Drop your Instagram, LinkedIn, Facebook, X, YouTube, or wherever you're most active in the comments so we can stay connected and support each other's journey. And while you're at it, answer this: What's one thing you're building, learning, or excited about right now? I always enjoy seeing what members of this community are working on, and it's a great way for all of us to stay connected, share ideas, and celebrate wins together. Looking forward to connecting with you all!

Following my challenge of semantically grouping 1000+ records I now have a follow-up challenge where I need to cluster a sub-set of the semantic relevance output. As before my current scenario appears limited to processing a few hundred records. (In the video, I show how it processed 238 just 7 days ago and made me think it's done and dusted). But I just tried using the same scenario to process 1300 records and the agent didn't even try; it processed 0 records (effectively giving up before it even began). So this time I want to be proactive and not get myself in the mess that caused me to consume 17000 credits in less than an hour! Thanks to @Aashiya Bi for helping me come up with a 2-part scenario I think will work for large-scale semantic relevance processing. But how do I do something similar for this follow-up scenario. What do I need to change to my current scenario or LLM so that the scenario can execute. Any ideas up front will be most welcome. cc. @Mohamed Jahar

OMG! Did I just get burned. Easily my biggest ouch in the 18 months I've been using Make. I apologise in advance for the poor quality video, (a lag between my voice and screen) but hope you can hear my frustration and start to see my problem. In a nutshell, how do you get a scenario to process batches (of Airtable data) and then end cleanly when it's iterated through all the records. Alternatively, what AI Agent or AI model/LLM could I use (via OpenRouter) that would process 1000s of records). That would be the easiest solution.

Just drop one word in the comments: WordPress, Shopify, Webflow, Wix, Framer, Custom, or None Let's see which platform wins. 🏆

The Problem: Busy professionals spend 1+ hour daily replying to emails. Most replies follow predictable patterns - same tone, same structure, yet still get written manually one by one. The Solution: Connect Gmail to Claude, teach it your writing style as a reusable Skill, and let it draft replies automatically every morning. How It Works: 1️⃣ Connect Gmail - Use the official Gmail connector in Claude Desktop (Customize → Connect Your Apps → Gmail). 2️⃣ Create a Skill from your writing style - In a new chat, prompt: "Go through my emails from the last 30 days, learn how I reply, and turn that into a skill." Claude reads your sent mail and extracts your patterns - greeting style, tone, length, sign-off, even how you negotiate or escalate. 3️⃣ Save the Skill - Claude packages everything into a .skill file. Click Save Skill and it's stored permanently. This is the key step: a Skill is a reusable instruction file Claude loads automatically whenever it's relevant. You build it once, no re-explaining your style in every chat. 4️⃣ Schedule it - In Claude Cowork, create a daily scheduled task: "Go through all of my unread emails every day at 8 AM and draft responses using my Gmail reply skill." The Result: Every morning, draft replies are waiting in your Gmail Drafts folder — written in your voice. You review and send in minutes instead of an hour. Why Skills Matter Here: Without a Skill, Claude drafts generic replies. With a Skill, every draft sounds like you and the same Skill works across future automations too (follow-ups, client updates, proposals). Key Design Decision :Keep it draft-only. Nothing is auto-sent without review. Approving a good draft takes seconds; an auto-sent bad reply can damage a client relationship. Setup time: ~10 minutes | Tools: Claude (Pro) + Gmail | Code required: None