Anthropic just dropped managed agents and routines. Everyone's asking "does this replace n8n?" Short answer: no. Here's why. Routines are time-based only. No webhooks. No event triggers. Research preview. The Register called them "mildly clever cron jobs." Managed agents? Powerful — but single-task. No multi-tenant awareness. No version tracking across clients. No rollback. So what actually happens in a real agency stack: → n8n for event-driven workflows → Claude routines for scheduled reasoning → Make for the stuff already wired up → Custom scripts for edge cases → GHL sub-accounts held together with prayer → Now managed agents on top of all of it 6 dashboards. Zero shared view of what's actually running. Every new tool solves one problem and adds another integration to maintain. The issue was never which tool — it's that nobody's tracking what's running across all of them. DM me if you're hitting the scaling wall — I'll help you map the fix.

Hey, I based in London. For fun, I like to go to concerts, listen to music and cook a nice meal to fuel my day!

Not a demo a real working bot. It can: • Auto-reply to messages like “hi”, “price”, “help” • Track conversations in real time • Show live stats + active rules • Run completely on autopilot Built using Claude Code I simply described the system, and it generated the frontend, backend, logic, and database. This isn’t about “no code tools.” It’s about how clearly you can think and instruct AI. Most people struggle here not because of tech, but because they don’t know what to tell the AI. 💬 Comment “BOT” and I’ll share the exact prompts + process I used

🔥 Just finished my 1st AI animated short. Would love your thoughts. "The Beast That Feared a Tiny Firefly: Luma's Brave Journey" The reference frames and a few shots were made using Google Flow, and the maximum scenes were made using OpenArt.ai. Everything from the bioluminescent forest to the Shadow Beast was generated through prompt engineering. A few things I'm still figuring out and would love feedback on: → Fighting scenes- struggling with it. → The emotional pacing — does the ending land for you? → Anything about the visual style that feels off For most of the scene prompts, I used a 6-part prompt formula [Subject + Action + Setting + Camera + Style + Audio] with reference images method between clips to keep the world consistent.

Hey all, im a 23 year old computer science graduate, in love with AI automations and voice agents… not sure where to start!