Insigmind is B2B automobile supplier management Saas platform that provides AI-assisted purchasing solutions to car companies.
Automobile part suppliers currently have to personally go to car companies and talk with buyers, which is time-consuming and a major cost.
Car company buyers cannot efficiently find the suppliers that are most specialized in the products they need and can offer the lowest price.
Buyers often have to buy various products from different suppliers at multiple locations. They have to individually connect with them personally, which is high in time and cost.
Suppliers wants to connect to buyers who are in need of their products.
Buyers wants to find suppliers who could sell them products at the best rate.
Insigmind brings suppliers and buyers to the same platform
As the lead UX designer, I focused on balancing user-centered design methodologies and upper management’s business needs to lead the design of the following areas.
I will showcase the AI-Guided Supplier Data Search Project here.
Prior to this project, the team has been busy gathering supplier data and creating a backend database to store it. But now that we do have the data, the question is what do we do with it?
An Initial Exploration Based on Assumptions
In this first stage, we have not officially conducted user research for this project yet. Instead, I conducted several interest-gauging meetings with the two founders, who both have worked as buyers for more than 25 years.
From these expert interviews, I understood that there are three mains ways buyers often use to look for suppliers.
Based on this knowledge, I mapped out the three types of user flows:
Here are the screens to sketched out to show an initial idea of how buyers might look for suppliers based on their user flows.
Research-Informed Design
When testing my initial explorations from stage 1, we realized that buyers don’t follow the three ways to explore suppliers as we assumed.
Most of the times, users ignored the three search conditions on the top of the search bar
If the buyer knows what they want, they would go directly to the search bar and type it. The three conditions were actually seen as obstacles that stopped them from smoothly going to the next page.
Most of the times, buyers don’t know the exact term they are searching for. They put in any related information they could think of.
We would allow buyers to search for anything they can think of in this search bar, similar to search engines such as Google. Instead of asking them to categorize their search into the three buckets, we categorize the results instead.
We decided to design an open-ended search bar and categorize the results instead.
Returning to the Business Goal
At this stage, we had a series of meetings with product leads to revisit Insigmind’s unique business goals. The current supplier search design doesn’t reflect our core business goal that differentiates Insigmind from other products.
We introduced the idea of category curation.
Identify what products the supplier specializes in
Place these suppliers into categories based on their specialties
When user searched for a product, they would be taken to the category with all suppliers that are top in the industry at the product
The core difference from other search engine is that Insigmind’s unique category system analyzes the user’s vague search words and provides more concrete and curated results.
While I was busy meeting with management to find a better product direction that focuses on this business model, the dev team is already building the AI logic that would take care of the process of parsing through the user’s search words to form connection with our categories.
At this stage, I thought it crucial to work with developers to make sure I understand the AI logic.
Designing for a User-AI Collaboration Search Workflow
Users directly start typing when they are presented with a search bar in our task study.
So we placed a search bar in the very center. All search activity can be done in here, following the Google one-search-bar pattern. This is simple, straightforward, and establishes Insigmind’s core workflow.
Business Model utilizes categories to curate suppliers based on the buyer’s need of specialty products.
So we leverage an LLM model to parse through the user’s search words, which could be freeform and vague at times, and match them to potential categories.
User is often unsure about what their specific needs are. They use this platform to help identify their needs.
So we provide them with several categories to choose from, all recommended through LLM’s analysis of their key words. Each would generate a list of available suppliers they could then contact with our internal communication hub.
