Split a large project across agents that specialize in different parts of it. Each keeps responsibility for its work, coordinates with teammates and can use its own temporary subagents for smaller jobs. The team can tackle more than one agent could keep in view.
When a project has months of decisions behind it, another agent may already know what you need. Use rig send to ask that specialist directly and bring the answer into your work, without creating a new task for a simple question.
An assignment needs to stay visible after the conversation moves on. With rig queue, an agent can assign work to a named teammate, who reads and claims it. The task keeps its owner and progress available for later follow-up.
A small task can grow into the wrong project if its purpose gets lost. OpenRig scopes connect the immediate work to its mission and slice, so an agent can check what belongs in the current milestone before deciding what to build.
A long project builds up decisions that no single agent can keep in its immediate context. With rig context, an agent can retrieve a specific piece of project knowledge—including why a choice was made—and use it in today’s work.
An orchestrator should not have to remember every step of a long project. OpenRig workflows keep the current position and authored sequence available, so the agent can check what comes next, use its judgment and move work to the next owner.
Share an idea, report a problem or ask for a change. Your lead agent clarifies what you want, finds the right teammate and routes the work. You don’t have to know who handles each part of the project.
“What can I try today?” Your lead agent checks the team’s tracked work, asks a specialist where more detail is needed and brings you an answer. You don’t have to piece it together from tickets, commits and separate agent conversations.
