. Payments powered by Stripe.