Why is reliability the core problem in multi-step AI workflows?

A workflow wires models and tools together along defined paths. It is the structured, predictable cousin of an agent: instead of letting the model decide every step, a workflow lays the steps out in advance. Anthropic frames the choice as exactly this, between workflows that follow predefined code paths and agents that direct themselves, and advises starting with the simplest approach that works.^[1]

The reason orchestration exists comes down to multiplication. If a single step succeeds 95% of the time, a chain of twenty such steps does not succeed 95% of the time. It succeeds about 0.95²⁰, which is roughly 36%. Push the per-step reliability to 99% and twenty steps still only reach about 82%.

The curve is unforgiving, and it is why a capable model can still produce an unreliable system once you string enough calls together. Every structural pattern below is, at heart, a way to bend that curve.