Team: AssistInt

Team Participants:
  • Alex Ronce
  • Isha Santhosh
  • Leslie Segovia
  • Ruby Osorio
  • Phone Nay (Richard) Myo

“Millions of people apply for jobs every year, but nearly none of them get realistic practice before their initial interview.” 

Problem

Students preparing for technical and non-technical job interviews need interactive, multi-modal mock interview practice across behavioral, design, and technical dimensions, but career services staff have limited time for repetitive initial practice sessions. This includes scheduling and delivering one-on-one mock interviews covering voice-based behavioral questions, whiteboard design exercises, and live coding challenges. This time-intensive, staff-dependent model consumes significant scheduling and delivery time that could be better spent on personalized coaching and advanced interview preparation. With student demand for practice spanning multiple interview formats, the existing workflow cannot scale to meet volume across voice, whiteboard, and coding sessions. The heavy reliance on staff-led repetitive practice sessions creates a capacity gap that leaves students under-prepared and less confident heading into actual job interviews, particularly for high-stakes technical roles.

Technical Solution

The AssistInt team developed a multi-modal AI interview assistant that conducts realistic mock interviews across behavioral, design, and technical formats, delivering structured feedback after each response. The solution accepts a target job description (e.g., via link) and dynamically generates relevant interview questions, then interactively assesses student responses per-question across voice, whiteboard, and coding modalities. The platform uses natural language processing for behavioral interviews, visual analysis for design exercises, and code execution for technical challenges, providing immediate, actionable feedback. For voice interactions, the system leverages Amazon Nova Sonic speech-to-speech on AWS Bedrock for low latency conversational capabilities. By automating initial mock interviews, the system offloads repetitive practice from career staff, allowing them to focus on advanced coaching while improving student readiness and confidence at scale.

Showcase

Presentation Recording A recording of AI Summer Camp students presenting their project.
Slideshow The accompanying slides shown in the video.

About the DxHub

The Cal Poly Digital Transformation Hub (DxHub) is a strategic relationship with Amazon Web Services (AWS) and is the world’s first cloud innovation center supported by AWS on a University campus. The primary goal of the DxHub is to provide students with real-world problem-solving experiences by immersing them in the application of proven innovation methods in combination with the latest technologies to solve important challenges in the public sector. The challenges being addressed cover a wide variety of topics including homelessness, evidence-based policing, digital literacy, virtual cybersecurity laboratories and many others. The DxHub leverages the deep subject matter expertise of government, education, and non-profit organizations to clearly understand the customers affected by public sector challenges and develop solutions that meet the customer needs.