Thought I’d give everyone a proper update on where BuilderCore is. The backend has reached a point where I’m finally running real trial projects through the entire system. At the moment, the focus isn’t adding new features—it’s debugging, validating and making sure every stage behaves exactly as intended. Some of the biggest challenges so far: • The UI is constantly playing catch-up. I naturally move much faster on backend architecture than frontend, so a lot of the recent work has been making the platform usable rather than just functional. • Governance is hard. The biggest challenge isn’t getting AI to generate code—it’s making sure work can only progress when the correct gates have been passed. Planning, implementation, review, validation and operator approval all have to happen in the right order, every time. • Testing is everything. Building the platform turned out to be only half the job. The real challenge is debugging it until it behaves exactly how you imagined. Every trial uncovers edge cases that you’d never think of on paper. • Model limitations are real. One thing I’ve learned is that different models genuinely excel at different tasks. At the moment, my own experience has been: 1. Fable 5 2. GPT-5.6 3. Claude Opus 5 None of them are perfect, and usage limits are still a genuine bottleneck when you’re building complex AI systems every day. Right now BuilderCore is successfully working through trial projects, and each run helps expose another issue to fix. Once I’m happy with a single project, the next milestone is running multiple projects simultaneously and making sure the orchestration scales properly. If all goes to plan, I should have a proper demo to share soon. It’s been six months of building, breaking, rebuilding and learning, but it’s finally starting to feel like a real platform rather than just an idea. Looking forward to showing everyone what it can actually do. 🚀

Have been fiddling with ICM, Hermes, GSD, BMAD, taskMaster etc. They all sound perfect and logical on their own but feel "out of control" somehow so put it inside of ICM. I tried to make sense of them all and cook up an ICM here: .icm/ ├── CLAUDE.md # Upgrade safety gates, rollback hooks, and CLI routines ├── .icm.env # NEW: Central environment vars feeding variables to scripts │ ├── 00-gsd-wave-governor/ # CONTEXT & SPREAD CONTROL │ ├── contract.md # Rules: Blast-radius mitigation, branch naming, strict file locks │ └── active_wave.md # Tracks the current migration delta and target files │ ├── 01-discovery-and-party/ # LEGACY ANALYSES & DEBATE │ ├── contract.md # Rules: Analysis must document side-effects before code editing │ ├── codebase_discovery.md # Static analysis logs, dependency graphs, and tech debt maps │ ├── 00-party-room/ # BMAD Party Mode: "Refactor vs. Wrap" architectural battles │ │ ├── system_prompt.md # Personas (Winston/Arch, John/PM, Safety-QA Specialist) │ │ └── migration_consensus.md # Binding agreement on the upgrade strategy & fallback path │ └── 01-feedback-loops/ # Regression and breaking change post-mortems │ ├── 02-taskmaster-decomp/ # MIGRATION STEP DECOMPOSITION │ └── todo/ # Micro-tasks focused on localized refactoring steps │ └── 03-bmad-assembly-line/ # IMPLEMENTATION & REGRESSION TESTING │ ├── 01-architect-spec/ # BMAD Role: Designing code deltas & backward compatibility │ ├── 02-dev-workspace/ # BMAD Role: Executing precise, isolated modifications │ └── 03-qa-sandbox/ # BMAD Role: Core regression suite, smoke tests, validation

Tell us three things: 1. What you do (job, industry, student, career-changer, whatever) 2. What brought you to Clief Notes 3. One thing you're trying to figure out right now related to computing or AI I'll respond to every single one. And read each other's intros too because the person who's stuck on the same problem as you might already be in this thread. I'll go first I am Jake, I have been working in tech for 15 Years, building with Generative AI for 3 Years straight now! Excited to teach and learn! That's it. Simple, scannable, gives you data on who's joining and what they need, and keeps the feed clear for content that retains people past week one.

I'm seeing three different formats for builds, but I'm not very experienced, so correct me if I am wrong. - Standard product: Everyone uses essentially the same software—like Canva or Trello. Customers may adjust settings, templates, colors, or permissions, but the underlying product remains the same. - Configurable product: The core software is standardized, while each business selects its workflows, roles, terminology, templates, branding, and integrations. - Custom software: The tool is built or substantially modified for one client’s processes, systems, or regulatory requirements. So, what do you build? And, what are you listing on Ledger? I promise, I'm nobody's competition. I'm just trying to understand what works, why it works and where you show your work.

I recently moved to the Seattle area after living in a small town, and I’d love to start meeting more people from this community in real life. Are there any Jake Van Clief community members in Seattle or the surrounding area who would be interested in grabbing coffee, meeting for lunch, or putting together a small local meetup? It would be great to connect, exchange ideas, and get to know some of you beyond the online community.