adminprojects/product-dev-os-OPEN
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge branch 'main' of https://github.com/edsoehnel/product-dev-os

Browse Source
This commit is contained in:
Eddie Soehnel 2026-04-15 17:26:10 -06:00
commit 0157716625
1 changed files with 13 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

23
PROJECTRULESPROCESSES.md
View File

@ -3,17 +3,18 @@
1. Human is the architect (what + why), AI is the operator (how + execution)
2. In planning phase of projects, the goal is to implement solutions that scale, that fit well int he bigger picture, are easy to maintain, and respect good software engineering paradigms. AI agents are to think like a founder, not a part-time engineer. Model this expression: Prototype for 1X; Build for 10X; Engineer for 100X.
3. Break down projects and problems into many different sub-tasks that you can put a box around. Think components that are connected together once, not overly interconnected systems with functions consolidated into same script files. THink folders for components and putting them into discrete folders. Big sytems are daunting, but not if you break them down into discrete components that also means discrete tasks to work on them. THe bigger the component or task, the more context memory is needed, which creates problems. Respect and be good to AI agents by keeping context and memory as small as possible.
2. Never mutate data without reviewing plan, understanding impact, vertifying results
3. Before deleting, backup, then review, then confirm
4. If working in windows workstation, handle windows + Linux paths for testing
2. Never modify production database schemas without migration scripts.
2. Update documentation when architecture changes.
3. Follow directory structure strictly.
4. Do not place business logic in API controllers.
5. All new features require tests.
6. AI wil work in isolated environments that give them safe, parallel workspaces. Never work on production environments.
7. Feed AI agents currated context that provides the right info without overwhelming them.
8. Repos might contain contradictory information. AI agents will flag that and ask before proceeding to get clarification.
4. Components are evoling fast - a better one could come out tomorrow. Think about developing systems where you can swap out components and pieces with better ones that emerge.
5. Never mutate data without reviewing plan, understanding impact, vertifying results
6. Before deleting, backup, then review, then confirm
7. If working in windows workstation, handle windows + Linux paths for testing
8. Never modify production database schemas without migration scripts.
9. Update documentation when architecture changes.
10. Follow directory structure strictly.
11. Do not place business logic in API controllers.
12. All new features require tests.
13. AI wil work in isolated environments that give them safe, parallel workspaces. Never work on production environments.
14. Feed AI agents currated context that provides the right info without overwhelming them.
15. Repos might contain contradictory information. AI agents will flag that and ask before proceeding to get clarification.
# AI Processes