Rudder separates the person-like role you work with from the program that runs it and from each individual attempt.

​
The three parts

Rudder coordinates the task and keeps the record. The runtime performs the actual work.

​
Example: a writer that handles every release

Create a Release Writer Agent when launch copy is a recurring responsibility. Give it the runtime and instructions it needs. Each announcement creates a new Run, but the Agent keeps the same role and can reuse approved skills. If the first draft is wrong, ask for another attempt. You still have one Agent, but two separate Runs, so the result and cost of each attempt remain clear.

​
When to create another Agent

Create a new Agent when a repeated class of work needs a different role, runtime, instruction set, budget, or permission level. Use an existing Agent for a one-off request that already fits its job. A Run can start from Chat, an assigned Issue, a review request, an Automation, or a manual action. The starting point changes; the Agent/Run distinction does not.

​
What a Run can show

  • the answer or completion summary
  • created files, reports, screenshots, or links
  • usage and cost when the runtime reports them
  • transcript, tool activity, logs, and final errors when available
Different runtimes expose different features. Rudder shows what each one supports rather than pretending they all behave the same. A partial reply from a stopped or failed Run is not a completed result. See Runtime types for the supported choices, or configure a runtime.