Lately I’ve been trying to improve my entire YouTube video creation workflow. Not just “come up with better ideas,” but the whole process: Idea → research → script notes → video structure → post-production → retrospective after publishing. The main problem I kept running into was context switching. So I built a small workflow web app to bring the whole video creation process into one place. Inside the app I can track: - Quarterly YouTube goals - My target audience - My value proposition - New video ideas - Active video projects - Core research findings - Script notes - Segment structure - Published videos - Post-upload retrospectives - Audience feedback I am excited to see how the retrospective flow goes. After a video is published, I can come back and review what worked, what didn’t, what the audience responded to, and what I should improve for the next upload. I don’t just want to publish more. I want the videos to actually get better. For the build, I used Next.js and built most of this as a background project while working on other things. I also used Superpowers, and honestly, it worked really well for this kind of workflow app because I already had a clear idea of what I wanted. Sometimes the best AI projects are small internal tools that remove friction from a workflow you already do every week. I may put this on GitHub after I clean up a few more things. What do you guys think: What workflow do you currently have that would be better if it was turned into a small web app? And where are you still bouncing between too many tools?

Hi brandon, Thank you so much for sharing this incredible resource. I am currently automating different carrier portals and thanks to your video i was able to fetch rates without using API. The only challenge is that my setup is really slow and doing it manually is even faster, do you have any tip on how to make this process faster?

I’ve been thinking about how easy it is to get stuck in the building phase. You have an idea → open ChatGPT or Claude → start coding → add another feature → tweak it for three days → suddenly you have a very impressive unfinished project. 😂 What’s helped me is keeping the process ridiculously simple: Find the problem → Build the MVP → Get it in front of people → Improve → Sell For the actual workflow, I’ve been using ChatGPT / Claude to work through product ideas and development, Floment to break the project into tasks and keep the execution moving, and automation tools wherever there’s repetitive work worth removing. The important part is not building the most technically impressive AI product. It’s building something someone actually wants. A simple product solving a painful problem will always be more interesting than a sophisticated demo nobody needs. And I think that developer → business owner transition is where things get really interesting. You have to start thinking about the audience, positioning, sales, delivery, and retention, not just whether the code works. For anyone here building an AI product right now, where are you spending most of your time? Finding the problem, building the product, or figuring out how to sell it?

✅ What does “done” look like for you this Friday? Comment below with: - Project: - Done means: - Not included this week: - Likely blocker:

🛠️ What is one problem stopping your project right now? 🤔📝 Post one blocker using this format: - I’m trying to: - I’m blocked by: - I’ve already tried: - A useful answer would help me: Keep it focused. If you can help someone, offer one practical next step or ask a question that makes the problem clearer.