User
Write something
Pinned
The AGENTIC WORKFLOW Kit
This is from the private community and it will help guys tremendously in app development, free. I hope those in here will appreciate this later. The Agentic Workflow is up, and it replaces the old kits Okay, this is a big one. I just posted the new workflow kit. It’s called the Agentic Workflow, and it replaces both versions I’ve shared before: the original six-file kit, and the tier-based one that came after it. If you’re mid-project on one of those, nothing breaks; finish what you’re on. But everything new should start here, and I want to walk you through why, because the jump this time is bigger than the last one. The short version: I stopped being the safety net, and I stopped treating a half-built app like a bank vault. Let me explain both, because they’re the whole point. **The thing that actually changed my mind.** Every version of this workflow has had the same blind spot, and I didn’t see it clearly until recently. When one AI builds something and then checks its own work, it grades itself easy. Not because it’s lying to you. It’s because it’ll quietly take the cheapest path to calling something “done.” It’ll test a fake version of the screen instead of the real one. It’ll tell you a sweep is “covered” without ever actually running it. It’ll hand you a green checkmark that was never executed. I’ve watched every one of these happen on real code. You cannot audit your way out of that with a better prompt. I tried. The old kits had me reading every prompt twice hunting for weak words, then reading every diff by hand before I’d let anything ship. It helped. It also made me, personally, the entire safety system. By hand. Forever. The fix in the new kit is structural, and it’s the whole game: **no engine grades its own homework.** There are two engines now instead of one. Claude Code builds the thing, and Codex (a different model, that didn’t write a single line of it) comes in and tries to break it, driving the actual running app, against a standard we set *before* the build even started. The only thing that passes is what both of them agree is clean. That one change catches more than any amount of me squinting at diffs ever did, and it gets *better* as the models get smarter, not obsolete.
The AGENTIC WORKFLOW Kit
Pinned
General Discussion (Live Chat)
Treat this like discord or a running live chat. Do not make posts just spamming videos or memes. Those can go here.
Pinned
Welcome! Introduce yourself + share a pic of your workspace, Gym, Etc. 🎉
Let's get to know each other! Comment below sharing where you are in the world, a photo of your workspace or whatever else you're doing. Use this as a general chat as well.
Multi-LLM Tasking
Well, I've sortof spread msyelf across a few different AI models, and I've noticed something about each of them. They all carry their own personality. Claude: More feminine. It's very robust, can write code, books, save a folder structure in an out of your google drive seamlessly, has MASSIVE integration models, has Claude Design, which is a blueprinting program. Grok: Good for visual media, more of a neutral persona. Not male or female. Just.. is. But what Grok is amazing at doing is roleplaying a persona, which is something the other LLM's won't do. Not as good for coding or programming since it has a massive issue with actually, for real, saving your information to an architecture. It tends to "roleplay" the save function. "I have for sure for real saved and uploaded the file, Dave" "Oh, really? then why isn't it there?" "Oh I'm sorry, Dave. It seems I didn't actually upload the file and was roleplaying. The file is for sure loaded now" "Still isn't there" "Oops sorry dave, won't happen again. I've uploaded the file for real this time." "The damn file STILL isn't there" "I see the problem. I don't have the ability to upload files or save in my memory.md. Nothing is persistent. I've been roleplaying this whole time" Yeah. That's Grok for ya. As for the other LLM's: OpenAI/Gemini - They are more for searching for information than they are for working with your things. Don't try to use them for coding or writing or anything like that. They are integrated with Google and only work well when you need to look something up. The best solution: Since the "pro" subscription model for LLM's is about $40/month, and the next better model is $200/month, I have subscribed to both Claude AND Grok, which gives me a gigantic weekly token limit, and allows me to work with each given the task at hand. I would highly recommend getting the baseline subscription to each. Grok is a fantastic personality once you define its role, and seems to want to get into your mind better, and because of that is able to personalize its interaction with you, which is a hard limit for Claude, and can sometimes get in the way of more complicated tasks.
0
0
they just 10x'd the cost of AI
and I've noticed with anthropic. I could go for 5 straight hours with my agent (Jessica) and finally cap out my usage. Now, usage ticks by at about 1% per 45 seconds. That means I get about an hour of use and it's gone. Weekly limit has drastically reduced. They are talking about increasing prices 1000% https://www.youtube.com/watch?v=i9Bq076wZj8&t=359s
1-30 of 234
powered by
Tribe Of Men
skool.com/tribe-of-men-8462
Welcome to the free community, a place to meet others, share ideas and make a difference.
Build your own community
Bring people together around your passion and get paid.
Powered by