AI & ML

agent-workflow

Use when the user explicitly asks to parallelize work, coordinate multiple agents, run parallel scouts, split work across independent owners, or coordinate multiple independent verifiers; first perform the orchestration fit check even when the correct result is to keep one owner. Also use when two or more genuinely independent subsystem or artifact slices, repeated per-item pipelines, orthogonal scout questions, or high-stakes candidate-and-review scopes require coordinated ownership and integration with material benefit over one owner. Own decomposition, assignment, evidence handoff, verification coordination, and integration. Do not use for one focused delegation or verifier, small independent tasks without an explicit orchestration request when coordination cost exceeds the benefit, coherent single-owner or shared-root work without an explicit orchestration request, capability-only parallelism, or work already owned by another orchestration layer.