Architecting Intelligence
From regulated systems to applied AI — deliberately, from first principles.
I’m learning machine learning and generative AI in public. This is not a highlight reel — it’s a disciplined log of fundamentals, experiments, and applied builds. My background is in payments and regulated delivery; I’m bringing that same rigor to evaluation, failure modes, and real user outcomes.
Learning Path
Phase 1 — Foundations
Python fluency, data handling, and the mental models behind supervised learning. Focus: clarity over complexity.
Now: numpy/pandas, data cleaning, train/test splits, baseline thinking
Phase 2 — Classical ML
Regression and classification, feature engineering, and models that survive messy data.
Next: linear/logistic regression, trees, cross-validation, leakage traps
Phase 3 — Evaluation & Risk
Metrics, calibration, and decision quality — especially under imbalance and regulation.
Next: precision/recall tradeoffs, ROC-AUC, PR-AUC, thresholds, explainability
Phase 4 — Generative AI
Prompting, retrieval (RAG), grounding, and evaluation — building safe patterns for real users.
Next: retrieval pipelines, citations, hallucination controls, eval harnesses
Phase 5 — Applied Builds
Turning the learning into products: FinLens + Questions for My Doctor — with constraints and evaluation built in.
Focus: real workflows, measurable outcomes, and responsible system boundaries