← All projects

Edward

Edward is an AI coding workspace where users can generate apps from chat, inspect files, run them in isolated environments, publish previews, and sync everything to GitHub.

Overview

Edward was built as a place to actually make software, not just chat about it. A user can describe an app in plain language, generate code, inspect and edit files, run it in an isolated environment, publish a live preview, and sync the result back to GitHub without leaving the product.

How It Was Built

The main technical choices behind the product, from system design to the parts that make it work day to day.

  • Split the product into a web app, an API, background workers, and Docker-based run environments so each part has a clear job.
  • Built the full flow from prompt to files to running app. Users can inspect code, edit it, see logs, preview the result, and sync it to GitHub.

Impact

  • Combined prompt, build, preview, and sync into one workflow instead of spreading that work across several tools.
  • Made generated code easier to review by turning it into running apps with logs and live previews.

Highlights

  • Built around execution, not just generation.
  • Combines product design with the backend systems needed to actually run apps.

Tech Stack

Next.js 16Express.jsBullMQDocker SandboxesOpenAI & GeminiPostgreSQLRedisGitHub SyncAWS S3 + CloudFrontCloudflare Preview Routing

More Projects

Additional work across AI products, developer tooling, and full-stack systems.

Browse all →