Future-Ready AI
Product Design

Revolutionize software interactions through natural human language, transforming HCI in to natural language prompts using accurate, fast, and affordable AI agents.

Project overview

Collaborated with NEXA.AI, a tech company to redesign their on-device AI Agent platform tailored for various B2B use cases. The platform empowers businesses to build their own AI tools efficiently by leveraging our product and APIs.

Design Challenges

  • Introducing a Novel Technology: With no similar products in the market, we faced the challenge of presenting a brand-new technology in a way that is easily accepted and understood by users.
  • User Onboarding: There was a lack of guidance for users to try the system and see its benefits.
  • Complex Technology Visualization: The technology is complex and not user-friendly, making it difficult for businesses to understand what we can do and our advantages.

Objectives

Design a user-friendly product, and effectively introduce the abilities of Nexa's AI Model.

Information

Type
AI Web App Design
Platform
Website
My Role
UX Designer & Researcher
Design Methods
User Surveys | Personas | Competitive Analysis | Journey Maps | Content Strategy Map
Visit DrayEasy Web

Pre-launch Research

01 Understand the Market

01 Smaller, Efficient Models

Due to increased cloud computing costs and hardware shortages, the trend is shifting towards smaller, more efficient AI models.

02 Multimodal AI

AI models capable of processing and integrating multiple types of data.

03 Enhanced NLP Capabilities

Models are becoming more adept at understanding and generating human language.

02 Define the Product’s Value

NEXA AI envisions a world where software interactions occur through natural human language. We aim to transform human-computer interaction from GUI interactions to natural language prompts using accurate, fast, and affordable AI agents.

Design Process

01 Original Version product

API playground

API playground-Hover Code

02 Main Problems After Launch

03 After Launch Research

After launching the first version of our platform, we proactively gathered user feedback to understand how well the product met user needs and where improvements were necessary. We utilized platforms like Product Hunt for broad user insights and conducted several in-depth user interviews to delve deeper into specific user experiences.

To thoroughly address issues that might hinder user adoption, we revisited our user personas and divided our primary target users into two categories: non-technical users (such as business marketing staff, designers, or personnel from other departments) and technical users.

For non-technical users, we optimized technology visualization and refined textual descriptions to make the platform more accessible and understandable.

For technical users, we added a comprehensive documentation page that aligns with their familiarity with code and technical products.

Revised Design

01 Website Showcase

02 Product Playground

03 Documentation

04 Video Prototype