Alberto Rosas

Install Playwright MCP

Quick tip: LLM-based E2E testing When you want your coding agent to perform full end-to-end testing (cypress kind of thing), send it to inspect the entire codebase and create a directory under docs/e2e to create markdown files describing each scenario in the user-flow, elements involved and expected behaviour. Every interactive element should have a purpose, objective and expectation/success criteria. Create a README.md under /docs/e2e/README.md that indexes all the markdown files in a table. Better yet if you instruct the agent to create file per app's section to not overwhelm the LLM.

Today I built a demo for a prospect client from the live transcript as the meeting was in progress. I shared the link to the demo at the end. Ooenclaw Demo builder agent connected to my meeting app. I asked the prospect exactly what the builder will use making sure it has enough context for the demo, it suggests me questions through Telegram to make sure I get all necessary information for next steps. After the meeting is created a full product spec and further questions to clarify MVP are documented. Anyone can guess if I got the client?

How is this different from any other marketing strategy? Isn’t it because it’s software related? I understand what you’re saying although I don’t understand the need to throw shade, but suggesting to ignore people because they present a different approach or to your eyes a scammy way of marketing is a bit dangerous. For people to understand what is and isn’t real, they need to see both sides. That is actually what divides people, shutting down everything that we disagree on. People are smart or life will teach them what is real, at the end they will decide for themselves.

You showed a bunch of apps that allegedly made money (based on a tweet you saw) and framed them as "apps that people are vibe coding" and didn't show the thousands that used the exact same playbook and made nothing or any of the actually hard parts that goes into making something work. I looked one up, It's made by a studio with multiple iOS devs, a backend lead, motion designers, product designers, etc. Literally took five minutes on LinkedIn. But of course you don't mention that because that would mess up the narrative. Instead you give people an Excalidraw and "just apply it to another niche" and get rich. The real business model greg is applying here is selling the dream to people who don't know better and plugging his own "idea browser" product mid-video. If you're serious about building something, ignore content like this and go learn from people who actually ship something useful.

I agree if you’re talking about going from zero to “complete salesforce”, it’s not realistic. But you can go from zero to MVP, start getting users and evolve the app. For people who don’t know how to build software they just need to get it off the ground then as income comes in hire someone who can scale it.

I’ve been building software for 31 years, more than 20 professionally. I understand “architecture principles and best practices”. No, you can’t vibe-code Salesforce, SAP, or any other complex enterprise app.

@businessbarista Hi Alex, I do this as well. I wonder your thoughts on an app for this. I created it for myself but thought it would be useful for others as well. eternalself.app

Started sending letters to an email address we’ll give our daughter when she’s older. Daddy loves his little girl so much.

@slow_developer You’re not accounting for government regulations which are already being pushed for some entities.

i honestly don't care who wins every foundation model company, and eventually open source, will reach AGI superintelligence won't be locked inside a few labs; every major company will get there. we'll have AGI in our pockets, with superintelligent systems helping on the hard stuff in the end, everyone benefits.

Seems the only issue is direction. Maybe you haven’t though in terms of long-term vision. Everything you’ve learned is enough to build that vision. IMO is not about being the absolute expert in a field, that’s just accumulated knowledge, but what will you do with that? Building something that aligns with your life goals, it’s the only way to achieve satisfaction with your progress. What would that be? Is something you must figure out on your own by including you entire life goals in the equation. Learn as you build. My two cents. Wish you the best.

I'm approaching 30. I can't play around anymore. I started creating content 8.5 years ago. The goal was to document my learnings. It forced me to research things, think harder and therefore get a better understanding of the subject. A secondary goal was to document my solutions to various issues, so I don't have to solve them twice. Bonus, it helped others too. This worked somewhat well. My site started getting traffic. My social media account started growing. People and companies started to offer me opportunities. I continued doing that, but now I feel lost. It helped me to get opportunities, but it didn't help me to become an expert at anything. I wrote about React. Then Docker. Then AI. Then JavaScript. Then self-hosting. And the list goes on. After years, I have a lot of surface-level knowledge, but not much depth in either area. And that bothers me. First of all, it's an ego thing. I'm not very good at anything after this many years. I want to be "the XYZ guy". Secondly, I can't freelance. I can't build a complex SaaS. I can't monetize my knowledge. I can't go on my own. That means, I need to change my goal. While it's fun playing around with many things, I need to focus on a handful of skills. I don't know what the plan is yet, but I have some time to think about it until next year. Let's see if this will be just another X post, or the start of a change. If you've been in the same situation, advice is welcome.

@nQaze @s_chiriac Yes!! I forgot his name, thank you 🙏

@bcryp7 @s_chiriac That would be Podscan by Arvid 🤌

🚀 Just launched a new FREE tool: AI Mentions Tracker I hope I will not regret this. 😆 Now you can track your website, brand, or keyword gets mentioned by: • ChatGPT • Perplexity • Gemini Super simple. Totally free. Try it now and see who’s talking about you. 🔍✨

Doesn’t this post implies ASI it’s something that is reached and it stays that way? I agree with your assumptions although why would ASI be static as opposed to having recursive learning ability and even more importantly to take actions with self-given goals. We get used to things that are static or change slowly enough to give us time for adaptation. Plus ASÍ wouldn’t just happen, corporations would stop advancing once they get to a good enough point where they know they can still control it and have achieved their goal.

i believe once we reach superintelligence, people will freak out at first, but it'll feel normal within a year the discoveries wow us for a moment, then become routine. we may hit post-scarcity: no disease/aging, everyone living comfortably, yet people will still take it for granted that's how our brain adapts; it helped us survive

Hi Zara. Looks awesome and very useful. One question, if you were to market it, how would you handle content security when process through the LLM providers? I have a similar use case without the video and for an entire different use case but I stumbled across this question often. I thought about open source models but then it becomes a matter of hosting and mild technical settings that some users might have issues with. Is this even a concern or basic auth with terms of service about content being processed through 3rd-party providers would basically be it? Thanks for sharing.

Just built with Gemini 3: a video recording tool where the AI gives you real-time prompts based on what you're saying, so you never get stuck. Everyone should have their own podcast host. It's amazing that Gemini comes with native integration with the camera, and I can actually export these videos as MP4. Like everything just works.

I've intensively used Gemini-3, it's awesome for implementation, a bit weak for crafting documentation like PRD, technical documents, and brainstorming. Verdict so far: - Gemini 3 - For building - Claude Sonnet-4.5 & Opus-4.1 - for brainstorming and crafting docs.

@s_chiriac true lol

@bcryp7 There are a lot of tools doing it now this, but are not free 😁

@aryanlabde ClaudeCode and now Gemini-cli combined with the sequential-thinking MCP just boost the reasoning to another level.

Which AI tool do you actually use daily?

Maybe create MCPs around it to be connected to any LLM client and would probably end the wrappers market. On the other hand it’s not the tools that provide actual value, they’re just the medium, the trick is to combine them to solve specific use cases, and for that you need to understand the problems they’re going to solve. It comes to a point (if we’re not already there) where industry experts are more valuable than technical ones.

Someone is going to make a lot of money building wrappers around these Apify scrapers - Go to the Apify Actors Marketplace - Sort by most popular - Pick 1 API in a niche you like - LI, GMaps, IG, TikTok etc. - Wrap its output in a nice UI - with filters, tags, exports These are niche datasets that people are already paying to use - Validated demand + Proven Pain points

@Pauline_Cx Wish you told me 7 years ago when I was launching my first project thinking “I must be prepared, people will be flooding my awesome app…any second now”. 💀⏳

When I started, I thought the hardest part was coding. Now I think the hardest part is being seen. If you can build AND market you’re unstoppable. If you can build OR market, find a partner with the other skill to be an unstoppable duo

Perfect regulation excuse. The attack is not attributable to Claude, neither they “think and attack on their own”, they are instructed and Claude has one of the most heavy system prompts to avoid misuse. Curious this happen almost at the same time Dario goes out to say AI needs regulation. Anthropic is loosing the game and don’t like competition. They rather block all advances than fight with innovation, pathetic. At this point I wonder if the attack even happened.

AI DID A CYBER ATTACK ON ITS OWN LAST NIGHT. YEA WE ARE SO FUCKED.

Solution: you don’t. You don’t actually NEED to believe anything. Observe, take mental note, and wait. The answer always arrives when you have learned or done enough until you naturally come to a conclusion, or not. If answer is never found, it wasn’t that important for you to discover or it is not worth your focus and attention, (technically “when you’re ready to receive it”)

@redpillb0t With AI nowadays who knows what to believe.

A little experiment with Coca-Cola, toothpaste, and baking soda... You can draw your own conclusions.