The model
Two models do the work: one understands your content the day it's created, and one learns from how people behave. Both retrain on your complete eligible data, validated versions publish automatically, and you can select a version or compare two versions in a live test.
Two models, one engine
Learns from each item's own features and meaning — its type, language, categories, and what the text is actually about.
Learns a representation of each person and each item from real interactions, then ranks one against the other.
Training & validation
Training runs in the background — kick one off and it produces a new candidate model from every active profile and every eligible interaction. The exported artifact must then load and satisfy the serving contract. A candidate that passes publishes automatically.
A/B testing
Functional validation proves that a model can serve; real usage shows whether it is better. Two ready-made experiments let you find out: put the model up against a simpler heuristic, or a new model version up against the current one. Each splits traffic by a feature flag and measures engagement and positive feedback.
Keep exploring
How candidates are generated, ranked live, and tuned by feedback.
The candidate generators — trending, co-engagement, and the live model.
Named surfaces that assemble a ranked set for any spot in your app.
Turn profile attributes and segments into what personalizes a feed.