Chapter 02 of 12 · Aishwarya Ashok
Peanut equips the workshop
The model needs somewhere to work. Harness, runtime, scaffold, and orchestration describe overlapping pieces of that environment. Read them together: the boundaries vary across tools and teams.
The surrounding software that connects a model to tools, manages its work, and applies execution controls.
A model needs a way to call tools, receive results, retain progress, and operate within permissions. The harness supplies that supporting software. When an agent loses track of a task or handles a tool failure badly, examine this setup as well as the model. Teams draw the harness boundary differently, but these supporting responsibilities have to live somewhere.
The software that runs an agent's execution cycle and manages its active operations.
Someone has to make the model call, dispatch the requested tool, and deliver its result. Those are runtime responsibilities. A runtime may also manage concurrent operations, cancellation, and failures. The term emphasizes active execution, so it overlaps with the harness wherever the harness also handles running the work.
A supporting arrangement of prompts, code, and task structure used to guide an agent's work.
Prompts and code can give an agent useful structure: a planning stage, a checklist, or a review step before completion. That arrangement is often called a scaffold. The term has loose boundaries and can overlap with harness. When discussing a particular system, describe the structure it supplies rather than assuming everyone means the same component.
Software that coordinates the order, dependencies, and exchange of information between tasks, tools, or agents.
Dependencies determine what can run next. An orchestration layer tracks those dependencies, passes results between steps, and coordinates the work. Some choices follow rules; others can be delegated to a model. A useful design makes it clear who decides the sequence and what happens when a required result never arrives.
The computing environment in which an agent's tools and code run, including its resources and access limits.
Installed packages, files, compute resources, and network access all affect what a tool can do. Permissions further limit its reach. This is why a task that works in one environment may fail in another. Before blaming the model, check whether its tools can reach the files and services the job requires.