CareerQuest
by Nav, Arjun
An AI-powered adventure game that transforms career discovery into an immersive, runner-style simulation, complete with a per
The idea
CareerQuest is an AI-powered adventure game that helps students discover and prepare for future careers by combining Temple Run-inspired exploration, immersive career simulations, behavioral AI, and a Tavus-powered mentor that guides them through every step of their journey.
What it does
- Create a profile and start the Discovery Run - Explore 5 career worlds through interactive challenges - Get real-time coaching from a Tavus AI mentor AI analyzes gameplay to identify strengths and interests - Receive a personalized Career Compass with recommended career paths - Choose a career world to dive deeper into with advanced challenges and simulations
How it works
CareerQuest is built on a decoupled, stateless full-stack architecture optimized for low-latency gameplay and real-time AI generation: Frontend (Lovable & React): The interface powers a responsive, lane-mechanic runner game tracking real-time user selections, scores, and paths chosen. It handles video avatar streaming via the Daily JS SDK by dynamically hooking into remote audio/video media tracks for seamless, click-to-join mentor sessions without embedding restrictive iframes. Backend (Cursor & Node.js/Express): A stateless REST API that houses the game simulation math, evaluates behavioral metrics, and aggregates performance data on the fly. AI Orchestration & LLMs: When a gameplay level finishes, the backend processes student behavior and calls the Claude API (Anthropic) to generate tailored pedagogical textual feedback. This context is dynamically passed into field-specific system prompts. Immersive Video Mentor (Tavus API): The backend communicates with Tavus via a secure server-side environment (.env) to dynamically generate real-time conversational streaming rooms. This maps personalized system prompts to custom video avatar personas—like Sam Park for Business or Mx. Chen for Engineering—creating an interactive, face-to-face AI coaching experience
What's next
Here is our detailed outline : https://canva.link/wzyus2er3dm0bjg
■ Event Recap · June 27, 2026 · Tavus HQ
PALmaker × LovableHACKATHON
Built with PAL Maker + Lovable, together with the ProductTank SF community — Tavus HQ, San Francisco, June 27, 2026.
Chapter 01 / 04
Doors open.
Welcome, builders — badges on, credits claimed, countdown running.
The winners
On the podium
■Judges' favorites
Ten more that stood out
The full lineup
A–Z
■ The judging panel
Eleven judges. Every build scored.
★ THE JUDGING PANEL
- 01Saswat MishraProduct @ Hyperbound
- 02Gagan BhatApplied AI @ Anthropic
- 03Gaurav MahajanEngineering @ Apple
- 04Ankit SultanaEngineering @ Notion
- 05Karsh PandeyProduct @ Virta Health
- 06Zane HomsiProduct @ Glean
- 07Kelly PengFounder @ First Intuition
- 08Rohan BenkarEngineering @ Coursera
- 09Darius KarelEngineering @ OpenAI
- 10William GaoMentor @ StartX · stealth founder
- 11Karthik Ragunath Ananda KumarAI Research @ Tavus
■With thanks
Our hosts
■June 27, 2026