How to Use Claude's Massive New Upgrades
Episode
25 min
Read time
2 min
Topics
Remote Work, Design & UX, Artificial Intelligence
AI-Generated Summary
Key Takeaways
- ✓Remote Control (Claude Code): Start a Claude Code terminal session on your desktop, then continue directing it from your phone via URL or QR code. The session runs entirely on your local machine — accessing your file system, MCP servers, and configs — while mobile acts purely as a window. Use slash-RC to switch mid-session without restarting.
- ✓Dispatch (Claude CoWork): A single persistent conversation thread on your phone that spawns and manages multiple simultaneous CoWork or Claude Code sessions on your desktop. One user directed roughly 25 minutes of async instructions across a full day, generating over three hours of parallel Claude execution — competitor analysis, Notion pages, infographic iterations — without sitting at a desk.
- ✓Computer Use: Claude can now control mouse, keyboard, and screen inside Claude CoWork, operating any desktop application without API integration. This makes it viable for legacy enterprise software with no native AI connectors. Combined with Dispatch, Claude can execute multi-app workflows autonomously while you are physically away from the machine.
- ✓Channels (Claude Code): Connect external event sources — Sentry alerts, CI failures, webhook payloads, Telegram or Discord messages — directly into a running Claude Code session. Unlike chat, channels push events in from outside, enabling Claude to react autonomously to monitoring triggers without user initiation. Designed for developers wanting a fully hackable, programmable event pipeline.
- ✓Scheduled Tasks: Claude CoWork and Claude Code both now support recurring scheduled tasks. Local schedules run while your machine is awake; cloud-based schedules run on Anthropic infrastructure with no local dependency. Practical use cases include sweeping open PRs, analyzing overnight CI failures, syncing documentation after merged PRs, and generating weekly spreadsheet updates automatically.
What It Covers
Anthropic released five major Claude upgrades over roughly one month — Computer Use, Dispatch, Remote Control, Channels, and Scheduled Tasks — collectively shifting Claude from a chat tool into a persistent, always-on orchestration layer that executes multi-hour workloads autonomously across devices while users are away from their desks.
Key Questions Answered
- •Remote Control (Claude Code): Start a Claude Code terminal session on your desktop, then continue directing it from your phone via URL or QR code. The session runs entirely on your local machine — accessing your file system, MCP servers, and configs — while mobile acts purely as a window. Use slash-RC to switch mid-session without restarting.
- •Dispatch (Claude CoWork): A single persistent conversation thread on your phone that spawns and manages multiple simultaneous CoWork or Claude Code sessions on your desktop. One user directed roughly 25 minutes of async instructions across a full day, generating over three hours of parallel Claude execution — competitor analysis, Notion pages, infographic iterations — without sitting at a desk.
- •Computer Use: Claude can now control mouse, keyboard, and screen inside Claude CoWork, operating any desktop application without API integration. This makes it viable for legacy enterprise software with no native AI connectors. Combined with Dispatch, Claude can execute multi-app workflows autonomously while you are physically away from the machine.
- •Channels (Claude Code): Connect external event sources — Sentry alerts, CI failures, webhook payloads, Telegram or Discord messages — directly into a running Claude Code session. Unlike chat, channels push events in from outside, enabling Claude to react autonomously to monitoring triggers without user initiation. Designed for developers wanting a fully hackable, programmable event pipeline.
- •Scheduled Tasks: Claude CoWork and Claude Code both now support recurring scheduled tasks. Local schedules run while your machine is awake; cloud-based schedules run on Anthropic infrastructure with no local dependency. Practical use cases include sweeping open PRs, analyzing overnight CI failures, syncing documentation after merged PRs, and generating weekly spreadsheet updates automatically.
Notable Moment
A developer built a custom iOS app to orchestrate Claude Code sessions across Docker containers, VMs, and local machines — just four days after Channels launched. The speed from feature release to functional custom orchestration infrastructure illustrated how composable these new primitives are for technical users.
Episode Transcript
Today on the AI Daily Brief, how to use all of Claude's massive new upgrades. The AI Daily Brief is a daily podcast and video about the most important news and discussions in AI. Alright, friends. Quick announcements before we dive in. First of all, thank you to today's sponsors, recall dot ai, Assembly, PromptQL, and Blitsy. To get an ad free version of the show, go to patreon.com/aidailybrief, or you can subscribe at Apple Podcasts. To learn about sponsoring the show, send us a note at sponsors@aidailybrief.ai. We are getting very close to full with q two spots. So if you're promoting, for example, a launch or anything in the near future, it is definitely a good time to reach out. Now, one more note on today's show. Yesterday was kind of a big politics and society episode. Today, we're running all the way in the other direction with something a lot more practical. There have been so many new things that have come out for Claude Code and Claude Cowork that it was time to go through them all, and and it ended up running quite long, so we will end up not doing the headlines today. We will be back with a normal headlines episode tomorrow. Two more things to quickly flag before we get into that. First, agent madness is live. The round of 64 is going. Hundreds of you have voted, and voting will close for this first round at the end of the day on Thursday, March 26. So go to agentmadness.ai to check that out. And finally, I'm noticing that I'm doing a lot more little companion experiences with these episodes. And so as of today, we're launching play.aidailybrief.ai, which is where all of those fun little experiences live. So for example, today, you can find the checklist of things to try with Claude right now, and again, that'll live at play.aidailybrief.ai. With all that out of the way, let's talk about all the cool new things you can do with Claude. Every other day or so for the last month, there has been some part of the headlines where Claude launched some new feature or upgrade for Claude Code or coworker or some other part of the Claude ecosystem. And at this point, it has officially gotten to the point where we needed to do a full on retrospective of everything that has launched over the last month or so to help you guys map out and figure out how to use all of these big new upgrades. Now, of course, this comes in a specific lineage of updates. Step one was the models. The Opus four five g p t five two generation of models that came about at the end of last year catapulted us into a new capability era that Opus four six g p t five three codecs and g p t five four have continued. Step two, of course, was the unlock that OpenClaw represented. It was …
Get the full transcript (5,251 words) + summary by email — free
One-time email with the complete transcript and AI summary of this episode. No account needed.
One email, no spam. We’ll also show you what SignalCast does.
You just read a 3-minute summary of a 22-minute episode.
Get The AI Breakdown summarized like this every Monday — plus up to 2 more podcasts, free.
Pick Your Podcasts — FreeKeep Reading
More from The AI Breakdown
The Right Way to Worry About AI
Aug 7 · 28 min
20VC (20 Minute VC)
20VC: SpaceX Soars to $2.7TRN | Anthropic's Fable Banned by US Government | Wix and Adobe Hit All-Time Lows | Mistral Raising at $20BN and The Case for Sovereign Models | Fin Acquired by Salesforce for $3.6BN
Jun 18
More from The AI Breakdown
Google’s AI Leadership Shakeup: Disaster or Exactly What It Needs?
Aug 6 · 33 min
20VC (20 Minute VC)
20VC: Cursor Acquired for $60BN by xAI | Anthropic Hits $1TRN in Secondary Markets | Did Anthropic Just Kill Figma, Adobe and Canva | Rippling Hits $1BN in ARR | Salesforce Goes Headless: Smart or Stupid | Cerebras IPO 2.0
Apr 23
Books, tools, and gear mentioned in this episode
SignalCast may earn commission on purchases via these links.
Tools
by Anthropic
“Claude can now control mouse, keyboard, and screen inside Claude CoWork, operating any desktop application without API integration.”
by Anthropic
“Dispatch (Claude CoWork): A single persistent conversation thread on your phone that spawns and manages multiple simultaneous CoWork or Claude Code sessions on your desktop.”
by Anthropic
“Anthropic released five major Claude upgrades over roughly one month — Computer Use, Dispatch, Remote Control, Channels, and Scheduled Tasks — collectively shifting Claude from a chat tool into a persistent, always-on orchestration layer.”
by Anthropic
“Remote Control (Claude Code): Start a Claude Code terminal session on your desktop, then continue directing it from your phone via URL or QR code.”
More from The AI Breakdown
We summarize every new episode. Want them in your inbox?
The Right Way to Worry About AI
Google’s AI Leadership Shakeup: Disaster or Exactly What It Needs?
Why the Data Center Fight Has Little to Do With AI
Why AI Washing Won’t Work Much Longer
What Happens When AI Breakthroughs Outrun Human Understanding
Similar Episodes
Related episodes from other podcasts
20VC (20 Minute VC)
Jun 18
20VC: SpaceX Soars to $2.7TRN | Anthropic's Fable Banned by US Government | Wix and Adobe Hit All-Time Lows | Mistral Raising at $20BN and The Case for Sovereign Models | Fin Acquired by Salesforce for $3.6BN
20VC (20 Minute VC)
Apr 23
20VC: Cursor Acquired for $60BN by xAI | Anthropic Hits $1TRN in Secondary Markets | Did Anthropic Just Kill Figma, Adobe and Canva | Rippling Hits $1BN in ARR | Salesforce Goes Headless: Smart or Stupid | Cerebras IPO 2.0
Pivot
Apr 14
Pope's Pushback, Orban's Concession, and Bessent's Anthropic Warning
Hard Fork
Apr 10
Anthropic’s Cybersecurity Shock Wave + Ronan Farrow and Andrew Marantz on Their Sam Altman Investigation + One Good Thing
This Week in Startups
Apr 9
Anthropic’s Mythos is a cyber-weapon, so you can’t have it | E2273
Explore Related Topics
This podcast is featured in Best AI Podcasts (2026) — ranked and reviewed with AI summaries.
Read this week's AI & Machine Learning Podcast Insights — cross-podcast analysis updated weekly.
You're clearly into The AI Breakdown.
Every Monday, we deliver AI summaries of the latest episodes from The AI Breakdown and 192+ other podcasts. Free for one show.
Start My Monday DigestNo credit card · Unsubscribe anytime