Decisions

Short reference pages, one per recurring "which one do I use?" question. Each page has a decision tree, a quick-reference table, and pointers to the deep guides for the chosen option.

Picking your starting point

• Which tier? — Basic, Mid, Full, or Advanced.

Inside an Agent

• Return type — .text() vs .payload vs .metadata.
• State layer — Memory, Store, or sources=.
• Tool wrapping — Tool.wrap(fn, ...) directly, a shared-state handle, or a bridging class (usually: not the class).

Composing Agents

• Composition — Agent.chain vs Agent.parallel vs Agent(tools=[...]) vs Plan.
• Parallelism — automatic (LLM-decided) vs declared.

Human / verifier placement

• HumanEngine vs SupervisorEngine
• verify= placement — Agent / tool / Plan step.

Production-grade Plan

• Checkpoint & resume — when is the storage overhead worth it?

Extension surface

• Do I need Advanced? — smell test for the framework-author tier.