Definition
An agent scaffold is a task-specific arrangement of prompts, tools, control logic, examples, and feedback wrapped around a model to improve performance. Researchers often use scaffolds to test how much a model can accomplish when given a particular procedure or set of capabilities.
The term is used inconsistently. In one paper it may mean a single planning prompt; in another it may include tool execution, memory, retries, and verification. A result attributed to a scaffold should name those components so another team can reproduce the comparison.
Scaffolds can expose capability, but they also change cost, latency, and failure modes. More calls and more elaborate planning do not guarantee better outcomes.
Distinguish it from nearby terms
A scaffold usually means a task arrangement designed to elicit performance. A harness is the broader runtime and governance layer that operates the agent across work. The boundary varies by source, so the included responsibilities matter more than the label.
Check your understanding
Two benchmark results use the same model. One gives it a code runner, retrieval, five retries, and a test verifier; the other gives it one prompt. The comparison is partly between scaffolds, not only between model outputs.