Quickstart: App
Published
Updated
From zero to a working AI coding session.
Before You Begin: The Waiting Room
Verifying your email confirms your address, but a new account remains pending until the Wallfacer team activates it. Open the app to view your account status and any available setup steps.
If your account is awaiting activation, the app shows You're on the list and says the Wallfacer team will get in touch. When your signed-up email address loads, the page shows where the team will reach you. The workspace opens automatically after activation.
Once the account is active, the dashboard opens on account setup: a welcome, your email subdomain, and your Slack workspace. See Set Up a New Account.
Choose Contact the team to email Wallfacer while you wait. If you have another account, choose Use another account to switch to it. Sign out is in the iOS navigation bar and on the page on Android and web.
Prerequisites
- A GitHub account (this quickstart builds on a code repository; see GitHub Integration for when GitHub is optional)
- A Wallfacer account
- For the iPhone or iPad app, iOS 27 or iPadOS 27 or later. Devices on version 26 cannot install the current app. You can use Wallfacer in a browser instead.
On iPhone or iPad, Continue with Apple is available on the welcome, log-in, and sign-up screens. See Sign Up and Set a Password for code requirements and Apple's email privacy choice.
Step 1: Create an Agent
You assign work to an agent with its own computer, model, and identity. Create one before you start coding.
- Open Team on the dashboard and choose Hire your first AI employee. The app's Hire on the dashboard link opens this page.
- Work through the six steps: a role, a first name, an avatar, an email address, an experience level, and Add to Slack. Wallfacer provisions the agent's computer when you finish the experience level step.
- Hiring ends on the agent's page, which opens with its onboarding checklist. Wallfacer supplies the model for the level you chose, so there is no model key to connect.
See Agents for the full model, and Environments for what a computer contains.
Step 2: Connect Your Agent to GitHub
This quickstart clones a repo, so GitHub is required here. Work that doesn't use a repository can skip this step.
- Open the agent from Team on the dashboard and choose Integrations > GitHub.
- Paste a token for the GitHub account the agent should act as. Use a dedicated bot account so its work is clearly attributable.
- Choose Connect. The section then shows the account the agent is connected as.
See GitHub Integration for details.
Step 3: Create a Task
- On iPhone or Android, tap New Chat in task history and choose your agent. On web, open your agent from Team and choose Assign work. Its computer and model are set for you automatically.
- You land in the task screen, empty, with the chat input at the bottom.
- Type a message describing what you want built and send it. Sending it is what creates the task.
Step 4: Start Coding
A VM usually boots from your snapshot. If that snapshot cannot be restored, Wallfacer boots a fresh VM and rebuilds the snapshot. You're in a live chat with Claude Code.
- Send messages to direct Claude's work
- Watch file changes appear in the diff viewer as Claude writes code
- Claude auto-commits to a branch as it works
Step 5: Review
When files change, the pill above the task composer shows the changed-file count and lines added and removed. Select it to review the diff. On phones, the Code Changes tray lets you switch between the Code diff and a Files list that covers every repository in the task. On tablets and desktop, the pill opens the Diff pane. Additions appear in green and deletions in red. See Code Review for file navigation and pull requests.
What's Next
- Agents -- How agents carry their computer, model, and identity
- Environments -- Customize your setup commands, services, and platform
- Sessions -- How coding sessions work
- API Quickstart -- Programmatic access via the REST API