split and merge
An agentic pattern where Claude automatically decomposes a task into independent pieces, fans out to multiple sub-agents running in parallel, and merges results back into a single output
As defined in Every Claude Code Workflow Explained (& When to Use Each)
Where it comes up · 1
Most important claims · 5 of 5Search all claims for “split and merge” →
- The builder-validator chain is a powerful application of split-and-merge where one sub-agent builds something, passes it back to the main agent, which then passes it to a second sub-agent for validation and review, enabling quality assurance without manual user review.Every Claude Code Workflow Explained (& When to Use Each)
- Sub-agents in split-and-merge can only report back to the main agent; they cannot communicate directly with each other, requiring all inter-agent coordination to funnel through the main agent in a hub-and-spoke topology.Every Claude Code Workflow Explained (& When to Use Each)
- Claude can create up to 10 sub-agents in parallel simultaneously within split-and-merge; any additional parallelizable tasks beyond 10 are queued as additional sub-agents waiting for capacity.Every Claude Code Workflow Explained (& When to Use Each)
- The GSD framework (Get Stuff Done) and similar planning frameworks are recommended for comprehensive projects with split-and-merge, as they split project briefs into subtasks and execute on those subtasks in a structured way.Every Claude Code Workflow Explained (& When to Use Each)
- In split-and-merge, research is an example of a custom sub-agent that might be described as 'a single gray area decision and returns a structured comparison table with rationale,' defining its role and the tools it has access to.Every Claude Code Workflow Explained (& When to Use Each)