Inspiration
Every candidate before an interview asks the same questions: Am I speaking too fast? Do I sound confident? Should I smile more? But the truth is they never really get an answer. 48% of students fail interviews not because they lack skills, but because they lack confidence and feedback. Corporates overspend on wrong hires, universities face placement setbacks, and students are left guessing. That broken system is what inspired Evalvate.
What it does
Evalvate is an AI-powered interview coach. It provides candidates with structured, instant, and personalized feedback on their interview performance.
- AI-Simulated Interviews tailored to industries.
- Precision Analytics on clarity, tone, confidence, pacing, structure.
- Actionable Guidance with role-specific suggestions.
- Progress Dashboards to track growth over time.
For students: practice interviews + detailed feedback. For universities: batch-level analytics to improve placement readiness. For corporates: smarter hiring and reduced attrition.
How we built it
- Frontend: an intuitive student-facing dashboard for practice + analytics.
- Backend: Gemini API analyzing video, audio, and text inputs.
- Core: ML models trained to measure delivery (tone, filler words, pacing), structure (answer clarity), and confidence (facial + vocal cues).
- Reports: four-layer feedback- Delivery Metrics, Content Quality, Confidence Index, and Custom Suggestions.
Challenges we ran into
- Prompting AI to give feedback that’s human-like but objective.
- Balancing affordability for students with sustainability for us.
- Convincing universities to try something new in placements.
- Ensuring the system works across accents, languages, and technical domains.
Accomplishments that we're proud of
- Built a working prototype that gives structured interview feedback.
- Secured initial interest from universities to pilot with full student batches.
- Designed an affordable pricing model ($6/month) that’s accessible to students.
- Created a product that we ourselves, students actually use and benefit from.
What we learned
- Interview prep isn’t just about “what” you say, but how you say it.
- Students crave specific, actionable feedback, not generic “good/bad.”
- Universities want measurable insights, not vague placement reports.
- Building trust with users requires empathy we tested Evalvate on ourselves first.
What's next for Evalvate
- Scale pilots across universities in the next 6 months.
- Expand to corporates to cut down on costly mis-hires.
- Build multilingual support for diverse student populations.
- Extend beyond interviews into admissions, leadership training, and public speaking.
- Ultimately, make Evalvate the go-to platform for feedback anytime performance matters.
Try it out
Just added the frontend, we will be deploying the backend once we get our domain name.
Built With
- amazon-web-services
- facialmodel
- geminiapi
- node.js
- python
- react.js
- tailwindcss
- tenserflow
Log in or sign up for Devpost to join the conversation.