Skip to content
Go To Dashboard

Agent Studio Overview

Agent Studio puts Claude Code or Codex inside an environment built for shipping Sapiom agents. You keep the coding-agent conversation and terminal while Studio adds project navigation, deterministic inspection, and direct local or cloud lifecycle actions around it.

It’s your coding agent on your machine: your login, plan, and model settings apply, and sessions run locally. Cloud operations such as capability calls, deploys, and production agent runs go through Sapiom.

Three surfaces, left to right:

  • Workspace rail. Open local folders, discover agent projects, start from a template or idea, and choose the project a session targets. See Workspaces and projects.
  • Sessions. Run parallel coding-agent conversations in real terminal processes, review recorded history, and choose native resume or a new conversation with a bounded brief. See Sessions.
  • Canvas · Steps · Code. Read the bound agent’s deterministic graph, inspect authored steps and observed runs, then get SDK or HTTP starters after a cloud build is ready. See Canvas, Steps, and Code.

Press ⌘K to jump between sessions, agent projects, and recent folders, or to browse templates. Local Run, Prod Run, and Deploy stay in the action bar above the terminal.

Studio keeps direct product actions separate from coding-agent requests:

  • Direct actions run through Studio itself. Canvas rendering and Local Run are local; Deploy starts a cloud build, while Prod Run starts a production run. None prompts your coding agent.
  • Coding-agent actions type or inject a request into the active Claude Code or Codex session. Free-form chat, step debugging and explanation, and template or idea creation belong to this path. Background description rewriting currently requires Claude Code.

Agent Studio and its session-scoped Sapiom MCP require a signed-in Sapiom account. After sign-in, local inspection and Local Run stay on your machine and create no Sapiom capability spend. Deploys and production runs additionally use Sapiom cloud infrastructure, and production work can incur capability spend.

Studio launches the selected coding agent with session-scoped instructions and Sapiom MCP. This wiring lets it scaffold, check, locally test, deploy, and run agents without changing your global Claude Code or Codex configuration. Studio’s own local state and session records are separate and can remain after the terminal process exits.