Generative AI

Who controls what your AI recommends?

Seasons, campaigns, and weekly events — retail runs on overlapping cycles, and the AI recommender has to keep up with all of them. Notes on the business-rules control surface that lets merchandising teams steer a conversational recommender without editing prompts, filing tickets, or waiting for a deploy.

Cyril Noirot

April 16, 2026

Share on

8 min read

> "The buyer wants to push the new Ralph Lauren collaboration this week. How do we change what the system recommends by Friday?"

If the answer involves editing prompts, redeploying, or filing an engineering ticket, the recommender is not a system. It is a demo.

If the answer is "the merchandising team edits a config file and it takes effect on the next customer query", the recommender is something that can survive contact with a real retail operation.

The system in question is the conversational AI your customers interact with — the shopping assistant, the product recommender, the commerce chat agent. The label changes. The control question does not.

About the author

Cyril Noirot

Lead Data Scientist

Freelance data scientist. I design and ship decision systems — forecasting, pricing, marketing measurement, optimization.

From SaaS to intelligence native: the feedback loop.

Intelligence-native systems need agent access to decision artefacts and feedback loops. Why context, not models, is the differentiator — and how MCP, traditional ML, and versioned artefacts fit together.

Generative AI11 min

Ce que le commerce agentique exige vraiment en production

Macy's annonce que les clients utilisant son assistant IA dépensent 4,75x plus. Sephora vient de lancer une app dans ChatGPT. Zalando déploie son assistant dans 25 marchés. La question pour tous les autres retailers n'est plus 'faut-il le faire ?' mais 'comment l'architecturer pour que ça tienne en production ?'

Generative AI11 min

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.

Newsletter

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

Enter your email