Agent Workflows
The workbench treats agent development as a workflow problem. You define the goal, the tools the agent can use, and the policies it must follow. The workbench handles orchestration, execution, and repeatability.
How Workflows Are Structured
- Projects are the top-level container for code, prompts, and agent configurations.
- Runs capture a single execution, including inputs, outputs, and logs.
- Background agents keep long tasks moving while you focus elsewhere.
- Versioned experiments let you test multiple approaches in parallel.
What A Good Workflow Includes
- Clear outcome (merge a PR, generate a report, update a spec).
- Scoped tools so the agent can act but not overreach.
- Profile and limits to control cost and risk in the runtime sidecar.
- Review point before changes reach production systems.
Parallel Agents
Traditional AI interfaces present single-threaded conversation. Real projects involve exploration, comparison, and parallel investigation.
- Spawning sub-agents: A primary agent working on a task can spawn sub-agents to research alternatives, investigate dependencies, or draft tests. Each runs independently and reports results back.
- Forking for exploration: Facing a decision, fork the context and direct each fork down a different path. Both develop in parallel. Compare results and pick the winner.
- Spatial overview: The workbench presents parallel activity visually, showing all active agents, their status, recent outputs, and relationships.
Why This Matters
Teams need predictability when agents touch real systems. The workbench makes behavior reproducible, comparable, and reviewable while keeping execution controlled.