Everyone's asking the same question this week: does Claude Routines kill n8n? Short answer: it's the first real 1-to-1 replacement — but that doesn't mean you should rip out n8n tomorrow. Here's the breakdown. https://www.youtube.com/watch?v=j3aXJNu9804 What's the same: - Event-driven (schedule, webhook, or API trigger) - Connectors for Gmail, Slack, GitHub, etc. - Outputs to downstream platforms (CRM, DB, Slack, email) What's different: - n8n: You build the middle logic with drag-and-drop nodes. Credentials, mappings, field variables — hours of work. - Claude Routines: You describe the logic in natural language. No nodes. No mappings. The agent figures out the path. Pick n8n when: - You're running high-volume, deterministic ETL (compute is cheaper than tokens) - The flow has complex branching with strict rules that must execute the same way every time - You're moving large amounts of structured data between systems Pick Claude Routines when: - It's knowledge work — drafting, summarizing, researching, proposing - You expect to modify the flow often (editing via prompt beats re-wiring nodes) - It's a new build you'd rather not spend 2 hours wiring up - The logic is something a human could describe in 3 sentences The real verdict: Routines don't kill n8n — they kill the reason you reached for n8n for 80% of knowledge tasks. Keep n8n for the deterministic pipes. Use Routines for anything where an agent's judgment adds value. Discussion: What's a flow you're keeping in n8n no matter what? And what are you moving to Routines this week?

If you've been hearing about Claude Routines but haven't actually set one up yet, this is your no-fluff walkthrough. By the end you'll have a routine that checks your inbox every morning and Slacks you drafts before you wake up. Watch the full demo first — then use the checklist below as your copy-paste guide: https://www.youtube.com/watch?v=j3aXJNu9804 Prereqs: - Claude Pro/Max or Claude Code access - Connectors set up for whatever apps you're hitting (Gmail, Slack, etc. — add these at Claude Code Settings → Connectors) The 6-step setup: 1. Go to claude.ai/code/routines → click New Routine (top right) 2. Name it — something specific like morning_inbox_drafter 3. Write the prompt like an SOP. Be more precise than a normal skill — routines run hands-off with no steering. Example: "Pull all unreads from the provided Gmail connector. For each unread, check for prior conversations with that contact and pull them for context. Draft replies based on what you know about me. When done, use the Slack connector to DM me a summary with each draft." 4. Pick your model (Opus 4.6 1M is Nick's pick for context-heavy flows) 5. Choose a trigger: Schedule → visual picker, hourly/daily/etc. (best for recurring stuff) Webhook → fires from an external event API call → triggered by another system or agent 6. Attach connectors (Gmail, Slack, whatever the prompt references) → hit Run Now to test Pro tips from the video: - Routines run without you watching — so lock down the prompt. Fewer edge cases = fewer silent failures. - Use the calendar view on the Routines page to see everything that's about to fire today. - You can stack multiple triggers on the same routine (schedule + webhook). Your turn: What's the first routine you're building? If you want feedback on your prompt before you schedule it, paste it below and the group can pressure-test it.

If you've spent hours building n8n flows, the idea of rebuilding them from scratch in Claude Routines probably sounds brutal. Good news — you don't have to. Nick Saraev just dropped a walkthrough showing the exact port-over method. Watch this first, then I'll break down the steps: https://www.youtube.com/watch?v=j3aXJNu9804 The 3-step migration: 1. In n8n, hold Shift + right-click your workflow → Copy. You now have the full workflow as JSON on your clipboard. 2. Open Claude Code, paste the JSON, and prompt: "Use the routine generator to turn this n8n workflow into a routine." 3. Claude reads the nodes, connections, and logic — then rebuilds it as a natural-language routine with triggers and connectors wired up. That's it. A scraper workflow that took 2–3 hours of node-dragging becomes a routine in under a minute. When to actually migrate (and when not to): - ✅ Migrate if you're maintaining the flow often, or it's simple enough that tokens cost less than your compute + time. - ❌ Don't migrate high-volume data-shoveling flows. Tokens > compute for pure ETL work. - ✅ Best use: new builds you'd otherwise wire up in n8n. One-shot them as routines instead. Question for the group: What's the first n8n flow you'd port over? Drop the use case below — curious which ones people are prioritizing.

Hey Squad! I just uploaded a quick demonstration of the new Google Gemini Auto-Browse feature inside Chrome, and honestly, the potential here is wild. 🤯 We all know the struggle of automating sites that don't have an API (or have a limited one). In this video, I test out using Gemini’s agentic layer to handle my daily Skool checks for me. In this demo, you’ll see: - 🤖 Navigation: Gemini logging in and finding our specific community. - 👀 Detection: Scanning for new comments that need a reply. - ✍️ Interaction: Drafting and posting a response directly to a member—hands-free. It wasn't perfect (it missed the "like" button on the first try), but for a tool that can learn and execute "human" browsing tasks while you work on other things, it’s a game-changer. Watch the full demo here: https://www.youtube.com/watch?v=gzYiG0zgw8Y How are you guys using these new agentic browser features? Let me know in the comments! 👇

A lot of times I see these images on LinkedIn and X and don’t necessarily agree with the tools they feature. Many of them are usually outdated or ones that I’ve tried and not really liked. But this one has some pretty good tools on it and my opinion! So I figured I’d share for everybody!