Generative AI10 min read

Who controls your AI recommender in production?

Most AI commerce demos look great until you ask: who controls the ranking next Monday? This article walks through the operator-control architecture I built for a fashion recommendation system — hot-reloadable business rules, multi-agent persona routing, and a catalog analytics layer that lets merchandisers query their own data in plain French.

Cyril Noirot

Lead Data Scientist

April 16, 2026

About the author

Cyril Noirot

Lead Data Scientist

Freelance data scientist. I design and ship decision systems — forecasting, pricing, marketing measurement, optimization — for teams making high-stakes calls.

Building a recommendation engine that doesn't trust the LLM

This is the engineering companion to the production architecture piece. Instead of re-arguing why open-ended agents are risky in commerce, it walks through the actual implementation choices in `ai-florist`: FastAPI boundaries, LangGraph orchestration, pgvector retrieval, learned scoring weights, deterministic fallbacks, and runtime observability.

Generative AI10 min

What agentic commerce actually requires in production

Macy's reports customers spending 4.75x more with their AI assistant. Sephora just launched inside ChatGPT. Zalando rolled out to 25 markets. The question for every other retailer isn't whether to build this — it's how to architect it so it actually works. Here's what I learned building one for premium floral e-commerce.

Generative AI6 min

LLM Systems: Architecture First, Framework Second

LangChain, LangGraph, Claude ADK, Google ADK, PydanticAI — different names, different abstractions, same promise. This article cuts through the framework noise and identifies the five architectural properties that actually determine whether an LLM system survives production.

Newsletter

Technical writing on forecasting, pricing, and decision systems. No fixed schedule, no spam.

Enter your email