Skip to main content
Test Text Search

​
What you can do

  • Run test searches and review results in one place.
  • Switch between demo profiles to simulate different shoppers.
  • Use the Search Workbench to tune search parameters and bypass features.
  • View Query Understanding to see how your search was processed.
  • Get AI-powered explanations of the search pipeline.

​
Create a demo profile (persona)

Demo Profile
  1. Go to Evaluate → Text Search.
  2. Open Demo Profiles and click Create.
  3. Add a nickname (e.g., “US returning customer”).
  4. (Optional) Add location, past purchases, items in cart, and prior searches.
  5. Save.

​
Use a demo profile in testing

Select Demo Profile
  1. In Evaluate → Text Search, pick a profile from the dropdown.
  2. Enter a few search terms and browse the results.
  3. Try another profile to compare behavior.

​
Search Workbench

The Search Workbench panel lets you fine-tune search parameters and selectively bypass features to understand their impact on results.

​
Tuning Parameters

Adjust these parameters to see how they affect search results:
  • Textual Weight: Controls the influence of text-based matching (0-1). Higher values prioritize keyword and semantic text matches.
  • Visual Weight: Controls the influence of image similarity (0-1). Higher values prioritize visual similarity in results.
  • Minimum Match: Sets the minimum similarity threshold for results to be included (0-1).
  • Top K: Limits the number of vector matches considered during search.
  • Multiple Factor: Adjusts how multiple query terms are weighted together.

​
Bypass Options

Toggle these options to isolate specific features:
  • Bypass Cache: Forces a fresh search without using cached results.
  • Bypass Query Expansion: Disables AI-powered query expansion to see results for the exact query only.
  • Bypass Intent Modifiers: Disables automatic intent detection that may boost or filter results.

​
Query Understanding

The Query Understanding panel visualizes how your search query was processed through the search pipeline. Each step in the pipeline is displayed with its effect on the query:
  • Query Expansion: Shows synonyms and related terms added to broaden the search.
  • Query Replacement: Displays any typo corrections or query rewrites applied.
  • Query Cleanup: Shows preprocessing steps that cleaned or normalized the query.
  • Metadata Filtering: Indicates any automatic filters applied based on query context.
  • Intent Modifiers: Shows detected shopping intent and resulting boosts or filters.
  • Experiment Applied: Indicates if an A/B test variant affected the search.
  • Rule Applied: Shows any Search Rules that matched and modified the request.

​
AI Explain

Click the Explain button to generate an AI-powered explanation of why the search pipeline processed your query the way it did. This provides a natural language summary of each step and helps you understand the reasoning behind query transformations and result ranking.

​
Notes

  • Demo profiles are for testing only and don’t use real customer data.
  • If results look off, confirm your catalog is synced and search settings are saved.
  • Workbench parameter changes are temporary and only affect the current test session.
  • Query Understanding data is available after each search execution.