Bronze Mobile Technologies, Applications and Software Design · 2024
Wel AI Personal Email Assistant App
- A' Design Award 2024 Bronze Winner in Mobile Technologies, Applications and Software Design
- Awarded April 15, 2024
- CLIENT: Ruoyong Hong and Qian Wan
- Estimated Number of Design Views: 31,278
- Verification code C3C52662E3 · Verify this award
About Wel AI Personal Email Assistant App
The concept integrates AI into daily email processes, facilitating analytical reading and offering a conversational approach to seamless email composition, guidance, and drafting. The design stands out for creating a flexible and respectful collaboration between humans and AI, provides assistant that is just right. The design also cultivates a personal writing style and a social relationship library, benefiting both the user and the AI, encouraging growth and improvement like a supportive buddy in life.
Press Kit
- Unique Properties
- The concept integrates AI into daily email processes, facilitating analytical reading and offering a conversational approach to seamless email composition, guidance, and drafting. The design stands out for creating a flexible and respectful collaboration between humans and AI, provides assistant that is just right. It then cultivates a personal writing style and a social relationship library, benefiting both the user and the AI, encouraging growth and improvement like a supportive buddy in life.
- Dimensions & Packaging
- The design is for iOS system and responsive adapting to fit other mobile platform.
- Tags
- Email App, ChatGPT, Conversational AI, Personal Assistant, UX, Writing
- Production Technology
- Using Figma and Photoshop, the design creates an intuitive interaction flow and polished visual system. it uses human centered approach, then starts with user research, transitions to design exploration, and concludes with prototype testing. The product integrates GenAI for text tone and intent analysis, drawing insights from prompts in a writing and relationship library. It reviews user daily actions like and selection to continually optimize performance and closely align with user personality.
- Design Challenge
- Emails blend personal context with universal knowledge. Our goal was an evolving AI buddy that aids and grows with users, diverging from standard chatbots. The design needed seamless integration into daily email activity, avoiding constant screen switching or text box button. Externally, technology constraints barred us from a tangible demo, making it challenging to learn user-AI behaviors. This initiative marks a pioneering stride towards AI companions seamlessly embedded in daily routines.
- Project Duration
- The project started in May 2021 and finished in Sept 2022, in Seattle.
- Operation Flow
- Wel AI uses tags throughout the app, make text heavy tasks easier. On launch, it shows a brief of emails with tags of purpose. A swipe up reveals an detailed list. Swiping left or right transitions between Assistant and Librarian modes, representing work and train mindsets. In the email view, swipe up to displays in depth analysis or seeks AI guidance. It use of blue and white shades subtly communicates the depth of AI involvement, blending trust with clarity, like a buddy in life.
- Research
- User interview using AI prototype with scientist are conducted to understand user needs and how user would interact and growth together with AI as well as the feasibility of technology. Diverse email users, from students to professionals are invited. User persona, flow map, affinity map and process mining are used to reveal fluctuating AI assistance and trust based on user confidence and context familiarity in tasks. Together with human-centered UX design, the insights shape the core concept.
- Inspiration
- In the AI copilot era, the hardest part is integrating AI into personal email systems without overshadowing people own essence. Designing a personal tutor instead of AI ghostwriter for daily communication is a unique approach. Inspired by adept writing buddy, this innovation respects user personality, fostering a sense of control and trust, while enhancing communication efficiency and nurturing a personal AI style, seamlessly integrating into daily activities.
Colors of Wel AI Personal Email Assistant App
Design Interview about Wel AI Personal Email Assistant App
The inspiration behind the project “Wel AI” comes from observing that people often struggle with writing proper emails or messages for various situations. There are many potential solutions to this problem, ranging from searching for templates to purchasing writing services. However, one idea stood out – an AI assistant for composing emails.
While this is not a new concept, existing AI software still falls short in providing substantial help. Simply detecting tone and replacing words is not enough. We began with thorough user research and open conversations with various individuals. Through this, we learned about the current state of writing assistant apps and services, and we identified significant opportunities in this market.
While this is not a new concept, existing AI software still falls short in providing substantial help. Simply detecting tone and replacing words is not enough. We began with thorough user research and open conversations with various individuals. Through this, we learned about the current state of writing assistant apps and services, and we identified significant opportunities in this market.
The goal was to create a mobile-based writing assistant that integrates AI into daily email processes, facilitating analytical reading and offering a conversational approach to seamless email composition, guidance, and drafting. The design stands out for fostering a flexible and respectful collaboration between humans and AI, providing assistance that feels just right. It cultivates a personal writing style and a social relationship library, benefiting both the user and the AI, encouraging growth and improvement like a supportive buddy in life.
I plan to continue researching and exploring how the latest AI technology can be integrated into this design concept. Building a personal contact library and offering writing assistance that is sensitive to people with different national backgrounds are key areas of focus. I also aim to promote “Wel AI” to a diverse audience to identify customization opportunities and ensure the app meets the needs of users from various backgrounds.
The design was initially conceived as a UX research initiative focusing on trust in human-AI collaboration in the summer of 2018. It has evolved significantly since then. With insights from the research phase and the expertise of AI scientists, I spearheaded the development of this proof-of-concept app as the lead designer in 2022. Therefore, it took approximately 3-4 years from concept to design, predating the popularity of ChatGPT.
At the time of the initial concept, suggestion-based AI systems were insufficient, and people continuously sought further help from AI for email writing. There was a growing desire for AI to assist in a customized way. However, when we turned this idea into a product, the issue of trust in AI emerged. Would people want a "robot" to represent them? How far would they like AI to help, and in what ways? This led me to explore a design that could bridge this gap and establish a new pattern of interaction with AI in writing.
This design distinguishes itself from two main concepts. Firstly, traditional email writing assistance products focus primarily on word or emotional detection, with the best ones helping to rephrase individual emails. In contrast, our design leverages previous conversations and emails to build a personal library, enabling users to write in their own tone and cater to their social connections. Secondly, unlike AI conversation products, Wel AI introduces a more integrated interaction by providing AI assistance step by step, rather than controlling everything through typing or talking to the AI. Users can choose the level of assistance they feel is just right from Wel AI.
I utilized a variety of design tools to aid in the development and execution of the design. Using Figma and Photoshop, I created an intuitive interaction flow and polished visual system. The project followed a human-centered approach, starting with user research, transitioning to design exploration, and concluding with prototype testing. The product integrates GenAI for text tone and intent analysis, drawing insights from prompts in a writing and relationship library. It reviews users' daily actions and selections to continually optimize performance and closely align with their personalities. Key design tools included user research methods such as interview guides, note-taking apps, and audio/video recording devices.
Beyond its AI features, the most unique aspect of Wel AI is the intuitive swipe interaction logic and clear visuals that separate user input from AI input. Wel AI uses tags throughout the app to make text-heavy tasks easier. On launch, it shows a brief of emails with tags indicating their purpose. Swiping up reveals a detailed list, while swiping left or right transitions between Assistant and Librarian modes, representing work and training mindsets. In the email view, swiping up displays in-depth analysis or seeks AI guidance. The use of blue and white shades subtly communicates the depth of AI involvement, blending trust with clarity, much like a supportive buddy in life.
Yes, my design is heavily influenced by data and analytical research. We conducted user interviews using AI prototypes alongside scientists to understand user needs and how users would interact and grow with AI, as well as to assess the feasibility of the technology. We invited more than 10 users from diverse backgrounds to try and use the prototype of this design. Additionally, we conducted multiple rounds of quantitative research to gather detailed design feedback.
Our research included a diverse group of email users, ranging from students to professionals. We utilized tools such as user personas, flow maps, affinity maps, and process mining to reveal how fluctuating AI assistance and trust are based on user confidence and task context familiarity. Combined with a human-centered UX design approach, these insights significantly shaped the core concept of our design.
Our research included a diverse group of email users, ranging from students to professionals. We utilized tools such as user personas, flow maps, affinity maps, and process mining to reveal how fluctuating AI assistance and trust are based on user confidence and task context familiarity. Combined with a human-centered UX design approach, these insights significantly shaped the core concept of our design.
Grand Interview about Wel AI Personal Email Assistant App
The key to achieving this balance lies in our deep understanding of how AI processes and transforms human input. Through extensive testing and iterations, we carefully observed the differences between human communication styles and AI-generated content. Our most innovative approach was moving beyond standard neutral tags like "formal" or "polite" to introduce what we call the "Your Style" tag. This tag starts as a blank canvas and learns from both the user's original inputs and their subsequent refinements, creating a personalized style profile.Rather than simply having AI write emails, we're using AI to help users understand and refine their own communication style. Through this long-term learning process, users can improve their expression accuracy while the AI develops a deep understanding of their unique voice. Unlike traditional approaches where everyone gets the same "formal" or "professional" options, each user's style tag evolves differently, reflecting their individual communication patterns.
The design learns from two primary sources: the continuous flow of email communications and user interactions with the platform. By analyzing both outgoing and incoming emails, the AI builds an understanding of relationship dynamics and communication patterns. This is complemented by our unique "Your Style" tag system, which evolves as users draft, refine, and optimize their messages with AI assistance.For social relationship management, we analyze email exchanges to create detailed contact profiles. After each interaction, we update these profiles and present users with refined relationship tags, such as team member or client, along with interaction history summaries. This creates a comprehensive social relationship database.Importantly, we've implemented what we call "progressive assistance." Rather than immediately taking over email writing tasks, we start with subtle suggestions and gradually increase AI involvement as both the user and system mature. If users show hesitation or uncertainty, we scale back the assistance level. This approach ensures that users develop their communication skills alongside the AI, creating a collaborative growth experience rather than dependency.
Our research revealed several fascinating insights about human-AI interaction. First, we discovered that the boundary of acceptable AI assistance isn't fixed but rather dynamic, expanding or contracting based on user trust and AI performance. Users initially prefer minimal AI involvement, but as trust builds through successful interactions, they become comfortable with more comprehensive assistance. However, this comfort zone can contract if the AI makes mistakes, creating a breathing dynamic boundary.Second, we found that maintaining user control over final decisions is crucial, even in cases where users trust the AI completely. This is similar to having a launch button for a rocket – the final control should always rest with the human operator, providing a sense of agency and responsibility.Perhaps most surprisingly, we discovered that users often prefer AI that writes like them rather than perfectly. Even if the AI occasionally makes minor mistakes while matching their style, users showed greater trust in the system compared to one that produced flawless but impersonal content. This insight significantly influenced our design approach, leading to the development of our personalized style tags alongside standard writing options.
The tag-based interface emerged from extensive research into existing email assistance software and understanding how users naturally categorize and process information. We observed that email summary tools were already using categorical tags, which users had grown accustomed to. Additionally, tags proved highly effective for training our language models.Initially, we experimented with traditional summary formats, but found that users struggled with processing large blocks of text, regardless of length. This led us to explore various visualization methods, including graphics, tags, and voice interfaces. We discovered that the same tags used for AI training could serve as excellent quick-reference points for users, instantly communicating key information about sender identity, purpose, and tone.The final design combines relationship tags (e.g., "team member"), purpose tags, and tone indicators to create a comprehensive but quickly scannable overview. For instance, seeing "Urgent feedback from team member" with an appropriate tone tag immediately sets the context before the user even opens the email, reducing communication anxiety and improving efficiency.
Our approach differs fundamentally from chatbots because we designed this system before the ChatGPT era, focusing purely on user needs rather than following current AI interaction patterns. Instead of forcing users into a chat interface, we integrated AI capabilities directly into the familiar email interface.The assistant is available on-demand rather than dominating the interaction. Users can activate different levels of assistance based on their needs – from simple tag summaries to phrase suggestions, paragraph rewrites, or full email responses. This graduated approach to AI assistance maintains efficiency without requiring users to engage in constant chat-style interactions for every task.The design focused on providing the right level of help at the right moment, scaling from minimal to comprehensive assistance based on user preference and context. This progressive integration approach sets us apart from chatbot-style interfaces that often force users into a rigid interaction pattern for every task.
Interestingly, in the years following our project, we've seen many AI tools adopt similar color schemes. Our choice was driven by specific psychological and practical considerations. We wanted to convey the fluid, dynamic nature of AI assistance while clearly distinguishing between AI-generated content and objective information.For AI-generated content and optimized responses, we used gradient blues to suggest fluidity and ongoing evolution. For objective information like email text and fixed tags, we maintained a clean white background to represent unchanging, factual content.The choice of blue specifically came after testing various colors. For a daily-use email tool, we wanted to avoid colors that might trigger strong emotional responses (like red or yellow) or imply definitive judgments (like green). The combination of blue and white creates a neutral, calming environment that doesn't interfere with the emotional content of the messages themselves. This allows the AI's outputs to carry their own emotional weight without being influenced by the interface design.
Our design provides a vision for future AI-assisted software that acknowledges and adapts to different levels of user needs. Whether users need quick tag summaries, word substitutions, sentence rewrites, or full response generation, the system flexibly adapts to these varying requirements based on context, content, and user confidence levels.While current AI software often provides a one-size-fits-all approach, we believe AI should be intelligent not just in its capabilities but in how it integrates into user workflows. It's gratifying to see some of our design concepts, such as clear visual distinction between AI-generated and objective content, being adopted by current AI tools.However, the key innovation we hope to see more widely adopted is the intelligent scaling of AI involvement. The future of AI assistance isn't just about making AI smarter, but about making it more contextually aware of when and how to assist users, providing a spectrum of support rather than a binary all-or-nothing approach.
These distinct modes emerged from our research showing that users approach email composition and relationship management with fundamentally different mindsets. The Assistant mode focuses on immediate communication needs, analyzing content and providing real-time suggestions for improvement, while the Librarian mode helps users organize and understand their broader network of relationships.The Librarian mode acts as a knowledge repository, helping users maintain a comprehensive view of their professional relationships and communication patterns. It provides historical context and relationship insights that inform future interactions.These modes work symbiotically – the Librarian mode's accumulated knowledge enhances the Assistant's ability to provide contextually appropriate suggestions, while the Assistant mode's interactions contribute to the Librarian's growing understanding of relationship dynamics. This dual approach creates a more comprehensive and nuanced email management experience.
My background in autonomous vehicle design significantly influenced my understanding of human-AI collaboration. In self-driving vehicles, AI assists but doesn't completely take over, with humans remaining ultimately responsible – similar to our email assistant's approach.The automotive industry taught me three crucial aspects of human-AI interaction: the importance of split-second timing, the potential for serious consequences from mistakes, and the risk of over-reliance on automation. While email communication isn't as time-critical as driving, these principles helped shape our approach to user engagement and safety mechanisms.This experience also provided valuable insights into testing methodologies for AI systems. The rigorous testing requirements in automotive applications helped us develop robust verification processes for our email assistant, ensuring reliability while maintaining user agency.
Our award-winning approach demonstrates that ethical AI integration isn't just about capability limits – it's about thoughtful implementation that respects user agency and promotes growth. We've shown that AI can enhance rather than replace human communication skills through our progressive assistance model.The app contributes to the ethical AI conversation in three key ways. First, it demonstrates how AI can preserve and enhance individual communication styles rather than standardizing them. Second, our transparent approach to AI involvement, clearly indicated through visual design, sets a standard for honest AI integration. Finally, our focus on user growth rather than dependency shows how AI tools can empower rather than replace human capabilities.We believe this approach can serve as a model for future AI tools, showing how to balance automation with human development, and how to integrate AI assistance while maintaining user autonomy and authenticity in communication.