AI Board workflow

Build mode

Turn several AI models into a coding team: one architect plans and reviews, while worker models implement focused tasks in parallel.

Architect and worker models

In Build mode, the judge model becomes the architect. It breaks your request into concrete tasks, assigns those tasks to worker models, reviews the results, asks for fixes when needed, and writes a final hand-off summary.

Worker models handle focused pieces of the implementation. The architect tracks approvals, fixes, failures, and throughput so the strongest available models are favored over time.

Local-first project access

Files can stay in the browser, be downloaded as a zip, be written to a browser-picked folder, or go through the optional local runner. The runner is a script you start yourself. It can write to your project folder, run tests/builds with your approval, fetch public pages, and bridge MCP tools such as Playwright, Context7, or SearXNG search.

When to use it

  • Scaffolding a small app or feature from a clear prompt.
  • Splitting implementation work across several AI models.
  • Letting one model review another model's code before hand-off.
  • Running local checks through a user-controlled runner.

Start a build