Inspiration
We were inspired by Wolf of Wall Street—how Jordan Belfort could adapt his pitch to anyone. We wondered: what if people fail interviews not because they lack knowledge, but because they can’t adapt their explanation?
What it does
Our product is an AI communication simulator.
You upload a topic, and it:
Simulates different personas (investor, recruiter, layman, etc.) Asks follow-up questions Forces you to adapt your explanation in real time
It also uses voice input/output and gives feedback on clarity, tone, and jargon—so it feels like a real conversation.
How we built it
Frontend: React Backend: FastAPI Speech-to-Text: Whisper Text-to-Speech: Deepgram LLMs: Anthropic
We built a multi-agent system:
Interviewer agent (persona-based questioning) Evaluator agent (structured feedback) Session pipeline to manage real-time interaction
Challenges we ran into
Making voice interaction feel natural Handling latency vs smooth experience Designing realistic personas Ensuring reliable AI outputs with validation and retries
Accomplishments that we're proud of
We built a full end-to-end system, not just a chatbot:
Real-time voice interaction Multi-persona interviews Structured, actionable feedback
It genuinely feels like a real interview simulation.
What we learned
We realized communication is the real problem—not knowledge.
People struggle because they can’t explain things clearly under pressure. This project taught us that adapting to your audience is everything.
What’s next for Tech Explained for Dummies
We want to build a full AI communication coach:
Mock interviews with voice + video Personalized improvement tracking Integration with career platforms
Our goal is simple: Help people confidently explain anything, to anyone.
Built With
- claude
- css
- fastapi
- javascript
- python
- react
- tailwind
- vite
Log in or sign up for Devpost to join the conversation.