EveStudioDocs

The workspace

Once an agent is active, Studio's window has three regions: the left rail (your agents and their chat threads), the per-agent header (name, status, and run/deploy controls), and the top tab bar (everything you do with the agent). This page is the map; each tab links to its own doc.

The left rail

The rail lists every agent Studio knows about. At the top:

  • Add existing — opens a folder picker to register an Eve app you already have (the folder containing agent/).
  • ＋ — scaffolds a new agent. See Create an agent.

Click an agent to make it active. It expands to show that agent's chat threads, with an inline ＋ New chat to start a fresh one. Threads are your saved conversations — see Chat.

Managing threads:

  • Hover a thread to reveal an archive icon; archiving moves the thread out of the sidebar without deleting it.
  • An ARCHIVED · N row appears when an agent has archived threads. Click it to open the Archived modal, where you can Reopen a thread back into the rail or delete it for good.

Settings sits at the bottom of the rail.

The per-agent header

Above the tabs, the header shows the active agent's state and its controls:

  • Name of the agent.
  • A status pill — running or stopped.
  • A mono metadata line with the current facts about the agent: its local dev URL and port, its deployed URL and age, and the Eve version — e.g. local :2000 / deployed · 3d / eve 1.x.
  • Start / Stop — starts or stops the local dev server (eve dev). Local Chat needs this running.
  • Deploy — ships the agent to production (eve deploy). See Deploy to Vercel.

The top tab bar

The tabs are the surfaces for building, running, and shipping the agent:

  • Chat — talk to the agent's local dev server or its production deployment, with streamed tool calls, subagent delegations, reasoning, and approvals.
  • Instructions — edit instructions.md (the system prompt) and the model and reasoning in agent.ts.
  • Capabilities — browse, create, open, edit, and delete Tools, Skills, Subagents, and Hooks.
  • Integrations — wire up Connections and Channels.
  • Memory — see whether the agent uses Eve's native durable sessions or an external long-term brain (Arcana), and configure it.
  • Schedules — list and create cron jobs that wake the agent (agent/schedules/*.ts).
  • Deploy — build, deploy, view logs, and manage environment variables and the sandbox.
  • Evals — inspect and run the agent's evaluations.

Next