Hey everyone. I want to pick your brains. I have a Claude OS built for myself and my consulting business using local .md files that save memory and provide instructions and context to Claude (using Cowork and Code). It works great! I'm seeing the changes that are coming from Claude that move things into the cloud and the launch of tools like Duet and am wondering if I should consider a different way to run my personal OS without using local .md files. I'm wondering if I would get more value out of Claude when working on mobile and through Duet if my instructions, context and memory were accessible beyond my computer. Has anyone had success with this considering the direction Claude is taking the product? I have .md files that orchestrate, explain my brand, my voice, my orderings, my projects, etc. Just not sure how to replace those in the cloud... If it's possible. As I said, I'm very happy with my system. I'm just wondering if this is an old school way of building Claude OSs. I also want to be able to guide my clients on how to future proof their set ups.

Hey everyone, just wanted to give a quick shoutout to @Rudransh Chouhan. A few weeks ago I put a post up in the community to have someone build me a website for my new agency in exchange for a testimonial. I got a lot of offers from many people, but I decided to give Rudransh a chance considering he was still looking to build his portfolio of work. It turns out I made the right choice. I was very impressed with how cooperative he was and how willing he was to make sure the website would turn out exactly how I would want. He used color schemes, templates, and logos I gave him and was able to return me the full HTML source code in a ZIP file just as I requested. As promised, I gave him his quick video testimonial, but was also impressed by his work and wanted to give him a shoutout in the community. Rudransh is only 14, but he is already ahead of the curve with his eagerness to work and his projects. I definitely would recommend his service if you need a website or landing page built. I haven't really seen any other post in the community where people get praised for their work, so hopefully this could be the first of many so that we can build relationships for work within the community.

I’m a fresh software engineering graduate trying to start an AI automation agency, but I’m struggling to figure out what to sell. Starting a startup has always been my dream. I want to build something of my own, get my first clients, and eventually turn it into a real business. I decided to explore AI automation, targeting local businesses in the US, particularly HVAC companies. But the more I research, the more confused I get. Here’s what I’m struggling with: Most HVAC businesses already use tools like ServiceTitan, Housecall Pro, Jobber, and others. These platforms already offer scheduling, follow-ups, customer management, and many other automations. So what am I supposed to sell them? - Lead follow-up automation? - Missed-call recovery? - AI receptionists? - Automated booking and customer communication? - These sound useful, but established software already handles many of these problems. I’m struggling to find a genuine gap where I can provide real value instead of rebuilding something that already exists. I’ve been researching businesses, looking for problems, and building demos to show potential clients. But sometimes, I feel like I’m building solutions that businesses don’t actually need. And convincing a cold prospect to buy something they don't think they need feels almost impossible, especially through cold emails and DMs. Here’s a little about my background: I’m a fresh software engineering graduate. I can build full-stack applications using technologies like FastAPI, PostgreSQL,, LangGraph and more. I use AI coding tools heavily, but I understand the code, architecture, and systems I’m building. I’m not limited to basic no-code automations. I can build custom AI agents, backend systems, and complete applications if there’s a real problem worth solving. So, I have a few questions for people who are already doing this: 1. Am I approaching the AI automation business model the wrong way? 2. Are basic automations actually selling well, or are people just hyping them up online? 3. How do you find problems that businesses will genuinely pay to solve? 4. Should I stick with AI automation, explore custom software development, or combine both?

Hey everyone, I'm not the only person in this community who thinks the AI Operating System (layering a business into an AI platform and merging humans with AI agents for business processes) is the next big thing that will become somewhat standardized in medium to large-size businesses. Currently, you can create your own with Claude Code, Codex, or use cloud apps like Kylon or Hyperagent that onboard you. Recently, both OpenAI and Google have released their own version of an AIOS (no onboarding yet and not super personalized). OpenAI's Dots platform is perfect for businesses to streamline their workflows through, and Gemini Agent is already used by so many big enterprises and companies that use Google services. Anthropic's Cowork is alright as well, but it doesn't have all the same features for an AIOS (no data or shared context layers). If these big AI labs that everyone already uses for basic chats will also create AIOS platforms for businesses, then what can we expect going forward? I'm curious to hear what you guys think about this in terms of how it will influence the AI for business industry and what will it mean for AI agency owners in terms of what how they will have to adapt their services to fit these kinds of platforms.

Hey everyone, my website is now live: https://tracksideaisystems.com I'm building Trackside AI Systems, an AI text-message assistant for automotive service shops (detailing, tint, wraps, PPF). It answers leads, handles pricing and availability questions, and moves people toward booking, so shops stop losing customers when staff are busy. I built the site with Claude Code, React, Tailwind and Motion, and it's hosted on Cloudflare Pages. I'm a high school senior working on this alongside school. I'm open to any tips, especially on: - Clarity: does it explain what Trackside does within a few seconds? - Design and mobile experience - Anything that feels confusing or unconvincing to a shop owner If you've landed a first client for a service business, I'd love to hear how you found them and what worked in outreach. Thanks in advance. Be honest, I can take it.