Every Monday, same question. What are you building this week? Drop a comment below. One line or ten — doesn’t matter. Show the thing you’re working on. Ask a question. Share a blocker. If you’re stuck, say where. Someone here has probably been stuck in the same place. Here’s the format if you want structure: 🔨 Building: [what you’re working on] 🧱 Stuck on: [what’s blocking you — or “nothing, making progress”] 💡 Tip from last week: [one thing you learned that others might find useful] You don’t have to have something finished. You don’t have to have something impressive. You just have to show up. The builders who get the most from this community are the ones who post before they have all the answers — not after. Reply to someone else’s comment if you’ve solved what they’re stuck on. That’s the whole point of this place. This thread resets every Monday. See you here. 🚀

I came across a post about a fencing company that built an automated lead generation system. 3 to 7 qualified appointments every single day. Automatically. I thought — what if I built the same thing for flooring businesses? So I did. In a few hours. Watch the video. Here's what it does: → Customer uploads a photo of their room → Sees exactly how the new floor looks — before and after → Gets an instant price range → Receives an SMS + email automatically → Books a consultation in one click The sales team gets every lead in real time with full details. No phone tag. No waiting. No lost customers. Built with Lovable AI + Supabase + Twilio + Resend + Calendly. Now here's the part I'm excited about — This week I'm doing cold outreach to real flooring businesses with this demo. I'm going to try to close an actual client and document everything. The wins, the rejections, the lessons. I'll share it all here. So tell me — do you think a flooring business would pay for something like this? And what other industries would you build this for? Drop your answers below 👇

Our benchmarks show it completes tasks in 40% fewer turns, making it more efficient. Lovable builders get discounted rates through April 30, so you’ll see your credits go even further.

I realized I only want to share this with the 1,000 of you in here. You are the real builders. You are the ones actually putting in the work. So, to my Skool family: I need to make a confession. For years, I was the guy buying the dream. Affiliate marketing, dropshipping, agency building… you name it. I bought the courses from the 'gurus', tried every trick, and ended up exactly where I started: stuck. I was working in a family business that felt like a cage. My wings were clipped. But I had a wife and two kids at home relying on me. Leaving wasn’t just risky; it was terrifying. But then reality hit. Hard. I live in Israel. With the massive war going on right now, the constant tension, and the whole region shaking... it does something to you. It puts things into perspective. You wake up realizing that life is entirely too fragile and unpredictable to spend it trapped in a job you hate, waiting for 'someday'. That upheaval made me sick of all the BS. The whole system is rigged. Tech monopolies charge us thousands for basic SaaS tools, and fake gurus sell us outdated playbooks just to line their own pockets. So, I made the scariest bet of my life. I walked away from the family business, bet absolutely everything on AI, and decided to do the exact opposite of the gurus. I’m not here to sell you a secret. I’m here to arm you. ⚔️ We are going to build the tools that replace the expensive SaaS companies, and I am going to give you the exact blueprints to do it. Will I make mistakes? 100%. Just last month, I built a system for a client, the database completely freaked out, and wiped their test data. Total chaos. 🤦‍♂️ I’m a builder, and builders break things. But I’m learning, I’m scaling, and I want to take all of you with me. Here is my challenge to you (and my promise): Starting next week, I am building a brand new AI Micro-SaaS from scratch in public. My goal is to scale it to a 6-figure run rate using only Vibe Coding. I don't know if I'll hit it, or if I'll crash and burn. But I am documenting every prompt, every failure, and every win RIGHT HERE.

Most people blame Claude for strict limits. I blamed Claude too. Recently I realized that Claude doesn't count the number of messages. it counts tokens. All you need to do is use tokens wisely, but not everyone knows how to do that and ends up losing a lot of tokens and money as a result. I got really into this and put together a list of the best habits that will save you a ton of tokens. 1. Edit your prompt. Don't send a follow-up When Claude doesn't get your thoughts right, you might feel tempted to send: 1/ “No, I meant [your message]” 2/ “Ugh, that's not what I wanted [your message]” and so on Don't do that! Every subsequent message is added to the conversation history. Claude re-reads ALL of it every turn - burning tokens on context that didn't even help. Token cost per message = all previous messages + your new one. Total = S × N(N+1) / 2 (S = avg tokens per exchange, N = message count) At ~500 tokens per exchange: 5 messages: 7.5K tokens 10 messages: 27.5K tokens 20 messages: 105K tokens 30 messages: 232K tokens Message 30 costs 31x more than message 1 Instead: click Edit on your original message → fix it → regenerate. The old exchange gets replaced, not stacked. 2. Start a fresh chat every 15–20 messages In the previous section, I showed how token costs grow with every message. Ideally, you should start a new chat every 15–20 messages. Now imagine a chat with 100+ messages. At ~500 tokens per exchange, that's over 2.5 million tokens burned - most of it just re-reading old history. One developer tracked his usage and found that 98.5% of tokens were spent on re-reading the history. Only 1.5% went toward actually outputting the result. When a chat gets long → ask Claude to summarize everything → copy it → new chat → paste as first message. 3. Batch your questions into one message Many people believe that splitting questions into separate messages leads to better results. Almost always, the opposite is true. Three separate prompts = three context loads.