Hey everyone, I wanted to share a bit of my background and ask for some advice from people who are already running AI automation agencies. I’ve been working as a freelancer for a while, mainly building AI automations and voice agents. On Upwork I currently have a 100% Job Success Score with 5-star reviews, and most of my projects have involved building automation systems and AI-based solutions for clients. Recently I also started a YouTube channel where I showcase the systems I build (voice agents, automations, workflows, etc.) so people can see the actual implementations. Now I’m planning to start my AI automation agency next month. Initially, my main focus will be AI voice agents for clinics (AI receptionists, call handling, appointment booking, etc.), because it’s easy for businesses to understand the value. After that, I plan to gradually expand into other automation areas like lead generation systems, workflow automation, and content automation, since I also have experience with those. Right now my main questions are around pricing and infrastructure. Until now as a freelancer, I’ve always built systems directly on the client’s platforms (their Twilio, Vapi, OpenAI, etc.) and just charged a setup fee. But now that I’m moving toward an agency model, I’m wondering what the best approach is. A few things I’d really appreciate advice on: • Do you usually build on the client’s platforms or run everything on your own infrastructure? • For someone starting an agency, would you recommend continuing with client-owned accounts for the first few clients, or moving to agency-owned infrastructure from the start? • How do you typically structure pricing setup fee only, or setup + monthly maintenance/retainer? Another thing I’m unsure about is monthly maintenance. If I charge a monthly maintenance fee: - Is that something you keep indefinitely as long as the client stays? - Or do you structure it like a limited support period or contract (e.g., 3–6 months)?

Hi everyone! I'm trying to implement AI Agent logging in n8n based on this tutorial: https://youtu.be/vVdS-ZEFf50?si=eFIw-W-PDVrfZb0b&t=157 Even though I've enabled the 'Return Intermediate Steps' option, the output still only returns the basic response. The detailed token usage and intermediate steps aren't appearing in the output data at all. Has anyone else encountered this issue? Is there a specific expression or perhaps an additional Code node required to properly extract these JSON fields? Thanks for the help!

What a journey over the past 16 weeks, our students in Uganda have been put through an intensive AI program as part of our work with Jack's Secret Food Group. The results are in now and they are impressive and amazing !! Top scores of 96.0 and 80.0 out of 100 for the last assignment, with multiple perfect test results along the way. That's not just passing that's excelling. But this was never just about scores, it was about AI readiness. Readiness to take the next step. And that step is now!! We're moving from evaluation into real AI automation business building. Together with our team in Uganda, we're setting up operations for Jack's Secret, developing solutions, and turning potential into impact. This is where it gets real. And for those still growing? We don't leave anyone behind. We keep building, keep coaching, and keep raising the bar together!! To top it off: next week, two new students will join the program, bringing fresh energy and new perspectives to the team. The momentum is only growing. A special thanks to Bauke Dekker, founder of Jack's Secret Food Group, for his unwavering support and belief in these amazing people. Together we are committed to creating real opportunity and building something meaningful from the ground up. The business ideas they brought to life in the last month will be a starting point. This is what development looks like. Not just training, but creating real skills, real business, and real futures. Proud of this team. Excited for what's next. If you want to know more just leave a comment

Having an online store is honestly one of the biggest business advantages of this generation. With a physical store, you’re thinking about rent, electricity, staff, and hoping people walk in. With an online store, your “location” is the internet. You can literally sell to someone in Miami while you’re relaxing at home and your store is still open. No closing hours. No geographic limits. No ceiling on how far you can scale. A physical store serves one area. An online store can serve the world. That’s leverage. That’s power. And the crazy part? Most people still think you need a fancy building to build a serious business. You don’t. You need strategy, consistency, and the willingness to treat it like a real company, not a side hustle experiment. If you’re building or thinking about starting, don’t underestimate how big this opportunity really is.

🚨 Big question for the AI builders and automation community: With the launch of Claude’s remote-control capability, AI can now operate tools, execute workflows, and interact with systems more independently than ever before. Does this mark the early phase of AGI, or is it simply a powerful step toward more advanced automation? Where do you draw the line between autonomous agents and true AGI? Curious to hear your perspective—especially from those already building with AI agents and workflow automation. 👇?