Blog · August 12, 2026 · 5 min read

Want to Be Notified When Claude Responds? How Claude Notifications Work on Web, Desktop, and Mobile

You hand Claude a big job — a long piece of research, a pile of files, a task that will clearly take a while — and a little prompt appears: "Want to be notified when Claude responds?" Most people either click it away without reading or click Allow and never see a notification they noticed. Then they do what everyone does: keep the tab open and glance at it every ninety seconds.

That prompt is actually the fix for one of the most annoying parts of working with AI: the babysitting. Here's what it does, how to turn Claude notifications on (or back on) across web, desktop, and mobile — and what to do in the places that little prompt doesn't reach, like the terminal.

What that prompt actually does

Claude's web app at claude.ai can send you a browser notification when a long-running response is finished, so you can go do something else instead of watching the tab. Because browsers don't let websites notify you without permission, Claude has to ask first — that's the "Want to be notified when Claude responds?" prompt, which typically shows up when you kick off something slow, like a research task or a large generation.

Click Allow (in both Claude's prompt and the browser's own permission popup, if it appears) and you're done: when Claude finishes while you're in another tab or another app, a system notification tells you it's ready.

If you dismissed the prompt and want it back

The prompt itself won't nag you forever, and if you (or your browser) blocked notifications once, Claude can't re-ask. The switch lives in two places, and both need to be on:

  • Claude's own settings — open claude.ai, go to Settings and look for the notifications option, and enable notifications for completed responses.
  • Your browser's site permissions — click the icon next to the address bar on claude.ai and set Notifications to Allow. In Chrome this is under Site settings; Safari, Firefox, and Edge have equivalents. If this is set to Block, no setting inside Claude can override it.

One more gotcha at the operating-system level: if your system's Focus or Do Not Disturb mode is on, or your OS has notifications from your browser disabled, the notification fires and dies silently. macOS users will find this in System Settings → Notifications; Windows users under Settings → System → Notifications.

Desktop and mobile apps

If you use the Claude desktop app instead of the browser, it notifies through your operating system's normal notification system — grant it permission the first time it asks, and check the OS notification settings for the app if nothing comes through. On the Claude mobile apps for iOS and Android, it's the standard push-notification permission: allow it when the app asks, or enable it later in your phone's per-app notification settings.

The mobile app is quietly the best answer to a common wish: getting pinged on your phone when a long job you started on your laptop is done. Start the conversation, walk away, and your phone tells you when there's something to read.

Where the built-in notifications stop

All of the above covers the Claude chat apps. But a lot of the longest-running Claude work doesn't happen in a chat window — it happens in a terminal, inside Claude Code, where an agent can churn away for ten or twenty minutes on a refactor or a test suite. There is no "Want to be notified?" prompt there.

The terminal has its own answers, and we've written them up in detail: the built-in terminal bell and hook system in our Claude Code notifications guide, and the equivalent setups for Codex CLI and Cursor. They work — but they all involve config files, hooks, or shell scripts, and each tool needs its own setup.

The habit that makes notifications worth it

Turning notifications on is step one. Step two is trusting them: close the tab, switch to real work, and let the ping bring you back. The whole point of delegating work to Claude is reclaiming the minutes it's thinking — a notification you trust is what turns "watching a progress spinner" into actual free time. Allow the prompt once, check the three switches above if it goes quiet, and stop checking the tab.

Keep reading

Claude Code Tips and Tricks: 12 Ways to Use Claude Code Effectively

8 min read

Claude Code Multiple Sessions: How to Run Agents in Parallel Without Losing Track

6 min read

A Claude Code Workflow That Doesn't Involve Watching the Terminal

5 min read

Claude Code Hooks: A Practical Guide to Automating Your Agent Workflow

7 min read

Claude Code Auto Mode: Fewer Permission Prompts Without Living Dangerously

7 min read

Claude Code Subagents: How to Delegate Work to Specialized Agents

7 min read

Claude Code Context Management: Treat the Context Window Like a Budget

6 min read

Per-Subagent Model Selection: Route the Grunt Work Down, Keep the Judgment Up Top

7 min read

Skills and Plugins: How to Teach Claude Code Your Way of Working

7 min read

Claude Code Background Tasks: Run Long Commands Without Blocking Your Session

6 min read

Codex CLI Notifications: How to Get a Ding When Codex Is Done or Needs Input

7 min read

Cursor Notification When Done: Every Way to Get Notified When Cursor Finishes

6 min read

Claude Code Notifications: How to Get Notified When Claude Code Finishes or Needs Your Input

6 min read

Claude Code Notification Scripts: Copy-Paste Recipes for Every Platform

6 min read

Get a Ding the Moment Codex Needs Your Response

6 min read

Get Notified the Moment Claude Code Is Waiting for Your Input

6 min read

“Notifications Are Turned Off for Claude” — Here Is the Fix

6 min read

Codex Sound When Done: Make Codex CLI Play a Sound When It Finishes

6 min read

terminal-notifier + Claude Code: Native macOS Alerts When Your Agent Finishes

6 min read

Gemini CLI Notifications: How to Get a Sound or Alert When Gemini Finishes

6 min read

Get Claude Code Notifications on Your Phone

6 min read