Here’s something that’s been sitting on my mind. We’re in a moment where a lot of people are saying learning to code is no longer necessary. That AI can just write the code for you. And on the surface, that argument sounds reasonable. But I think it misses something fundamental about how software actually works. The abstraction stack has always looked like this: Natural Language → [AI translates] → High-Level Code (Python, JS) → [compiler] → Assembly → [CPU] → Machine Language This is the same pattern software has always followed. We went from punching machine code, to assembly, to C, to Python. Every layer up was an abstraction that made the layer below more accessible. AI is simply the next one. You can now describe intent in plain English and get working code back. That’s powerful. That’s genuinely a shift. But here’s what hasn’t changed: The AI still produces code. That code still runs on software engineering principles, and neglecting those principles is just like pushing code that’s never been vetted. Same same, but different. If you can’t read what it produces, you can’t evaluate it, debug it, extend it, or know when it’s wrong. Think about it you wouldn’t trust a translator if you had no idea what language they were translating into. Same logic applies here. And here’s the honest truth: learning a programming language alone isn’t enough right now, because AI is doing that part better by the day. What actually matters is the engineering fundamentals. They teach you how to think in terms of logic, data flow, state, and structure. Those aren’t things AI removes from the equation they’re the things that help you direct AI well. So do we still need to learn to code? My take: software engineering fundamentals are non-negotiable. Understanding how code works, what a function does, what an API call is, how data moves through a system these matter more now, not less. You need to be a good reviewer of AI output. And knowing the fundamentals lets you govern what AI writes and how it writes it throughout the entire development process.

The perspective shift this community facilitates is invaluable. Understanding better prompts are good, but not nearly as valuable as giving Claude proper skills/rules to define it's purpose, cannot be stated enough. With that being said, I'm just starting out and realize I don't even know the right questions to ask when approaching solutions. For example, let's say I'm creating a social content creator automation, but my knowledge in growing a tiktok audience is lacking-nonexistent. How do I shape skills or give better rules to Claude, when I don't know myself? Prompts will only get me so far. Is there a resource that goes over this or teaches this? Or is it more just like, "practice makes perfect?" How have you solved the ignorance hurdle when developing automations?

Most people think they have an AI problem. What they actually have is a packaging problem. You don’t need to become a developer to use AI effectively. This guide breaks down the real “code” behind better results: prompts, skills, connectors, MCPs, hooks, scripts, and plugins — and shows you exactly when (and why) to use each one. Check it out in Davids Corner: https://www.skool.com/cliefnotes/classroom/c7f102c7?md=9a0d198e1c0140578f37f1c93873c2b6

OK, maybe not all of them, but for the most part you should be able to eliminate 90% I stumbled across this old blog post from the creator of PI AI (https://pi.dev/) and it's genius. It shows you how to easily remove the common web browser MCP's and replace with code. WHY ? - Because when you run executable code you no longer need to use the complex MCP queries which are typically bloat for all use cases, it simply runs the code. 1 line. What You need, not what 1million users need. Unfortunately it was about a week late, I could have used this a week ago as I was having trouble scraping epic-games for Unreal Engine documentation. I tried a number of different scrapers, Skill-Seekers, one I built for SEO about 5 months ago... and then decided to use Firecrawl, however I had to pay for it as it's over 6000 pages. So $36 later... THE BLOG POST: https://mariozechner.at/posts/2025-11-02-what-if-you-dont-need-mcp/ having 4-6 MCP's connected really adds some overhead. I even noticed this issue with Codex, I had to uninstall Vercel (3x bigger than GitHub), and a bunch of others. So moral of the story, keep your MCP's very light, if any at all. Even the GitHub MCP is pretty much pointless unless you're doing heavy actions / worktrees. Using 5 agents on 5 different trees. etc. If you're just doing light Push.Pull.Merge.Commits. then you don't need GitHub MCP. And after reading this post you can safely get rid of Playwright, Puppeteer, Chrome MCP Browser tools etc. EDIT: The scripts can be found here: UPDATED: https://github.com/badlogic/pi-skills (not just pi skills, can be used with Claude, Codex, Gemini, Hermes etc)

Before I get to the who and why, I want to say this plainly. Picking a winner this round was genuinely hard. I went through every submission. Pulled repos. Read identity files. Compared rules.md sections. Every entry did real work. A lot of you shipped something I would happily use, sell, or hand a client tomorrow. I can NOT explain to you how proud I am of everyone participating in these, you make this community worth and it and there is SO much potential for the future from just ONE competition let alone future ones. 💼 That part matters more than the prize. The $325 covers a year of Premium and that's great but... The portfolio piece is the real value here. A public repo of a working folder-based AI specialist with a clean README and receipts is a resume line that hiring managers can clone and test cold in five minutes. It is also something you can charge for. If you built a specialist that solves a real problem in a real domain, you already have most of what you need to license it to a peer in your industry, sell it as a service, or package it as a Done-with-You engagement. A few quick notes on that, because most of you did not realize what you actually built and I want to Highlight a few of you: 💸 @Nicolas Patron Uriburu USD Routing Coach AR could be sold to every Argentine indie consultor I know. Same playbook works for any country with FX restrictions. Subscription service, recalibrated annually, audit-pack included. It is a product. 🔗 https://github.com/Nicopatron/usd-routing-coach-ar 🔧 @Jannetje van Leeuwen RAMS specialist is a service business in waiting. Irish signage contractors will pay for this. Same model works for any trade with a regulatory documentation burden. Plumbing, electrical, fit-out, demolition. Each one needs its own folder. 🔗 https://github.com/JannetjeIQ/rams-irish-signage-installer