Going to production

AI Personalization is now available in public beta. Migrate now to personalize search results based on historical and predictive user affinities.

After collecting events and configuring your strategy, you can begin to personalize search results for your users.

Since Personalization can have an enormous impact on your relevance and search experience, before deployment you should:

1. Simulate Personalization
2. A/B test it with some users to confirm that it outperforms a non-personalized experience.

After A/B testing, when you’re ready to deploy Personalization:

1. Include enablePersonalization and userToken parameters for all searches you want to personalize. For details, see Enabling Personalization.
2. Check your implementation against the Personalization checklist to ensure you’ve covered everything.