Skip to main content

​
Get a quick overview

The Scott Method

Our philosophy on building with agents — why intent review matters.

How Scott AI works

Planspaces, context flows, and an agent centric project lifecycle.

​
Set up Scott AI

  1. Install Scott AI — run the install script (see Install below) or sign in at app.tryscott.ai for the browser version
  2. Create a planspace — name it after the feature or project you’re planning
  3. Attach context — connect your GitHub repo, upload docs, or point to a local folder so the agent can ground its output in your codebase
  4. Describe what you want to build — start with a rough prototype from your coding agent, or describe the intent from scratch
  5. Invite your team — click Share, add teammates by email, assign roles
  6. Request a review — when the spec is ready, request reviews from stakeholders
Start with a real project your team is about to begin. The best way to evaluate Scott is with a plan that actually matters.
Next steps: Sharing · Reviews · Making the most of Scott AI
  1. Accept your invite — check your email for a planspace invite and sign in
  2. Explore the planspace — review the document your team mate shared with you.
  3. Leave comments — select text in the document and add your feedback. Use @ to mention teammates
  4. Install Scott AI — curl -fsSL https://tryscott.ai/install | sh
  5. Pull context — run scott pull in your repo to link the planspace to your local branch
Next steps: Context flows · Comments · CLI
  1. Read The Scott Method at tryscott.ai/method
  2. Create a planspace or ask your team for a public link to see one in action
  3. Check the For You inbox — your surface for visibility into what’s being planned across teams
  4. See how intent links to code — Scott CI auto-links PRs back to approved specs
Next steps: For You · Scott CI · Making the most of Scott AI

​
Install

Go to app.tryscott.ai and sign in with Google or GitHub. The browser app uses cloud sandbox execution and supports Google Drive as a connected source.