Agent Workflow Patterns Skill

Goal

Compose reliable LLM systems from a small set of predictable, well-understood workflow patterns, and know when a fixed workflow suffices versus when a dynamic, autonomous agent is actually warranted. A workflow is a path you wrote — the control flow is fixed and the LLM fills in steps; an agent decides its own steps and tool calls at runtime. Workflows are cheaper, more testable, and more auditable; agents are more flexible but harder to constrain and debug. The objective is to reach for the simplest composition that meets the quality bar, add structure only when it earns its keep, and escalate to a full agent only when no fixed workflow can express the task.

Steps