AI Factory Engineering Coding

AI-assisted Development Video - Michael Perry:  https://www.youtube.com/watch?v=t13OH8TmeRk

AI software factories - Michael Perry:         https://factoryengineering.dev/

Factory AI:   https://factory.ai/news/build-with-agents

Factory Model:   https://addyosmani.com/blog/factory-model/

AI Playbook:  https://dev.to/truongpx396/building-production-grade-fullstack-products-with-ai-coding-agents-a-practical-playbook-2idd

AI-assisted Development Video - Matt Pocock: https://www.youtube.com/watch?v=-QFHIoCo-Ko

AI software factories - Matt Pocock:           https://www.aihero.dev/   

    with 

npx skills@latest add mattpocock/skills

grill me => to prd => to issues => tdd => improve codebase architecture (should be clean) => 

Skills:

   1) Matt Pocock's skill set  (which has you in control) at:    https://github.com/mattpocock/skills  

  OR

   2) Superpowers by Obra (which has model in control) at:     https://github.com/obra/superpowers

Roo Code extension is now Cline extension in VS Code

Had Roo models fire off Playwright for testing

rsync - remote sync utility tool - puts into shared area on network 

Orchestrator (workflow), 

    planner - happy path, edge cases

    Loop

      test-writer

      code-writer

      refactor

    End Loop

    planner - recheck that plan done

IMPORTANT - All must escalate to Orchestator on problems

Docker Compose with one YAML file

Software Factory - Factory Engineering (team)

Skills = team preferences or coding standard applied to certain type of tech 

 used when AI builds code for you.

 

Cursor - ran against all SQL script data and create skill that captures that info.

Most modern development is "Brownfield development"

Claude Code 

Claude Design

Manual Process of Accepting Code vs. Automated Delegation Where Could Run 24/7 But Incur Cost (ROI).

Riptides:   https://docs.riptides.io/introduction/

Product => Architecture => Program Design => Vertical Slices

Do Vertical Slices (small pieces) instead of Horizontal Slices (the layers that AI likes to build).

Remember to test that the test creates the problem.

DAILY TASKS FOR AI:

 * Find and remove dead code across the code base.

 * Find and remove dead tests across the code base.

 * Ship experiments that are 100%.  

 * Write tests for areas of the code base that needs coverage.  

 * Abstraction police. Finds and unifies nearly duplicate abstractions.

https://www.youtube.com/watch?v=qyPCVqFUyDo