Come hang and build with us!
Rubber Duck Thursday!
www.linkedin.com
Love this initiative! Simple ideas like this can make learning, collaboration, and problem-solving much more engaging.
Krishna Hiwale Create a portfolio with projects that show what you know. This will set you apart from the crowd in your job search. Just make sure the projects you share actually solve a real problem.
I'm vibe coding an entire platform for sharing blueprints workflows (sort of a Steam Workshop for business apps integrations): https://github.com/abmlib/automation-blueprints-marketplace
Love this. Rubber Duck Thursday is a great idea. Is it open to anyone, and what time zone are you running it in?
phrase as "Create a concrete plan to upgrade this repo to be comparative to other models of this style/format" see the diff
how reliable is the auto mode by picking the right model for specific tasks?
Did you have a risk matrix saved as .md beforehand, or are you trusting each model's individual assessment?
Most people use GitHub as a code repository. We’re using it as a governance layer for intelligent systems. Not just storing code— but structuring how decisions are made, validated, executed, and audited. Because the real failure point in AI isn’t generation. It’s commit. The moment output becomes action— where something shifts from suggestion to irreversible impact. What we’re building: • Systems bound to a decision surface • Workflows enforcing admissibility before execution • Architectures with stop authority and rollback paths • Repos that version not just code—but judgment Inside GitHub: /doctrine/ → what must hold /schemas/ → how decisions are validated /contracts/ → what’s allowed /workflows/ → execution in reality /governance/ → logs, failures, reversals The goal isn’t smarter agents. It’s systems that know when not to act. Systems that can prove why they acted.