Your first agent run.
From a blank workspace to a finished deliverable in roughly five minutes. Create a project, upload a file, ask the agent to do something useful, and watch it work.
§ 01Create a project
Open the agents workspace and click New project. A project is the top-level container — it holds your files, your runs, and the agent's history. Give it a name that reflects the work, not the model: "Acme Q3 contracts" is better than "test".
You can have many projects. Each one is fully isolated from the others — uploaded files, terminal scrollback, browser cookies, and run history never cross between projects, even when the same agent type is in use on both sides.
§ 02Upload files to the drive
Every project has a drive — its own file area. Drag files in from your desktop or use the upload button. Common formats are supported out of the box.
- Documents —
.pdf,.docx,.txt,.md,.json - Spreadsheets —
.xlsx,.csv - Images —
.png,.jpg,.jpeg,.gif,.webp(OCR runs automatically)
Each upload is validated by magic-number signature, not just extension, and the original filename is retained as metadata. Once a file is in the drive the agent can read it as soon as you reference it in chat.
§ 03Start a chat with the agent
Click into the chat pane. Ask the agent something concrete — concrete enough that you'd know whether it succeeded.
Read the contract I just uploaded. Pull out the parties,
effective date, term length, renewal terms, termination
clauses, and any payment schedules. Give me a one-page
summary I can paste into a memo.
Hit send. The agent receives your message together with a context bundle: the project's file list, the active surface, and any relevant skills. It plans, then begins to act.
§ 04Watch the surfaces switch
This is the moment that distinguishes the agent workspace from a chat product. As the agent works, the UI follows along.
- If the agent reads a file, the IDE opens with that file selected and the relevant section scrolled into view.
- If the agent runs a shell command — say, to convert a docx to markdown — the terminal surface comes forward, with live output streaming from a real PTY.
- If the agent visits a website to verify a fact or scrape a portal, the browser surface comes forward and you see the page being driven in real time.
- If the agent boots a dev server, the preview surface lights up with the live URL.
You don't have to switch tabs or click anything. The agent emits a surface_switch event each time it changes context, and the UI follows.
§ 05Inspect artifacts
When the agent finishes, two things have happened.
- It has told you what it produced, in the chat pane, with a short summary.
- It has saved the deliverable as one or more artifacts — the formal output of the run. Artifacts show up in the run record and in the project's outputs list, and you can download them as files or copy their contents inline.
Artifacts are the part of the run that survives the chat. The chat is the conversation; artifacts are the deliverables.
§ 06Re-run from history
Open the history panel for the project and you'll see every run, with timestamps and the prompt that started each one. Click into a past run and you can:
- Replay the timeline event-by-event — every tool call, every terminal output, every browser session.
- Re-open any artifact the run produced.
- Re-run with the same prompt against fresh files, or a tweaked version of the prompt against the same files.
§ 07Common patterns
A few requests that almost always produce a clean result on the first run.
Summarize this contract
Drop a contract PDF into the drive. Ask the agent to extract parties, effective date, term, renewal, termination, and payment terms, and to produce a one-page memo. The agent reads the document, identifies the clauses, and writes a structured summary.
Extract invoice line items
Drop a folder of invoice PDFs into the drive. Ask the agent to extract vendor, invoice number, date, line items, subtotal, tax, and total from each one, and to produce a CSV. The agent runs through the files, OCRs as needed, and saves the spreadsheet as an artifact.
Research and brief
Ask the agent to research a company, a market, or a topic. It will use the browser surface to gather sources, the terminal to process them if useful, and produce a written brief with citations.
§ 08Where to go next
Three good directions from here.
- I want to understand projects, runs, and sessions in detail → Project workspace.
- I want to learn the surfaces the agent acts through → Surfaces.
- I want to use a pre-built job instead of free-form chat → Skills & jobs.