# A Visual Feedback Loop for Electron Apps with Claude Code

DevFeed: [A Visual Feedback Loop for Electron Apps with Claude Code](<https://devfeed.tech/articles/a-visual-feedback-loop-for-electron-apps-with-claude-code-21153.md>)

Original publisher: [Read original article](<https://juri.dev/articles/visual-feedback-loop-electron-apps-claude-code/>)

Published: 2026-03-06T00:00:00Z

Content type: tutorial

Language: en

Sources: [Juri Strumpflohner](<https://devfeed.tech/sources/juri-strumpflohner.md>)

Topics: [Electron](<https://devfeed.tech/topics/electron.md>), [Agent Browser](<https://devfeed.tech/topics/agent-browser.md>), [Claude Code](<https://devfeed.tech/topics/claude-code.md>), [Protocol (disambiguation)](<https://devfeed.tech/topics/protocol.md>), [Tooling](<https://devfeed.tech/topics/tooling.md>), [Command-line interface](<https://devfeed.tech/topics/cli.md>), [Chromium](<https://devfeed.tech/topics/chromium.md>)

Tags: [agent-browser](<https://devfeed.tech/tags/agent-browser.md>), [chromium](<https://devfeed.tech/tags/chromium.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [cli](<https://devfeed.tech/tags/cli.md>), [devtools](<https://devfeed.tech/tags/devtools.md>), [electron](<https://devfeed.tech/tags/electron.md>), [nx](<https://devfeed.tech/tags/nx.md>), [protocol](<https://devfeed.tech/tags/protocol.md>), [tooling](<https://devfeed.tech/tags/tooling.md>)

## AI overview

This tutorial explains how to give Claude Code visual feedback when building Electron applications. It uses agent-browser and the Chrome DevTools Protocol to connect to a running Electron app, capture screenshots, inspect the DOM, and verify that the rendered interface works. The article covers installing the required tooling, enabling CDP, configuring electron-vite and Nx development scripts, and checking the CDP endpoint.

## Source excerpt

A Visual Feedback Loop for Electron Apps with Claude Code When building Electron apps with an AI coding agent, you run into a fundamental problem: the agent can't see what it's building. It writes code, runs the build, maybe checks the logs, but never actually looks at the rendered UI. If the window is blank or the layout is broken, it has no way to know. I found a way to close that gap using agent-browser and Chrome DevTools Protocol (CDP).