3 docs tagged with "loops"

A chain has edges you fixed at design time: step A always leads to step B. An agent hands that decision to the model — the next step is chosen at runtime, from the model's own output.

A plain addedge("a", "b") always routes from a to b. addconditional_edges routes based on a function of the current state — this is how a graph loops an agent node against a tool node until the model stops requesting calls.

Four looping forms cover every case. The decision is rarely about capability — they are mostly