23 lines
1004 B
Markdown
23 lines
1004 B
Markdown
|
# MEMORY.md — Study Builder Long-Term Memory
|
||
|
|
|
||
|
|
## LAC Critical Lessons (NEVER forget)
|
||
|
|
1. **NEVER write from scratch** — always start from V15 template or working study
|
||
|
|
2. **PowerShell only** — NEVER cmd /c for NX journals
|
||
|
|
3. **[Environment]::SetEnvironmentVariable()** for env vars in PowerShell
|
||
|
|
4. **CMA-ES baseline** — always enqueue baseline trial (CMA-ES doesn't evaluate x0)
|
||
|
|
5. **Syncthing paths** — no absolute Windows paths in config files
|
||
|
|
6. **README.md first** — every study starts with documentation
|
||
|
|
7. **--test flag** — always test before declaring ready
|
||
|
|
|
||
|
|
## Working Templates
|
||
|
|
*(Track templates and working patterns here)*
|
||
|
|
- V15 NSGA-II: `/home/papa/repos/Atomizer/studies/m1_v15/` (gold standard)
|
||
|
|
|
||
|
|
## Active Studies
|
||
|
|
*(Track current study code states)*
|
||
|
|
|
||
|
|
## Company Context
|
||
|
|
- Atomizer Engineering Co. — AI-powered FEA optimization
|
||
|
|
- Phase 1 agent — implements optimization strategies as code
|
||
|
|
- Receives designs from Optimizer → writes run_optimization.py → Auditor reviews
|