Skip to main content
This guide walks you through creating your first AI coding task on Whim. By the end, you’ll have an AI agent working on your code in a cloud container.
Prerequisites: A GitHub account and a repository you want to work on. Whim connects to GitHub for authentication and repo access.

​
1. Sign up with GitHub

Go to whim.run and click Start Building. You’ll be prompted to sign in with your GitHub account. No credit card is required — you start with a free trial. After signing in, you’ll fill in a short profile (name, email, role) so Whim can tailor your experience.

​
2. Install the GitHub App

Whim uses a GitHub App to access your repositories. During onboarding, you’ll be prompted to install the Whim GitHub App on your GitHub account or organization.
1

Click Install GitHub App

You’ll be redirected to GitHub to authorize the app.
2

Choose repositories

Select which repositories Whim can access — you can grant access to all repos or pick specific ones.
3

Confirm installation

GitHub redirects you back to Whim. The app is now linked to your account.
Already have the GitHub App installed? Whim detects existing installations automatically and skips this step.

​
3. Create a workspace

A workspace maps to a GitHub repository. Pick the repo you want to work on from the list of available repositories. Whim creates the workspace, syncs your repo’s code into the cloud, and sets up the environment.
You can also create a brand-new GitHub repository directly from this screen if you’re starting a fresh project.

​
4. Choose your AI provider

Whim supports multiple AI providers. Pick the one that fits your workflow:
ProviderDescription
Claude (Anthropic)Native Claude Code CLI. Use Whim’s built-in compute or bring your own Claude Pro/Team subscription.
Codex (OpenAI)Native Codex CLI. Requires your own OpenAI API key.
OpenRouterAccess 10+ models (GPT, Gemini, Grok, DeepSeek, and more) through a single integration.
You’ll connect your provider by entering an API key or linking your existing subscription. You can always add more providers later from workspace settings.

​
5. Launch your first task

Now for the exciting part — creating a task:
1

Write your prompt

Describe what you want the AI agent to do. Be specific: “Add a dark mode toggle to the settings page” works better than “improve the UI.”
2

Pick a model

Choose the AI model for this task (e.g., Claude Opus, Claude Sonnet, GPT-4o, Gemini).
3

Launch

Click Create Task. Whim spins up an isolated container, clones your repo, checks out a fresh branch, and starts the AI agent.

​
6. Watch it work

Once launched, you’ll see the agent’s terminal output streaming in real time. You can:
  • Watch the terminal — see every command and file edit as it happens
  • Open additional panes — add a shell terminal, file browser, or live preview alongside the agent
  • Send follow-up prompts — guide the agent if it needs course correction

​
7. Review the results

When the agent completes its work, you’ll find:
  • A git branch with all the changes, ready for review
  • A pull request (if the agent created one) linked directly from the task
  • Full conversation history showing the agent’s reasoning and every action it took
From here you can merge the PR, fork the task to try a different approach, or launch a new task to keep building.

Core Concepts

Learn about workspaces, tasks, providers, and branch isolation.

Onboarding Walkthrough

Detailed guide through every step of the setup wizard.