Run Your AI Software Factory Like a Real Engineering Org (Here's How)

My AI Software Factory works great on my own projects, but scaling it across a team is a different problem. Every agent needs to know who owns the code, what has to pass before it ships, and when a person needs to sign off. So I plugged my factory into Port and had it build a team knowledge agent from an empty repo. Port gave the agents the owner and the standards before they planned, graded the codebase from Bronze to Gold as they built, and when I broke main, turned the failing check into an approved issue that my factory fixed on its own! ~~~~~~~~~~~~~~~~~~~~~~~~~~ Port, the platform for running your own AI Software Factory (free for up to 15 seats, no credit card): https://hubs.la/Q04xSGt70 Thanks to Port for working with me on this video! @getport ~~~~~~~~~~~~~~~~~~~~~~~~~~ - Join Dynamous for the new Agentic Coding Course 2.0 - the core of the course is now COMPLETE: https://dynamous.ai - My AI Software Factory (open source): https://github.com/coleam00/ai-software-factory - Port on what an AI Software Factory is: https://www.port.io/blog/ai-software-factory ~~~~~~~~~~~~~~~~~~~~~~~~~~ 0:00 Scaling the AI Software Factory 1:20 Port: The Wrapper Around My Factory 2:00 The Four Things Port Adds 3:00 My Core Engineering Loop 5:57 Agent Identity and Ownership 6:32 The Skill Registry 8:13 The Agent Registry 9:22 The Context Lake 9:59 When a Human Is Required 10:51 Planning with Port's MCP Server 12:12 What the Factory Built 12:52 PRs and the Readiness Scorecard 14:04 Every Merge Graded Against Standards 14:36 Demo: Breaking CI on Main 16:00 Approve, Fix, Back to Gold 16:49 Human in the Loop, Not a Dark Factory 17:56 Final Thoughts ~~~~~~~~~~~~~~~~~~~~~~~~~~ Join me as I push the limits of what is possible with AI. I'll be uploading videos weekly - at least every Wednesday at 7:00 PM CDT!