top of page


A Shopping Assistant That Never Invents a Deal: Grounding the Model in the Real Catalog
A shopping assistant's worst failure is the invented offer. What a prototype teaches when you forbid it to lie: four narrow tools, zero prices from memory, and refusal as a feature.
Jul 9


The Invisible Map of European AI: Why Nobody Cites the Continent's Labs
Mistral, Hugging Face, Kyutai, DeepL, Aleph Alpha, Black Forest Labs, H: European AI is dense — and nearly absent from assistant answers. What drawing the map taught us about the mechanics of citation.
Jul 9


The State of AI, in French: a continuously updated reference read
ECTIME publishes L'État de l'IA, a free French-language long read on where AI stands: frontier labs including seven European players, adoption data, and 31 free resources.
Jul 2


From One Deal Link to Three Channels: Anatomy of an Agentic Distribution Pipeline
One deal link in, three native publications out. The division of roles that holds the pipeline together: deterministic code extracts, the model writes, the human publishes — and one north star, new users.
Jul 2


The AI Content Factory: Machines in the Middle, Humans at Both Ends
Daily multilingual content flows run by two or three people: what AI really accelerates, and why choosing the topic and accepting to publish stay human, by design.
Jul 2


Accepting AI Work: The Five Gates Before Anything Ships
An agent that loops is not an agent that's reliable. The five acceptance gates we apply before letting an AI publish or touch a system: deterministic first, generator separated from acceptor, evaluation sets, classified actions, human signature.
Jul 2
bottom of page