This page describes Vertex AI Search for commerce conversational commerce, a guided search capability. Conversational product filtering must be enabled to use conversational commerce. The general conversational commerce capability functions as part of the guided search package, providing users with a real-time, ongoing conversational experience that is more interactive.
What is conversational commerce?
Conversational commerce is an AI-driven guided search and product discovery tool. Instead of searching with keywords, users utilize natural language to ask for what they need, which includes follow up questions, multimodal interactions, improved intent understanding, and grounding with data beyond the product catalog. This approach enables more intuitive and efficient results filtering, helping users find more precisely and more quickly what they are looking for.
Conversational commerce capabilities
Conversational commerce adds to the Vertex AI Search for commerce experience in the following ways:
- Narrows user queries effectively: Conversational commerce filters 10,000 products down to less than 100 products, increasing the likelihood that the user decides to make a purchase.
- Hyper-personalization: Search agents analyze shoppers' preferences, purchase history, and social media activity to provide more personalized product recommendations, promotions, and shopping experiences.
- Integrated end-to-end journeys: From product discovery to checkout, the search agents accompany the end user along their entire shopping journey with immersive, dynamic, and continuous conversation.
- Adapted to commerce use case: Conversational commerce covers ecommerce, product discovery, and support.
- Immersive user experiences: With the help of search agents threading user conversations, augmented and virtual reality can be additionally implemented on the merchant site to create virtual try-ons, store tours, and spatial product visualization.
Impact of conversational search
As a central part of the guided search package, conversational commerce improves search result relevance and reduces user friction.
Customary commerce search is the most common way to find products. Customary approaches rely on rigid keyword matching, requiring users to use specific words and manually adjust filters to refine results. However, only 1 in 10 consumers say they find exactly what they're looking for when utilizing legacy keyword-based search.
Conversational commerce solves the most frustrating problems for users when searching, such as inexact matches, irrelevant results, or zero-return queries.
Natural language understanding
AI-powered search recognizes full-phrase queries, interprets intent and accounts for variation in language.

Predictive assistance
Helps users formulate queries more effectively by suggesting completions as they type.

Mobile-first experience
Nearly 80% of all ecommerce visits worldwide occurred on a mobile phone in 2024. Smaller screens, shorter user sessions and clustered menus create unique challenges for legacy search experiences. Conversational commerce is designed to enable users to access the full power of AI-driven search from their mobile devices.
The role of external search and AI assistants
When a user has a preferred retailer, they tend to go directly to it. However, when exploring new or broader options, the customer user journey is more likely to first start at a marketplace orientation, such as Google Search or an AI assistant.
As AI-driven search evolves, the Vertex AI Search for commerce guided search package bridges the gap between external and on-site product discovery. By treating the transition to the commerce site as a single, fluid conversation, conversational commerce ensures users find relevant results quickly.
Multimodal inputs
Conversational commerce enables users to search using multimodal input methods such as voice and image, in addition to text. It understandings user intent, context and natural language variations in phrasing without losing context.


- Voice search: Spoken queries are often structured differently than typed ones. Vertex AI Search for commerce processes these variations while accounting for variables like accents, background noise and "um's," "uh's" and "like's." For mobile, voice search is not only easier to input, but it can also take up less screen space, allowing more real estate product visuals.
- Image search: Image recognition makes it faster to find a similar or unique item on a social media post or by snapping a picture in real life. Shoppers can then use image search to quickly search and locate a similar item on your site.

Core principles and best practices
This section describes core principles and best practices for using conversational commerce as part of your guided search package.
Clarity and transparency
Configure your site in such a way that the shopper understands why results appear and has the ability to refine or adjust search parameters.
Ambiguous queries
When encountering a vague search, the conversational search proactively seeks clarification.

Nuanced queries
Extremely detailed queries require strong content structures and detailed metadata for Vertex AI Search for commerce to return accurate results.

User expectations
How and why specific results were prioritized must be shown with transparency for results based on the site visitor's search history.

Transparent limitations
If a query can't be understood or if it returns only limited results, Vertex AI Search for commerce lets the site visitor know and offers constructive alternatives.

Use predictive search
Provide autocomplete suggestions, predict intent, and surface relevant results instantly using historical data, trending queries, and user behavior.
Enhance filtering mechanisms
Refine results through conversational inputs to accelerate the process of getting what you are looking for.
Ranking and optimization
Prioritize the most relevant products based on context, user history, and search trends.
Reduce cognitive load
Configure Vertex AI Search for commerce to harness contextual awareness to remember a user's previous selections to minimize redundant actions and accelerate user decision-making.

Create personalization without overload
To avoid overwhelming users, dynamic filtering can strike a balance between personalization and user autonomy. Instead of overwhelming a user with too many filters upfront, conversational commerce has the capability of suggesting refinement based on preferences from a user's previous search or purchase data. Additionally, Vertex AI Search for commerce is adaptable to real-time behavior. For example, purchase history may not be relevant while searching for a gift for someone else, so conversational commerce can recognize the contextual changes and adjust accordingly.
Control features to ensure context and continuity across sessions
Rather than treating every query in isolation, contextual awareness allows for more efficient searches without repeating previous inputs. Not only should contextual awareness be pervasive within and across sessions, but also across devices to ensure continuity.
Continuity within sessions
Vertex AI Search for commerce is designed to remember a user's past interactions within a session to allow for incremental refinements.

Continuity across sessions
Site visitors should be able to pick up where they left off in a previous session without conversational commerce feeling intrusive.
Integrate accessibility and inclusivity considerations
Whether site visitors interact through voice, text, or images, Vertex AI Search for commerce must provide inclusive solutions that support individuals with varying abilities, preferences, or technological constraints.
Multimodal input support | Voice-to-text correction |
Screen reader compatibility | Real-time transcription |
Clear semantic structuring | Predictive text assist |
Voiceovers for image-based content | Autocorrect |

Use targeted questions to ensure graceful error handling
Inevitably, there are instances when a query produces no results on a particular site. Instead of an unhelpful no results message, conversational commerce offers intelligent suggestions and alternatives. Additionally, an conversational commerce prompts for clarification, asking targeted questions to narrow down preferences and needs, creating a user-centric dialogue.
Design calls-to-action to end conversations effectively
To prevent user abandonment, conversational commerce ends conversations with clear, actionable pathways, maximizing user satisfaction and boosting the likelihood of conversion by maintaining momentum. Furthermore, conversational commerce can create opportunities for re-engagement after the initial interaction by surfacing relevant follow-up questions based on browsing activity or purchase history.

Practical guidance for web interface optimization
This section comprises a practical guidance for how to optimize your guided search components in Vertex AI Search for commerce.
Search optimization checklist
Take these steps to avoid common pitfalls:
Simplify the experience
A simplified user experience reduces cognitive load and ensures that users can quickly find what they are looking for without unnecessary distractions. This means:
- Minimizing the steps in the process.
- Keeping interfaces clean and intuitive.
- Streamlining AI suggestions.
Avoid misleading or irrelevant personalization
Irrelevant or misleading results can quickly frustrate users.
Understand intent and VIP questions
To refine intent, conversational commerce prompts users with relevant questions. Therefore, conversational commerce should be configured to ask targeted questions to further reduce the number of results and reduce ambiguity.
User journey
This is an example of a desirable user conversation.
Conversational filtering
Conversational filtering guides users toward more relevant options without overwhelming them by:
- Immediately updating results.
- Suggesting genuinely useful filters.
- Labeling filters clearly.
Read more about Conversational product filtering to learn more.
Handle edge cases and errors
To make the search process is more reliable and user-friendly, Vertex AI Search for commerce can gracefully handle edge cases and errors in a number of ways:
- Surfaces closely related alternatives.
- Clearly displays stock availability.
- Suggests similar alternatives.
- Offers back-in-stock notifications.
- Provides hand-off to customer support.
Design an adaptive web interface components and patterns
This section details how user interface design can optimize conversational commerce experiences, particularly on mobile. It focuses on enhancing search input and presentation, managing conversational elements without disrupting browsing, and leveraging autocomplete, predictive search, and carousels for efficient product discovery. The section also covers strategies for presenting search results, handling ambiguous queries, and using communicative animations to create a smoother and more intuitive user journey.
Search input and enhancement
As the entry point for conversational commerce, the search box must balance clarity and functionality and, particularly on mobile where screen space is limited, it must do so with minimal disruption.
Configure autocomplete and predictive search
To reduce the need for users to type out full search terms autocomplete and predictive search reduce the need for full search terms, implement:
- Intelligent predictive assistance: Predictive terms appear within the search bar as users type, offering real-time, autocomplete suggestions in a lighter font.
- Dropdown prediction list: A dynamic list appears below the search bar, showcasing suggested queries, popular searches, and recent history
- Contextual filtering chips: Filters display below the search bar as users type, providing relevant filter options such as categories, price ranges, or brands.
- Smart corrections: Subtle autocorrect suggestions for misspelled words will be displayed in the drop-down.
Search results presentation and refinement
Optimizing search item returns through layout and refinement options can make the browsing experience smoother, ensuring site visitors can efficiently scan, compare, and filter results.
Multimodal experience
Voice search, input and transcribed text ensures a multimodal model guided search experience.
- Voice search: Voice search is intended to feel natural and effortless to the site visitor. The web interface designed to support quick, clear user interactions.
- Voice input button: A microphone icon in the search bar allows the site visitor to activate voice search, with animated indicators pulsing or lighting up to provide users visual feedback when activated.
- Streaming transcribed text: Conversational commerce can stream transcribed text as the user interacts using voice, allowing the site visitor to review and adjust their input while minimizing site clutter.
Developer's guide
Conversational commerce is supported only by the Conversational API. The conversationalFilteringMode
in the Conversational API distinguishes between conversational commerce and conversational product filtering.
- gRPC:
conversationalSearchService
- REST:
conversationalSearch
User journeys and query classifications
Conversational commerce uses search query categories to determine whether or not an LLM-based answer is generated and how user queries are handled by the Conversational and Search APIs for these user scenarios:
Session maintenance
This section describes how conversational commerce sessions are maintained by the Conversational API.
The Conversational API uses a conversation_id
to manage ongoing conversations. To begin a new conversation, the API request omits the conversation_id
. The API response includes a conversation_id
that is used in subsequent requests to continue the conversation and maintain context. To ensure consistency between LLM answers and search results, subsequent Conversational API requests include SearchParams
that mirror the configuration of the core Search API.
Conversational product filtering API integration
Conversational product filtering allows the customer to continue the conversation for basic product search queries (the simple_product_search query classification).
Modes
Refer to these sections to view code samples of how to integrate the Conversational API using one of these three modes to control conversational product filtering:
Disabled
: In this mode, the client only has the query categories, but conversational product filtering is disabled.Enabled
: In the enabled mode, the client has all conversational capabilities. This includes all the query categories and conversational product filtering.Conversational_filter_only
: If chosen, the client only has conversational product filtering. This does not include support for any of the query categories and other default conversational capabilities.
For more information on modes, see the API documentation.
Disabled or unspecified mode
Enabled mode
Conversational filtering only mode
With conversational_filtering_only
mode selected, the user experiences only conversational product filtering, without generating an LLM answer, query classification, or suggested search queries.