You can implement AI Commerce Search for your ecommerce application.

When you use recommendations or search, you
ingest user event and catalog data and to
serve predictions or search results on your site.

The same data is used for both
recommendations and search, so if you use both,
you don't need to ingest the same data twice.

The average integration time is in the order of
weeks. Note that for search, the actual duration depends
heavily on the quality and quantity of data to ingest.

> [!WARNING]
> **Warning:** Never cache personalized results from an end user, and never return personalized results to a different end user.

## AI commerce integration overview

![Get started with AI Commerce Search integration](https://docs.cloud.google.com/static/gemini-enterprise-cx/ai-commerce-search/images/get-started-commerce-integration.png)

## Migrate in four phases

Migrating your search engine is a structured, four-phased approach that helps to ensure that every aspect of the migration is addressed to minimize risks and maximize your investment.

Manage the expectations of your merchandising teams and sellers by doing the following:

- **Keep merchant teams informed**: Proactively communicate the changes that are coming and why the company is moving to an AI-first approach.
- **Educate teams on the new paradigm**: Explain that the system is based on user behavior and intent detection, which leads to a more personalized product ranking. The search results look different.
- **Set clear guidelines for business rules**: Emphasize that business rules can be applied only for specific, data-backed business reasons, such as contractual obligations or a clear revenue-driving strategy. The goal is to let the AI do its job.
- **A/B test new rules**: If a new rule is proposed post-migration, the most data driven way to validate its effectiveness is to run another A/B test, one group with the rule, one group without the rule. Let the data decide whether the rule is promoted to production.

By diligently following this four-phased approach, a typical migration to A/B testing can be achieved in about two to three months, depending on the current search system complexity and speed of execution. This methodology has been designed and proven across numerous customer adoptions.

> [!NOTE]
> **Note:** Attempting to sprint through or skip steps can cause rework and delays.

<iframe src="https:///frame/gemini-enterprise-cx/ai-commerce-search/overview_a38c82517652d513244c22109f2cca9ad69c2300382925b5a03667fc12b8cc1c.frame" class="framebox inherit-locale " allow="clipboard-write https://" allowfullscreen is-upgraded></iframe>

## Onboarding best practices

When onboarding to AI Commerce Search, the primary driver for quality search results and performance is the ingested data. AI Commerce Search performance (relevancy, ranking, and revenue optimization) is extremely sensitive to the uploaded data, including catalogs, product info, and user events.

AI Commerce Search has multiple dashboards and data quality checks in place to ensure that any issues or potential flaws in the data or data schema are flagged. If data flaws are overlooked from the start, the model won't train accurately and an initial A/B test does not produce the expected results, the root cause being more often than not the catalog or user data rather than AI Commerce Search itself.

Click these links to jump to the best practices section for integrating each of these AI Commerce Search components:

- [Product catalog best practices](https://docs.cloud.google.com/gemini-enterprise-cx/ai-commerce-search/catalog.md.txt#product-levels)
- [User events best practices](https://docs.cloud.google.com/gemini-enterprise-cx/ai-commerce-search/user-events.md.txt#user-events-best-practices)
- [Integration and configuration best practices](https://docs.cloud.google.com/gemini-enterprise-cx/ai-commerce-search/serving-control-rules.md.txt#integration-best-practices)
- [A/B experiments best practices](https://docs.cloud.google.com/gemini-enterprise-cx/ai-commerce-search/a-b-testing.md.txt#best_practices_for_ab_experiments)

## Terms of Service

Product usage is under Google Cloud's [Terms and Conditions](https://cloud.google.com/terms) or relevant
offline variant. The [Google Cloud Privacy Notice](https://cloud.google.com/terms/cloud-privacy-notice)
explains how AI Commerce Search collects and processes your personal information relating to the
use of Google Cloud and other Google Cloud services.

For quality assurance, a small sample set of search queries and search results
from the logs, which include customer data, are sent for
human rating to third-party vendors [disclosed as Third-Party
Subprocessors](https://cloud.google.com/terms/subprocessors) for search.
Additional tests using search queries and search results from Google Search logs
that are publicly collected datasets are sent for human rating to different
third-party vendors for quality assurance. The Google Search logs are
not categorized as customer data.