Interview about Curi AI Mentoring Platform , winner of the A' Mobile Technologies, Applications and Software Design Award 2025
Curi is an AI mentoring platform that leverages Agentic AI and advanced LLMs to deliver high quality career guidance. Using real mentor data, Curi dynamically matches mentees with AI mentors based on their interests, enabling seamless, pressure free interactions. Designed to address the opportunity divide linked to the digital divide, Curi democratizes access to mentorship by providing personalized, data driven career insights. Regardless of societal background, users gain an intelligent and adaptive mentor capable of offering tailored advice, bridging the gap between ambition and opportunity.
View detailed images, specifications, and award details on A' Design Award & Competition website.
View Design DetailsCuri was developed as a conceptual prototype to examine how technology can be used to reduce the opportunity divide that often stems from the digital divide. Our research began with a deep exploration into how access to devices, internet bandwidth, and educational resources influences the ability of individuals to pursue career advancement.Through a combination of quantitative surveys and qualitative interviews, we found that many users who would benefit most from mentorship lack access to personal laptops or consistent internet. Text-based and asynchronous mentorship emerged as the most accessible option for these users.These findings informed the prototype’s core functionalities. Curi was designed to offer low-bandwidth, mobile-friendly, text-first interactions that are accessible in environments with limited connectivity. We are now preparing for implementation within the next year based on these research insights.This work would not have been possible without the dedication and talent of our global team, including Lauren Choi, Seongbin Lee, Hyunjong Joo, Giah Kim, Hyobin Cho, and Yeji Shim.
As a conceptual prototype, one of the most complex challenges we faced was designing an AI system that could simulate the empathy and authenticity of human mentorship. While AI is powerful in delivering information, mentorship involves nuance, reassurance, and context.We created detailed prompt structures and sample dialogues modeled on real mentor interactions. These helped shape how the AI mentor should respond based on different levels of user experience and career readiness. Our team was also attentive to avoiding bias and ensuring cultural sensitivity across different contexts.As we move toward implementation in the coming year, we plan to use feedback from real users to improve the personalization and emotional intelligence of the AI system.
Our global team brought together a variety of lived experiences that played a central role in shaping the conceptual prototype. Designing Curi to be both accessible and relevant across regions required us to account for differences in cultural norms, communication styles, and mentorship expectations.Seongbin Lee, based in Singapore and fluent in English, Korean, and Chinese, brought insight from his life in South Korea, China, and Japan. His contributions in software and user research helped us test the assumptions we might have made within a single regional context.This international collaboration allowed us to build a more inclusive foundation for the platform. As we move toward implementation, we will continue to incorporate perspectives from our global team to ensure Curi’s accessibility and cultural relevance.
Our research showed that users affected by the opportunity divide often feel anxious about asking basic or sensitive questions. They may fear being judged or appearing uninformed, which can deter them from seeking guidance through traditional mentorship.With this in mind, the prototype was designed to create a nonjudgmental space where users could ask anything. The AI mentor is presented as an approachable and confidential source of guidance, particularly for questions about career exploration, salary expectations, and educational pathways.The goal is to help users build foundational confidence before connecting with human mentors for deeper conversations. As we prepare for implementation, we are prioritizing user testing to refine this experience and ensure the environment remains welcoming and empowering.
When designing the conceptual prototype, we focused on using AI not just as a tool for information delivery but as a medium for meaningful conversation. We carefully crafted interactions that simulate warmth, empathy, and relevance, all qualities that mentees expect from human mentors.We used OpenAI’s API to test different types of prompts and response formats, combining them with user scenarios informed by real mentorship sessions. These shaped the tone and pacing of the AI mentor in the prototype.As we move toward implementation, we will continue iterating on these conversations with feedback from diverse user groups to ensure that the technology remains grounded in a human-centered approach.
Our conceptual prototype introduced a dynamic matching system where users identify their target industry, role, and location. Based on this input, the system pairs users with AI mentors trained on real-world insights from those fields.We also designed a flexible tag system to simulate personalization and created personas that reflect different types of career journeys. These initial frameworks allow us to imagine how AI mentors could evolve alongside a mentee’s interests.For the implementation phase, we plan to expand this matching system by integrating user analytics and feedback loops to improve alignment between users and AI mentors over time.
Our decision to design for mobile first was based on research into the behaviors of users most affected by the digital divide. Many of these users rely on smartphones as their primary or only device for internet access, while personal laptops remain out of reach for some.We optimized the prototype for iPhone 14, 15 Pro, and 16 models, as those were the devices available to our team for internal QA and usability testing. This helped us rapidly test and iterate key flows in a realistic mobile setting.Moving forward, we are planning a responsive desktop version of the platform. This will allow users to transition seamlessly between devices, depending on what is most convenient for them.
The conceptual prototype used anonymized mentor insights collected from interviews, mentoring programs, and open data sources. We reviewed and synthesized this information into categorized themes that could guide AI mentor responses.To simulate a realistic experience, we used the curated content to train our prompt structures and define the tone of the AI mentor. We focused on making sure that responses would feel helpful, relevant, and respectful.As we move into the implementation stage, we are exploring more formal partnerships with mentors and organizations to scale this data collection ethically and with high standards of accuracy.
At Cogito, our mission is to use design and technology as tools for social empowerment. Curi embodies this mission by addressing a real-world barrier that prevents many people from reaching their full potential.The platform was conceived as a prototype to test how mentorship could be reimagined for individuals affected by the digital divide. The results of this work reinforce our belief that thoughtful technology can create real access and opportunity.I am especially grateful to our interdisciplinary team for their shared vision and commitment to social impact. Their dedication ensures that Curi stays aligned with Cogito’s values as we bring it to life in the next year.
Curi was submitted to the A’ Design Award as a conceptual prototype designed to gather insight and inspire dialogue. Since that time, AI tools have continued to evolve, opening new possibilities for mentorship delivery.Over the next year, we plan to implement additional features including voice-based interaction and a more expressive AI mentor interface with 3D visuals. These enhancements are intended to make mentorship feel even more personal and engaging.We are also exploring integration with real-time labor data and language support features so that Curi remains relevant and inclusive across different geographies and career paths.
Dive into a world of design excellence with our curated highlights. Each feature showcases outstanding creativity, innovation, and impact from the design world. Discover inspiration and learn more about these incredible achievements.
