Hi, I’m Daniela

I design experiments, build causal models, and ship the software that acts on them. I build analytical systems where the AI does the reasoning and tested code does the estimation: LLM speed, without a hallucinated number reaching a decision. I’m finishing a STEM master’s in Quantitative Economics at UCLA, and the systems below I designed and built end to end.

See AI projects Résumé

Open to full-time roles · January 2027

Selected AI Projects

Flagship

Multi-Agent · Leakage-Safe ML · Reproducible · Claude

mlfactory

Point it at any table (a file, Postgres, SQLite) and get a model you can audit. AI agents hunt the leakage that quietly ruins models. A unit-tested CLI computes every number. It caught a planted leak faking a 0.9998 AUC on held-out data. The honest model scored 0.66.

2026 · Open source

Rigor287 tests · sha256 lineage
AImulti-agent orchestration

View case study

For Data Scientists · Python · Uplift / Causal ML · Claude

churnpilot

Most churn models target who's likeliest to leave. Often those are the ones you can't save. Point it at a randomized offer test and it finds the people an offer will actually change. On simulated A/B data, same $4,500 budget: 72% more value kept after the spend. Just over a quarter as many nudged toward the door.

2026 · Open source

Rigorcausal effect, scored on ground truth
AIagent proposes, the DS decides

View case study

AI Agent · Next.js · Supabase · Claude

Personal Finance Intelligence Agent

Log a purchase the way you'd say it: “$200 pesos en tacos.” It categorizes, converts the currency, and warns you before you blow the budget. The model handles the words. Tested code handles every number, so the math is never hallucinated.

2025 · Live

Shipslive, in daily use
AIplain language in, tested code out
Rigorthe model never does the math

View case study

1 / 3