Essay/Claude Code·Apr 18, 2026

Claude Code Gets a Full Redesign — and Routines That Run While You Sleep

Anthropic overhauled the Claude Code desktop app with a Mission Control sidebar and launched Routines — scheduled, API-triggered, and webhook-based automation that runs without you.

Luke Thompson
Luke ThompsonApr 18, 2026 · 4 min read
In this article
Claude Code Gets a Full Redesign — and Routines That Run While You Sleep
On April 14, Anthropic shipped two updates to Claude Code that change what "agentic coding" actually looks like in practice: a complete redesign of the desktop app, and a new feature called Routines that lets Claude run tasks on a schedule, respond to webhooks, or accept API triggers — without you being at your computer. Together, they move Claude Code from "AI assistant" to something closer to an autonomous engineering teammate.

Mission Control: Managing Multiple Agents at Once

The biggest visual change is the new sidebar — which Anthropic is calling Mission Control. It gives you a unified view of every active and recent Claude Code session: filter by status, project, or environment, and steer agents that have drifted off course or review diffs before they ship. You can drag and drop the layout — terminal, preview pane, diff viewer, and chat — into whatever grid matches how you actually work. (See also: Claude Code vs Codex CLI) (See also: Claude Code Auto Mode) (See also: Anthropic's 2026 agentic coding trends report)

This is a direct response to how senior developers use Claude Code in practice. You're not running one agent on one task. You're kicking off a refactor in one repo, fixing a bug in another, and writing tests in a third — all at the same time. The old terminal-only interface required constant context switching. The new desktop app makes parallel agent management viable.

Side Chat: Ask Questions Without Polluting the Main Task

There's a smaller feature that's going to save a lot of frustration: Side Chat (⌘ + ;). It opens a separate conversation panel so you can ask a clarifying question or get quick context without injecting that exchange into your main task's history. Anyone who's accidentally broken an agent's focus by asking a tangential question mid-task will appreciate this.

Routines: Three Types of Automation

Routines move Claude Code's execution off your local machine and onto Anthropic's infrastructure. Previously, if you wanted Claude to run a nightly bug triage, your laptop had to be open. Now it doesn't.

  • Scheduled Routines — Run on a cron-like schedule. Perfect for nightly backlog triage, docs-drift scanning, or weekly dependency audits.
  • API Routines — Each routine gets a dedicated endpoint and auth token. Trigger Claude from Datadog alerts, CI/CD pipelines, or any external tool via HTTP.
  • Webhook Routines (GitHub) — Claude listens for repository events and automatically opens sessions to address PR comments or CI failures.
25/day
Routines per day on Team/Enterprise plans (Pro: 5, Max: 15)

Desktop GUI vs. Terminal: The Real Trade-off

VentureBeat tested both environments extensively. The terminal still wins for single-task, high-focus work where you know exactly what you want. The desktop app wins for anything involving parallel agents, visibility into running sessions, or showing your work to a non-technical stakeholder.

The key enterprise insight: the desktop app makes Claude Code explainable to managers and product leads who aren't in the terminal. When you can show someone a visual grid of five agents working simultaneously, the ROI conversation changes.

Field note

Routines decouple Claude Code's power from your presence. A task that used to require you to babysit it can now run at 2 AM, file a PR, and be ready for review when you wake up.

What This Means For You

If you're using Claude Code for real work, Routines are the most immediately useful addition here. Start with one Scheduled Routine — pick something repeatable and low-stakes, like a nightly check for outdated dependencies or stale branches. Run it for a week and see what breaks. Then expand.

The API Routine type is particularly powerful for teams that already have alerting infrastructure. Wiring a Datadog alert directly to a Claude Code session that diagnoses and opens a draft PR is a genuine workflow multiplier. The webhook integration with GitHub for PR review comments is the same idea — Claude starts working the moment something needs attention, not when you remember to check.

The redesigned desktop app is available now for Mac and Windows. Routines are in research preview — meaning the functionality is live but the interface and limits will change as Anthropic collects feedback.

Sources & Further Reading

Related essay
Claude Code Gets a Mission Control and Routines That Run While You Sleep
Related essay
Anthropic's 2026 Agentic Coding Trends Report: 8 Shifts Reshaping Software Development
Related essay
Dynamic Workflows in Claude Code: How Anthropic Just Made Months-Long Engineering Work Finish in Days

THE CLAUDE INSIDER

Get the Claude playbook in your inbox.

One weekly email for Claude and Claude Code users. Real workflows, no hype. Subscribe and we send you The Claude Power-User Cheatsheet.

GUIDES AND COMPARISONS

— ¶ —

Luke Thompson

Luke Thompson

Editor-in-Chief · The Claude Insider

Luke Thompson is the founder of The Operations Guide, LLC and editor of The Claude Insider. Based in Jonesborough, Tennessee, he has spent years building AI-augmented business systems and automation workflows for operators and teams. He began working with large language models in production well before the current wave of consumer AI tools, integrating them into client workflows, content pipelines, and operational infrastructure. At The Claude Insider, he writes about Claude with the specificity of someone who uses it daily as a professional tool — not as a reviewer or commentator, but as a builder. His coverage focuses on what actually works: prompt patterns, API integration strategies, agentic workflows, and the real-world tradeoffs that practitioners face. He is not affiliated with Anthropic, PBC.

Articles are researched and drafted with AI assistance, reviewed and edited by Luke Thompson.

From Reading to Action

Know where AI can pay off in your company.

Take the free two-minute AI Readiness Assessment. See your score, the two gaps holding you back, and the next move worth making.

Get your readiness score

Instant report · No account to start

Related reading

View archive →