Hey everyone, I’ve been working on something called "ASES", and I think it’s finally at a point where it needs real-world testing instead of just me building in a vacuum. This is not just another “AI tool” or prompt setup. It’s basically my attempt at: "Turning LLMs into a structured, end-to-end software development system" --- ## What ASES actually is ASES is a "schema-driven Scrum workflow for AI-assisted development". Instead of: * random prompts * messy context * inconsistent outputs It gives you: * a "full project lifecycle" * "structured artifacts (PRD, HLD, LLD, tasks, tests, etc.)" * and a system where models operate inside that structure --- ## What makes it different ### 1. Everything is structured (schemas + templates) Almost everything in ASES is backed by schemas: * PRD → requirements * HLD / LLD → architecture * Tasks → execution * Decisions → tracked explicitly * Test suites + reports → validation * Sprint summaries + audits → closure So instead of “ask the model and hope for the best” you get: "deterministic, repeatable outputs" --- ### 2. Full Scrum lifecycle (not just tasks) This isn’t just a task runner. It actually maps a full flow: * Planning → PRD / roadmap * Design → HLD / LLD * Execution → sprint-based tasks + snapshots * Testing → structured validation * Closure → audit + summaries Everything lives in a "project structure", not chat history. --- ### 3. Runtime context control (this is the core) Instead of dumping context into every prompt, ASES: * Injects context "just-in-time (per action)" * Uses "layered + scoped context" (global / sprint / execution) * Adjusts how much context to include based on state So the model only sees: > what it actually needs *right now* This is where a lot of the "token efficiency + consistency" comes from. --- ### 4. Model orchestration (multi-model workflows) ASES is designed for using multiple models with "clear roles", not one model doing everything. For example:

I am going to do a long form video on this whole setup before I dive balls deep into wrapping up the agency courses inside the premium classroom! TLDR; This plugin creates a semantic relationship between ALL your data inside of your workspace, and bypasses using GREP. GREP is token heavy and is like a flashlight on data vs graphify which is a satelite with 5g connections between your data. So you're saving 70x the tokens when searching through data, inspired by Andre Karpathy, one of the coolest founding members of Open AI. Stack this with Obsidian to get a birds eye view (graph view) of all your data! Watch the youtube short I attached here to learn a bit more about it and how to set it up! & shoutout to @Spider Dancing for sending this plugin in for review yesterday, SUPER useful plugin. Hope this helps! God bless, Charlie

So i have a bunch of site examples and different elements that I like of each site, i uploaded them all to Claude and talked through what I like of each site, and the elements i want to see and what I dont like. Now I want to start actually building the site, any insite on what next steps need to be other than telling Claude to start building the site, or the best way to get the best results? This is a site for my agency so I'm wanting to have the ability to edit and update it in the future, I've been using Railways for all my web apps for internal use. Thanks in advance

Seen some content about codex inside claude code, what are your thoughts?

I feel like I'm spending too much time telling Claude Code to fix things, redo things. It's not following instructions last week or so.... I need to fix this . but in general.... Found that I had too many loaded skills from social media. Got rid of a bunch of them. I think it was costing me a ton of tokens and usage. Love using seed and paul. (seem like its used for more complex stuff) @Charles Dove help a brotha out..... premium??