Do real work.
The agent reaches APIs, local processes, and browser interfaces inside a recorded workspace.
THE METHOD LAYER FOR AGENTS
Keep the path that worked.
rote turns a successful execution trace into an inspectable, versioned Play that another permitted agent can run with fresh inputs.
The result survives. The method disappears.
An agent can reason well, choose the right tools, recover from errors, and finish a task. When the session ends, the result usually remains but the useful path does not. The next run pays to rediscover the same method and may repeat the same mistakes.
rote preserves the method that worked—not the whole transcript.
The reusable object is a typed execution contract, not a larger memory dump.
From execution to reusable method.
Keep evidence.
Each useful response becomes an immutable, queryable workspace artifact instead of disappearing into chat.
Compile what worked.
rote turns the successful trace into typed inputs, declared steps, dependencies, effects, and presentation.
Change the inputs.
Another permitted agent invokes the Play URI and follows the preserved method with fresh inputs.
A Play is inspectable before it is executable.
A Play declares parameters, tools, services, authentication, privileged requirements, effects, steps, dependencies, ownership, visibility, and version. It can render an honest human report, concise summary, or canonical JSON result.
Execution is declared.
The method does not depend on prose alone.
What worked is preserved.
A skill guides reasoning; a Play preserves a specific executable method.
The contract travels too.
Inputs, effects, evidence, presentation, ownership, visibility, and versions stay attached.
Your harness stays yours.
rote is a portable method layer for existing agents and harnesses.