Capabilities · Workbench

Workbench — the Agent Center

The Workbench is a local web view onto a run — a place to read the work, edit and comment on it, approve steps, and watch the agent graph move in real time. It is additive: nothing about a run depends on it being open.

Diagram of the Workbench: a per-project local Agent Center served on port 4317 with per-project *.localhost host-routing, showing a live agent graph alongside read, edit, comment, and approve controls.
A per-project local Agent Center on :4317 — read, edit, comment, approve, and watch a live graph.

The Workbench is a per-project local Agent Center on :4317, served with *.localhost host-routing so each project gets its own address on the one local server. From it you can read, edit, comment, and approve the run's artifacts, and watch and steer a live graph of the agents as they work.

It is an additive layer, not a dependency: the terminal works without it. Run the same task entirely from the command line and nothing is lost — the Workbench adds a way to see and steer the run, not a way to make it possible.

What it looks like

The Works home lists every run in the project with its status, shape, and progress — the front door to everything the agents are doing:

The Workbench Works home: a grid of run cards each showing title, routed shape, and progress, above KPI tiles for active runs, in-progress tasks, agents live, and throughput.
The Works home — every run in the project, with status, shape, and progress.

Open a run and the Live graph renders it as the task DAG — routing → spec → plan → the bounded tasks — with typed edges and live execution overlay, so you can watch the work move:

The Workbench Live graph: a run rendered as a directed task graph with auto-layout, typed edges, a legend (derives, blocks, satisfies), and a minimap.
The Live graph — the run as a typed task DAG with auto-layout, a legend, and a minimap.

Click any node and its artifact opens as a document you can read, edit, and comment on — the spec, the plan, an ADR, a task — with the agent conversation in a side rail:

The Workbench docs workspace: a run-document navigator (Definition, Decisions, Tasks) beside a rendered Spec document, with a conversation rail for comments and agent replies.
The docs workspace — read, edit, and comment on a run's artifacts, with the conversation rail alongside.