# Project export: The Duck You Mean? This document was generated by HackStack to give an AI agent context about a hackathon project. Sections are labeled with their provenance; content marked as truncated was cut to keep this document small. ## Project metadata - Hackathon: TreeHacks 2025 - Tagline: - if you can explain it to a duck, you can explain it to anyone. - Devpost: https://devpost.com/software/the-duck-you-mean - GitHub: https://github.com/joycechen721/duck-you-mean/ - Demo: https://docs.google.com/presentation/d/1wbRdoGqOnnMw5rVU0nRgBMmOErweNsQdrtsrA7q-214/edit?usp=sharing - Video: https://www.youtube.com/embed/eDDO_p1X9e8?enablejsapi=1&hl=en_US&rel=0&start=&version=3&wmode=transparent - Result: winner (ElevenLabs: Best Use of ElevenLabs (11M Credits + AirPods Max per team member [1st] & 8.11M Credits + Merch [2nd] & 5.11M Credits + Merch [3rd])) - Team: 2 GitHub contributor(s) — Joyce Chen (20 commits), John Connell (12 commits) ## Devpost submission (written by the team) ### Inspiration We were motivated by the power of rubber duck debugging and the wisdom of Richard Feynman’s quote: "If you can't explain it simply, you don't understand it well enough." Too often, AI is used to give answers, but true learning happens when we explain concepts ourselves. We wanted to flip AI on its head. Rather than asking the duck for answers, you teach it, and it pushes back with evaluations, scores, and follow-up questions to deepen your understanding. ### What it does The Duck You Mean is an interactive web app that lets users pick a topic and engage in a back-and-forth conversation where AI plays the role of a curious student. Users must explain concepts, and the AI: Scores their explanations based on clarity, correctness, and depth Asks intelligent follow-up questions to test deeper understanding Provides feedback to refine and strengthen their knowledge We also created zone called "The Pond", where users can create Zoom Meetings to study with friends or chill out after completing a lesson. Featured APIs -ElevenLabs - facilitates the full conversation process from user mic input to duck voice generation -Zoom API - creates meetings for peer-to-peer study sessions -OpenAI API - generates the starting question based on the prompt, -Mistrel AI - supports topic ideation and question formation -Luma AI - powers duck thoughts through created images ### Challenges we ran into Fine-tuning AI’s response evaluation—balancing depth of feedback while keeping interactions engaging Generating meaningful follow-up questions without redundancy Integrating voice interactions smoothly for an immersive experience ### Accomplishments we're proud of Successfully flipped AI’s role from answering questions to being the student Developed an engaging voice-driven AI tutor experience Created an effective learning tool that enforces deeper understanding Seamlessly integrated multiple AI-powered services ### What we learned Teaching a concept cements learning better than passive studying Thoughtful follow-up questions are key to uncovering misunderstandings Conversational AI can enhance education beyond just answering queries ### What's next Learning History to intelligently track user progress over time Gamification: Achievements, streaks, and leaderboards Mobile app version to promote learning on the go ## README (from the GitHub repository) ## TreeHacks 2025: 2nd Place in Best Use of ElevenLabs ## Inspiration We were motivated by the power of **rubber duck debugging** and the wisdom of Richard Feynman’s quote: > *"If you can't explain it simply, you don't understand it well enough."* Too often, AI is used to give answers, but **true learning happens when we explain concepts ourselves**. We wanted to flip AI on its head. Rather than asking the duck for answers, **you teach it**, and it pushes back with evaluations, scores, and follow-up questions to deepen your understanding. ## What it does **The Duck You Mean** is an interactive web app that lets users pick a topic and engage in a back-and-forth conversation where **AI plays the role of a curious student**. Users must explain concepts, and the AI: - **Scores their explanations** based on clarity, correctness, and depth - **Asks intelligent follow-up questions** to test deeper understanding - **Provides feedback** to refine and strengthen their knowledge We also created zone called "The Pond", where users can create Zoom Meetings to study with friends or chill out after completing a lesson. ## Featured APIs -**ElevenLabs** - facilitates the full conversation process from user mic input to duck voice generation -**Zoom API** - creates meetings for peer-to-peer study sessions -**OpenAI API** - generates the starting question based on the prompt, -**Mistrel AI** - supports topic ideation and question formation -**Luma AI** - powers duck thoughts through created images ## Challenges we ran into - **Fine-tuning AI’s response evaluation**—balancing depth of feedback while keeping interactions engaging - **Generating meaningful follow-up questions** without redundancy - **Integrating voice interactions smoothly** for an immersive experience ## Accomplishments that we're proud of - Successfully **flipped AI’s role** from answering questions to **being the student** - Developed an engaging **voice-driven AI tutor experience** - Created an **effective learning tool** that enforces deeper understanding - Seamlessly integrated multiple AI-powered services ## What we learned - Teaching a concept **cements learning better than passive studying** - Thoughtful follow-up questions **are key to uncovering misunderstandings** - **Conversational AI** can enhance education beyond just answering queries ## What's next for The Duck You Mean? - **Learning History** to intelligently track user progress over time - **Gamification:** Achievements, streaks, and leaderboards - **Mobile app version** to promote learning on the go DevPost Submission: https://devpost.com/software/the-duck-you-mean ## Detected evidence (automated analysis) Indexed codebase: 21 recognized source files, 44 KB. - CSS (language) — detected in the code - Firebase (technology) — detected in the code - JavaScript (language) — detected in the code - Next.js (technology) — detected in the code - OpenAI (technology) — detected in the code - React (technology) — detected in the code - Tailwind CSS (technology) — detected in the code - TypeScript (language) — detected in the code - Mistral AI (technology) — claimed on Devpost, not found in the code ## Codebase structure (from repository index) ### Files (26 of 26) ``` .gitignore eslint.config.mjs next.config.ts package.json postcss.config.mjs README.md src/app/api/get-luma/route.ts src/app/api/mistral/route.ts src/app/api/open-ai/calcScore/route.ts src/app/api/open-ai/extractKeywords/route.ts src/app/api/open-ai/generateElements/route.ts src/app/api/open-ai/generateImg/route.ts src/app/api/open-ai/genFirstQuestion/route.ts src/app/api/zoom/route.ts src/app/components/conversation.tsx src/app/components/navbar.tsx src/app/components/projector.tsx src/app/globals.css src/app/layout.tsx src/app/learn/page.tsx src/app/lib/Firebase.js src/app/page.tsx src/app/pond/page.tsx src/app/subjects/meetings/page.tsx tailwind.config.ts tsconfig.json ``` ### Dependencies - package.json: @11labs/react@^0.0.7, @eslint/eslintrc@^3, @mistralai/mistralai@^1.5.0, @types/node@^20, @types/react@^19, @types/react-dom@^19, axios@^1.7.9, eslint@^9, eslint-config-next@15.1.7, firebase@^11.3.1, fs@^0.0.1-security, lucide-react@^0.475.0, lumaai@^1.4.0, next@15.1.7, node-fetch@^3.3.2, openai@^4.85.1, postcss@^8, react@^19.0.0, react-dom@^19.0.0, tailwindcss@^3.4.1, typescript@^5 ### Recent commits (newest first) - Update README.md - Update README.md - added new prompt - Merge branch 'main' into talkingduck - add luma functions - the pond overflows....... - idk what i did - Merge branch 'main' of https://github.com/joycechen721/duck-you-mean into talkingduck - adfasfa - fix the finish lesson and add talking duck - got that drip got that style (yuh) - Mistral AI Addition - Create Zoom Meeting in the pond - ahhhh - failed attempt at prompting - styling - WE GOT STYLE - Set up firebase auth - styling - fixed some routes ## Key source files (fetched from GitHub, selected and truncated for size) ### package.json ``` { "name": "duckyoumean", "version": "0.1.0", "private": true, "scripts": { "dev": "next dev", "build": "next build", "start": "next start", "lint": "next lint" }, "dependencies": { "@11labs/react": "^0.0.7", "@mistralai/mistralai": "^1.5.0", "axios": "^1.7.9", "firebase": "^11.3.1", "fs": "^0.0.1-security", "lucide-react": "^0.475.0", "lumaai": "^1.4.0", "next": "15.1.7", "node-fetch": "^3.3.2", "openai": "^4.85.1", "react": "^19.0.0", "react-dom": "^19.0.0" }, "devDependencies": { "@eslint/eslintrc": "^3", "@types/node": "^20", "@types/react": "^19", "@types/react-dom": "^19", "eslint": "^9", "eslint-config-next": "15.1.7", "postcss": "^8", "tailwindcss": "^3.4.1", "typescript": "^5" } } ``` ### src/app/layout.tsx ```typescript import type { Metadata } from "next"; import { Geist, Geist_Mono } from "next/font/google"; import "./globals.css"; import Navbar from "./components/navbar"; const geistSans = Geist({ variable: "--font-geist-sans", subsets: ["latin"], }); const geistMono = Geist_Mono({ variable: "--font-geist-mono", subsets: ["latin"], }); export const metadata: Metadata = { title: "Create Next App", description: "Generated by create next app", }; export default function RootLayout({ children, }: Readonly<{ children: React.ReactNode; }>) { return ( {children} ); } ``` ### src/app/page.tsx ```typescript export default function Home() { const backgroundImage = '/background.png'; const logoImage = '/logo.png'; const startImage = '/start.png'; const duckImage = '/duck.png'; return (

the duck you mean?

- if you can explain it to a duck, you can explain it to anyone.

- the ai student that quacks back.

{/* Logo */} Start
Duck
); } ``` ### src/app/learn/page.tsx ```typescript import { Conversation } from "../components/conversation"; export default function Home() { return (
); } ``` ### src/app/pond/page.tsx ```typescript "use client"; import { useState } from "react"; import axios from "axios"; import Image from "next/image"; export default function SubjectsPage() { const [meetingLink, setMeetingLink] = useState(null); const [loading, setLoading] = useState(false); const [error, setError] = useState(null); const createMeeting = async () => { setLoading(true); setError(null); try { const response = await axios.post("/api/zoom"); setMeetingLink(response.data.join_url); } catch (err) { if (err.response) { console.error("Response error:", err.response); setError(`Zoom API error: ${err.response.data.message}`); } else if (err.request) { console.error("Request error:", err.request); setError("No response received from Zoom API."); } else { console.error("Error", err.message); setError("Failed to create meeting. Try again."); } } finally { setLoading(false); } } return (
{/* Background Image */} Pond Background {/* Content Overlay */}

Welcome to the Pond

Study with friends, enjoy some ducks, or chill after a tough lesson.

{error && (

{error}

)} {meetingLink && (

✅ Meeting Created!

Join here:

{meetingLink}
)} {/* Vertical Cards with Image for Study Rooms */}
{/* Notional Card 4 */}
Literature Review Techniques

Literature Review Techniques

Join Study Room
{/* Notional Card 1 */} {/* Notional Card 2 */}
Chemistry Basics

Compute [truncated — 1702 more characters] ``` ### src/app/api/mistral/route.ts ```typescript import { Mistral } from '@mistralai/mistralai'; const apiKey = process.env.MISTRAL_API_KEY; const client = new Mistral({apiKey: process.env.OPENAI_API_KEY}); const chatResponse = await client.chat.complete({ model: 'mistral-large-latest', messages: [{role: 'user', content: 'What is the best French cheese?'}], }); console.log('Chat:', chatResponse.choices[0].message.content); ``` ### src/app/api/get-luma/route.ts ```typescript // app/api/generateImage/route.js import fs from 'fs'; import path from 'path'; import { LumaAI } from 'lumaai'; const client = new LumaAI({ authToken: process.env.LUMALABS_API_KEY }); export async function POST(req:any) { try { const { prompt } = await req.json(); let generation = await client.generations.image.create({ prompt, }); let completed = false; while (!completed) { generation = await client.generations.get(generation.id); if (generation.state === "completed") { completed = true; } else if (generation.state === "failed") { return Response.json({ error: `Generation failed: ${generation.failure_reason}` }, { status: 500 }); } else { console.log("Dreaming..."); await new Promise(r => setTimeout(r, 3000)); // Wait for 3 seconds } } const imageUrl = generation.assets.image; const response = await fetch(imageUrl); const buffer = await response.arrayBuffer(); // Define the public folder path const fileName = `${generation.id}.jpg`; const filePath = path.join(process.cwd(), 'public', 'images', fileName); // Ensure the directory exists fs.mkdirSync(path.dirname(filePath), { recursive: true }); // Write the file to the public directory fs.writeFileSync(filePath, Buffer.from(buffer)); // Return the public URL of the saved image return Response.json({ imageUrl: `/images/${fileName}` }, { status: 200 }); } catch (error) { console.error(error); return Response.json({ error: 'Failed to generate image' }, { status: 500 }); } } ``` ### src/app/api/zoom/route.ts ```typescript import { NextResponse } from 'next/server'; import axios from 'axios'; // Export the POST handler export async function POST(request: Request) { try { // Get access token const tokenResponse = await axios.post( "https://zoom.us/oauth/token", new URLSearchParams({ grant_type: "account_credentials", account_id: process.env.ZOOM_ACCOUNT_ID || "", }), { headers: { Authorization: `Basic ${Buffer.from( `${process.env.ZOOM_CLIENT_ID}:${process.env.ZOOM_CLIENT_SECRET}` ).toString("base64")}`, "Content-Type": "application/x-www-form-urlencoded", }, } ); console.log("Token Response:", tokenResponse.data); // Debug log const accessToken = tokenResponse.data.access_token; // Create Zoom meeting const zoomResponse = await axios.post( "https://api.zoom.us/v2/users/me/meetings", { topic: "Scheduled Meeting", type: 2, start_time: new Date().toISOString(), duration: 30, timezone: Intl.DateTimeFormat().resolvedOptions().timeZone, settings: { host_video: true, participant_video: true, }, }, { headers: { Authorization: `Bearer ${accessToken}`, "Content-Type": "application/json", }, } ); console.log("Zoom Response:", zoomResponse.data); // Debug log return NextResponse.json({ join_url: zoomResponse.data.join_url, meeting_id: zoomResponse.data.id, password: zoomResponse.data.password, }); } catch (error: any) { console.error('Zoom API Error:', error.response?.data || error.message); return NextResponse.json( { error: "Failed to create Zoom meeting", details: error.message }, { status: 500 } ); } } ``` ### src/app/subjects/meetings/page.tsx ```typescript "use client"; import { useState } from "react"; import axios from "axios"; import Image from "next/image"; export default function SubjectsPage() { const [meetingLink, setMeetingLink] = useState(null); const [loading, setLoading] = useState(false); const [error, setError] = useState(null); const createMeeting = async () => { setLoading(true); setError(null); try { const response = await axios.post("/api/zoom"); setMeetingLink(response.data.join_url); } catch (err) { if (err.response) { console.error("Response error:", err.response); setError(`Zoom API error: ${err.response.data.message}`); } else if (err.request) { console.error("Request error:", err.request); setError("No response received from Zoom API."); } else { console.error("Error", err.message); setError("Failed to create meeting. Try again."); } } finally { setLoading(false); } } return (
{/* Background Image */} Pond Background {/* Content Overlay */}

Welcome to the Pond

Study with friends, enjoy some ducks, or chill after a tough lesson.

{error && (

{error}

)} {meetingLink && (

✅ Meeting Created!

Join here:

{meetingLink}
)} {/* Vertical Cards with Image for Study Rooms */}
{/* Notional Card 1 */} {/* Notional Card 2 */}
Computer Science Basics

Computer Science Basics

Join Study Room
{/* Notional Card 3 */}
History of Science

History of Scien [truncated — 1685 more characters] ``` ### src/app/api/open-ai/generateImg/route.ts ```typescript import OpenAI from "openai"; const openai = new OpenAI({ apiKey: process.env.OPENAI_API_KEY }); export async function POST(req:any) { try { const { prompt } = await req.json(); // console.log(prompt) const response = await openai.images.generate({ model: "dall-e-3", prompt, n: 1, size: "1024x1024", }); return Response.json({ imageUrl: response.data[0].url }, { status: 200 }); } catch (error) { console.error("Error generating image:", error); return Response.json({ error: "Failed to generate image" }, { status: 500 }); } } ``` [11 more indexed source files omitted to keep this export small. The full file list is in the Codebase structure section above.]