Talking shop: 7 ways conversational AI agents open up possibilities for designers and developers

Remember when online shopping meant typing specific keywords into a rigid search bar and endlessly scrolling through irrelevant results? Traditional e-commerce search, while common, helps only about 1 in 10 consumers find exactly what they're looking for. 

For designers and developers, this opens up possibilities to deliver on what users expect in the AI era. But what exactly are they looking for, and how can you design an experience that both delights, and helps get them what they need?Conversational AI is a significant leap in online search and shopping, moving towards more natural, personalized, and efficient interactions. By focusing on design principles that prioritize multimodal input, intelligent query handling, rich visual presentation, transparency, and accessibility, retailers can build AI experiences that meet user expectations and transform the online shopping journey. 

Here are seven ways building conversational AI agents can improve the online shopping experience for shoppers– and how you can start designing them. 

1. Smarter search that understands you

Gone are the days of finding the  perfect keyword. AI-driven search, or “conversational” search, understands natural language, interpreting full-phrase queries, user intent, and context. This means your users can search more naturally, like asking, "What's a good jacket for hiking in a rainy climate?" or "Show me red sneakers for under $100". AI can also intelligently rank and prioritize the most relevant products based on context, user history, and trends.

To help users  find what you're looking for even faster, AI, such as Google Cloud’s Conversational Commerce agent, offers “predictive assistance”, suggesting completions as you type. When a query is ambiguous, the conversational  AI agent can proactively ask clarifying questions. This reduces friction and improves product discovery.

2. Personalized recommendations 

AI allows for a truly personalized shopping experience. It can suggest products based on users' past behavior, preferences, and interactions such as conversation history. For travel, imagine a user booking a flight. They might  prefer the window seat, and an AI agent notices that an aisle seat has been assigned to their  ticket. You can design an experience that notifies the user if a window seat is available, so they have the option to switch. However, it's important that the AI agent is transparent about why results are personalized, perhaps stating: "Recommended based on previous searches/bookings", and always clarifying that users have the ability to modify or reset their personalization options.

3. Seamless conversational interaction

Users are increasingly interested in interacting with AI in a conversational way, much like using tools such as Gemini and AI Mode. This allows designers to ask questions in natural language about product availability, differences between items, best store locations, and more. Enhanced conversational capabilities can even help designers adapt to users’ styles and offer tailored prompts. 

For example, according to our research, end users have expressed a desire for an "agentic experience" that's more engaging. Asking clarifying questions when a query is ambiguous is a key part of this interaction.

These tools also  support  multimodal inputs, allowing users to search using voice, image, or text, or any combination. Voice search is particularly valued for its flexibility and hands-free convenience, especially on mobile devices. As a designer, you could design an experience where the user uploads an image of an item they saw, and ask the agent to see it in a different color – all by using their voice.

4. Addressing frustrations and enhancing comparison

One major pain point in online shopping is the uncertainty of item availability and receiving unsuitable substitutions when items are out of stock. AI can provide real-time stock information and suggest closely related alternatives if an item isn't available.

Users also strongly desire better tools for “comparing products”, especially details like nutritional information,  specifications on tech products, cars, even clothing. They want features like a "compare" button or the ability to see differences side-by-side on a single screen. AI-generated side-by-side comparison tables are highly valued by users as they help in making decisions between products.

5. Clear visuals and user-friendly design

Seeing product pictures and visuals alongside search results is crucial for online shopping. AI interfaces can effectively present results using visual layouts and features like “carousels”, which are particularly useful on mobile to showcase multiple relevant products without cluttering the screen. For designers, we recommend the following:

• Rethink placement on mobile: For conversational features on mobile, placing the conversational UI at the top of the page pushes products down. Consider placements like the bottom of the screen, a flyout menu, or a side panel that allows users to browse products while interacting with the AI. Let the user have control over when conversation appears. 

• Prioritize a "co-browse" experience: A preferred design is an "integrated mode" where the AI assistant appears on the same page as the product results, allowing users to see products update in real-time as they refine their search with the AI. A side panel/fly-out was suggested as an ideal way to achieve this without being as cumbersome as a top-of-page element.

• Use clear and intuitive labels: Descriptive labels like "shopping assistant" clarify the feature's function.

6. Building trust and handling errors gracefully

Trust is a significant factor in user adoption of AI features. Users want clear source attribution for information provided by AI. In a shopping context, this translates to clearly showing product details, prices, and links to retailers.

When the AI can't fully understand a query or finds no results, it should handle this gracefully. Instead of a simple "no results" message, it can offer intelligent suggestions, alternatives, or prompt the user for clarification, maintaining a productive dialogue.

7. Conversational commerce components library:

We have a downloadable component library on Figma accompanying the UX use cases, that can be used as a guiding kit to utilize designs as outlined in the UX documentation. It contains a collection of reusable UI elements reflecting our tech capabilities that are pre-designed and pre-built, allowing designers and developers to quickly adapt to their particular brand needs and quickly customize and incorporate into their projects.

Components include:

• Device sizes

• Color (Black/White/Tertiary Colors)

• Typography

• Component varieties (Buttons, Filters, etc)

• Search input

• AI prompt

• More detailed results

• Light/Dark Mode

In addition to speeding up implementation, the component library empowers teams with unmatched customization capabilities. With just a few clicks, designers and developers can easily tailor the experience to reflect their unique brand identity — adjusting everything from typography and color schemes to corner roundness and layout structure. This flexibility ensures that businesses don’t need to compromise between advanced AI functionality and maintaining a consistent, on-brand user interface. The components are built to scale and adapt, offering autonomy while reducing development overhead.

Get started 

Designers and developers have the opportunity to meet consumers where they are using conversational AI. To get started with Vertex AI Search: Conversational Commerce Agent: 

• Contact sales

• View the full documentation here

• View the user experience guide here

• View the UI components library here

• View the developer guide here