HackStack

Project Info

IntraView

Devpost

This project did not submit a demo video on Devpost.

Inspiration

IntraView was inspired by the need to bridge the gap between theoretical coding knowledge and real-world technical interview skills. Many candidates struggle with coding interviews due to lack of practice, real-time feedback, and exposure to diverse problem types. Our goal was to create a platform where users could simulate realistic coding interviews in a controlled and customizable environment, helping them develop both technical and communication skills necessary for success.

What it does

IntraView provides a complete AI-powered simulation of technical coding interviews. Users can select from various programming languages, adjust the difficulty level, and customize the interviewer’s persona to mimic real-world scenarios. During the interview, the AI presents coding problems, listens to the candidate’s thought process, and offers feedback in real-time based on their performance in problem-solving, communication, code quality, and time management.

How we built it

We built IntraView using React for the frontend and integrated OpenAI’s Realtime API to handle the interactive interview process. Monaco Editor was used for the code editor, and Web Audio API powers voice input/output for a seamless, voice-controlled experience. The platform includes customizable interview configurations, such as programming language selection, interview difficulty, and interviewer persona settings, to offer a personalized experience. Feedback is generated using AI and delivered based on user performance metrics.

Challenges we ran into

One of the main challenges we faced was creating a realistic interview flow where the AI could guide the interview without breaking the immersion. Another challenge was handling real-time voice input and integrating the feedback system effectively into the interview process. Additionally, designing a UI that was both functional and user-friendly for simulating technical interviews posed some challenges in balancing customization options and simplicity.

Accomplishments we're proud of

We’re proud to have created a platform that gives users a realistic and helpful interview experience. Implementing real-time voice interactions and AI-driven feedback was a major technical achievement. Furthermore, the flexibility of allowing users to customize their interview setup and receive performance-based evaluations is something we’re excited to offer to aspiring coders. Being able to deliver personalized feedback on multiple metrics was a key accomplishment as well.

What we learned

Through building IntraView, we learned a lot about integrating real-time APIs, handling audio processing in a web environment, and improving user experience in complex applications. We also deepened our understanding of how AI can be used not just for automation but for creating meaningful, interactive experiences that help users improve in technical areas.

What's next

Moving forward, we plan to enhance IntraView by introducing more interview question sets, improving feedback detail, and allowing users to receive mock feedback from multiple personas. We aim to implement deeper analytics and performance tracking to give users insight into their growth over time. Additionally, expanding the AI’s ability to provide tailored hints and suggestions during interviews would make the practice even more effective for users preparing for real-world technical challenges.

Analysis

Compare with all teams

View

Metric

Figures cover GitHub contributors during the hackathon window. A co-authored commit counts in full for each author, so per-member totals add up to more than the whole-team figures.

Technology

Found in codeClaimed only
  • CSSIn code
  • HTMLIn code
  • JavaScriptIn code
  • ReactIn code
  • TypeScriptIn code
  • OpenAIClaimed

5 of 6 appear in the indexed code. 1 claimed on Devpost could not be matched to code, which may simply mean the tool leaves no trace in the repository.

AI coding agents

No AI coding agent signals were found in this repository.

Detected from committed agent config files and commit authorship. Absence of a signal is not proof an agent was unused.

Codebase size

Source size

84 KB

Source files

24

Counts recognized source files only; vendored directories, binaries and lockfiles are excluded, so this is smaller than the repository on disk.

0 stars