This week taught me one important lesson: progress doesn’t come from feeling ready; it comes from showing up anyway. 🚀 I’ve been developing a tool that I keep referred to in the video as an “automation” tool. However, I know better it’s a custom quote generator. 🧾 This tool features reusable templates, allowing companies to avoid the tedious process of rebuilding quotes from scratch. They won’t have to jump into Canva, place images, format text, and repeat that entire process each time. Or constantly looking for files to copy paste The contents to not have to write it down every time The real value lies not in buzzwords, but in the time saved. ⏱️ I’m new to this, and things break; some features only work halfway. My laptop moves as if it's on vacation! 💻🐢 However, I still committed. 🔁 Here’s what I learned: - Consistency beats talent when talent gets tired. 💪 - Confidence comes after taking action. 💼 - Broken things are feedback, not failure. 🧠 Nothing is perfect yet. The user interface still needs improvement, and the templates aren’t finished. But I’m not the same person I was two weeks ago Heck! I’m not even the same person I was a year ago. 🌟 This journey isn’t just about building one app; it’s about developing discipline. 📈 If I occasionally use the wrong words, understand that my intentions are right. I might call it “automation,” but what I really mean is saving people time and reducing stress. 😊 And if my Accent sounds different, that’s just the Caribbean in me! 🌴 I’m focused on fixing code, not my accent. So for those that might have an accent remember what matters most is your hard work and dedication 😂🫡👊🏾 Week two is complete, and week three is on the way. I’m not stopping! 🚀

I think a lot of developers are stuck in this weird middle ground with AI. We know how to prompt ChatGPT. We’ve played with Claude Code. We’ve heard about MCPs. We’ve probably built a few little agent experiments. But getting from “this is cool” to “this agent reliably does work in my actual codebase” is a completely different problem. What helped me was thinking less about individual AI tools and more about the system around them. For example: Claude Code → actually works against the repo MCPs → gives agents access to the tools/context they need Skills → makes repeatable tasks more structured Orchestration → gets multiple pieces working together instead of having one agent try to do everything That last part is where it gets interesting. Instead of asking an agent to magically build an entire application, you can start giving it smaller responsibilities and connecting those pieces into a workflow. I've also found that keeping the work itself organized matters more than I expected. Floment has been useful for tracking the tasks and moving parts around an AI-assisted project while I’m actually building. The goal isn't “use more AI.” It’s getting to the point where you can say: “Here’s the problem. Here’s my repo. Go do the work.” …and actually trust the result enough to review, test, and ship it. How far along are you with agents right now, still experimenting, or do you already have one doing real work in your projects?

Last month I "hired" a senior dev. Cost: $180K/year, 6 weeks onboarding, still asking where the staging env is. This month I wrote a 40-line agent config. Cost: $12 in tokens. Shipped 3 features by Tuesday. Never asked for a standup. I'm not saying replace your team. I'm saying maybe stop pretending that a Notion doc titled "Q3 Roadmap 🚀" is a strategy when your competitor just shipped the whole roadmap over the weekend. Vibe coders are journaling. We're deploying. What's the smallest agent you've built that punches way above its weight? Drop the config, I want to steal it.

Friday tradition in my shop: find one thing a human still does, and put a bullet in it. This week's victim: onboarding emails. Old flow: New signup → I get Slack ping → I copy their name → I write "personal" email → I feel like a founder → I resent my life. New flow: Signup → agent reads their company site → drafts email referencing their actual product → queues in my outbox → I hit send while eating a sandwich. Time saved: ~30 min/day. Response rate: up 3x (turns out people notice when you mention their thing by name). Sandwiches eaten: appropriately many. What did YOU kill this week? Bonus points if it was something you swore "only a human could do." Those are always the most satisfying.

I used to restart Claude sessions all the time because I'd hit context limits or need to switch tasks. Every restart meant re-explaining my setup, tech stack, and what I was building. Then I started treating MCP servers like my 'external brain'. Instead of cramming everything into chat context, I built a simple MCP that reads my project docs, database schemas, and recent decisions from files. Now Claude just asks the MCP when it needs context. Now I can work on the same project across 10+ sessions without losing continuity. Claude remembers everything because the MCP remembers everything. Anyone else structuring their MCP servers this way? Would love to hear other patterns people are using.