# Project export: IntelliAgent 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: UC Berkeley AI Hackathon 2025 - Tagline: IntelliAgent is a multimodal multi-agent AI framework that helps students study for their AP courses. Chat, practice, quiz, and discuss with it to learn everything you need to know for your AP exam! - Devpost: https://devpost.com/software/intelliagent-iktjh5 - GitHub: https://github.com/usrnme20/IntelliAgent - Demo: https://v0-ai-tutoring-website.vercel.app/ - Video: https://www.youtube.com/embed/Vwcc6YjK40U?enablejsapi=1&hl=en_US&rel=0&start=&version=3&wmode=transparent - Team: 2 GitHub contributor(s) — Bhavya Paleru (13 commits), Aishwari Sirur (1 commits) ## Devpost submission (written by the team) ### Inspiration In 2022, 1.2 million students in the US took AP exams. While the usage of one-on-one tutoring has soared in high-income communities since 1997, other students are left behind and have to make do with juggling several website and textbooks. During high school, we also took several AP exams and had to alternate studying from several different resources such as our textbooks, practice exams, online audio practice and many more. Our tool consolidates all of these into 1 singular website to help the AP student focus on studying for the exam. ### What it does Our core features include an AI tutor chatbot Custom unit quizzes Custom remedial quizzes on topics you struggled with Expert full-length practice exams Progress tracker on each unit and topic For language courses, listening and speaking practice as well as spoken conversation with AI ### How we built it We created Letta AI agents that were trained on AP course Course and Exam Description PDFs as well as practice free-response questions and their scoring guidelines. Then, we integrated VAPI so that students taking AP Spanish and French can practice conversation with the AI and learn how to answer questions for the AP exam. Finally, we used Vercel to build and deploy our user interface which is clean and readable in light and dark mode. ### Challenges we ran into Of the many challenges we ran into, one of the most prominent challenges we faced was trying to integrate the AI agent with the front-end. Since this was our first time using them, there was a steep learning curve. Similarly, integrating VAPI into the final product was difficult for the same reasons. Additionally, v0 which built the frontend, hard-coded alot of the quizzes and practice exams, so we needed to rewrite many of the files so that the final product could work. ### Accomplishments we're proud of Successfully using AI agents Integrating Voice-Powered AI Agents for Spanish and French Deploying the final product on Vercel Creating a product that would have helped us a lot back in high school and that we hope can help many more AP students in the future ### What we learned how to use AI agents with Letta and Voice-Powered AI agents with VAPI how to debug a large project how to manage a multimodal multi-agent framework ### What's next adding more AP courses making an enterprise option for small to large-scale businesses for onboarding making a teacher login so that they can upload their notes, so their students can practice ## README (from the GitHub repository) # AP Tutor - AI-Powered Learning Platform A comprehensive AI tutoring platform for AP courses using Letta's stateful agents. Each course has a dedicated AI tutor that remembers student interactions and adapts to individual learning needs. ## Features - **6 AP Courses**: Biology, US History, Spanish, French, Chemistry, Computer Science A - **Personalized AI Tutors**: Each course has a specialized Letta agent with deep curriculum knowledge - **Adaptive Learning**: Agents remember student strengths/weaknesses and provide targeted help - **Interactive Practice**: Unit quizzes, review sessions, and full-length practice exams - **Language Learning**: Speaking/listening practice for Spanish and French courses - **Progress Tracking**: Detailed analytics and progress visualization ## Quick Start 1. **Clone and Install** \`\`\`bash git clone cd ap-tutor-platform npm install \`\`\` 2. **Get Letta API Key** - Sign up at [app.letta.com](https://app.letta.com) - Create an API key at [app.letta.com/api-keys](https://app.letta.com/api-keys) 3. **Setup Environment** \`\`\`bash cp .env.example .env.local # Add your LETTA_API_KEY to .env.local \`\`\` 4. **Create AI Tutors** \`\`\`bash npm run setup-agents \`\`\` 5. **Start Development Server** \`\`\`bash npm run dev \`\`\` ## Architecture The platform uses Letta's stateful agents [^1] to create persistent AI tutors that: - **Remember Everything**: Each agent maintains memory of student interactions - **Adapt Over Time**: Agents learn student strengths/weaknesses and adjust teaching - **Provide Expertise**: Each tutor has comprehensive AP curriculum knowledge - **Track Progress**: Agents store learning patterns in their long-term memory ### Agent Memory Structure Each tutor agent has specialized memory blocks: - **Persona**: Teaching style and expertise - **Course Knowledge**: Complete AP curriculum and exam format - **Student Progress**: Individual learning patterns and weak areas - **Human**: Student profile and preferences ## Course Coverage ### AP Biology - 8 units from Chemistry of Life to Ecology - Lab analysis and data interpretation - FRQ practice and exam strategies ### AP US History - 9 historical periods from 1491-Present - DBQ and LEQ writing practice - Primary source analysis ### AP Spanish/French - 6 thematic units with cultural focus - Speaking and listening practice as well as AI conversation - Authentic resource integration ### AP Chemistry - 9 units covering all major chemistry concepts - Mathematical problem-solving - Laboratory skills and analysis ### AP Computer Science A - 10 units of Java programming - Object-oriented programming concepts - Algorithm development and analysis ## Technology Stack - **Frontend**: Next.js 14, React, TypeScript, Tailwind CSS - **AI Agents**: Letta Cloud with GPT-4.1 models - **UI Components**: shadcn/ui with Radix primitives - **Styling**: Tailwind CSS with custom design system ## Development ### Adding New Features The platform is designed for easy extension: 1. **New Courses**: Add course configs to `scripts/setup-agents.js` 2. **Enhanced Quizzes**: Extend `QuizSection` component with new question types 3. **Progress Analytics**: Add new metrics to `ProgressDashboard` 4. **Language Features**: Expand `LanguageSection` with more interactive elements ### API Integration The chat interface uses the Vercel AI SDK with Letta provider [^1]: \`\`\`typescript import { lettaCloud } from '@letta-ai/vercel-ai-sdk-provider' import { streamText } from 'ai' const result = streamText({ model: lettaCloud(agentId), prompt: userMessage, // Only send new message, not history }) \`\`\` ## Deployment 1. **Environment Variables**: Ensure all `LETTA_AGENT_*` variables are set 2. **Build**: `npm run build` 3. **Deploy**: Compatible with Vercel, Netlify, or any Node.js hosting ## Contributing 1. Fork the repository 2. Create a feature branch 3. Make your changes 4. Test with your Letta agents 5. Submit a pull request ## License MIT License - see LICENSE file for details. ## Detected evidence (automated analysis) Indexed codebase: 83 recognized source files, 544 KB. - CSS (language) — detected in the code - JavaScript (language) — detected in the code - Next.js (technology) — detected in the code - React (technology) — detected in the code - Tailwind CSS (technology) — detected in the code - TypeScript (language) — detected in the code - Google Gemini (technology) — claimed on Devpost, not found in the code - Node.js (technology) — claimed on Devpost, not found in the code - Vercel (technology) — claimed on Devpost, not found in the code ## Codebase structure (from repository index) ### Files (89 of 89) ``` .gitignore app/api/agents/configure/route.ts app/api/agents/list/route.ts app/api/agents/setup/route.ts app/api/chat/route.ts app/api/generate-practice-test/route.ts app/api/generate-quiz/route.ts app/api/get-course-info/route.ts app/api/submit-quiz/route.ts app/api/vapi-config/route.ts app/api/vapi-token/route.ts app/courses/[courseId]/page.tsx app/globals.css app/layout.tsx app/page.tsx app/setup/page.tsx components.json components/agent-configurator.tsx components/chat-interface.tsx components/course-layout.tsx components/language-section.tsx components/practice-test-section.tsx components/progress-dashboard.tsx components/quiz-loading.tsx components/quiz-section.tsx components/theme-provider.tsx components/ui/accordion.tsx components/ui/alert-dialog.tsx components/ui/alert.tsx components/ui/aspect-ratio.tsx components/ui/avatar.tsx components/ui/badge.tsx components/ui/breadcrumb.tsx components/ui/button.tsx components/ui/calendar.tsx components/ui/card.tsx components/ui/carousel.tsx components/ui/chart.tsx components/ui/checkbox.tsx components/ui/collapsible.tsx components/ui/command.tsx components/ui/context-menu.tsx components/ui/dialog.tsx components/ui/drawer.tsx components/ui/dropdown-menu.tsx components/ui/form.tsx components/ui/hover-card.tsx components/ui/input-otp.tsx components/ui/input.tsx components/ui/label.tsx components/ui/menubar.tsx components/ui/navigation-menu.tsx components/ui/pagination.tsx components/ui/popover.tsx components/ui/progress.tsx components/ui/radio-group.tsx components/ui/resizable.tsx components/ui/scroll-area.tsx components/ui/select.tsx components/ui/separator.tsx components/ui/sheet.tsx components/ui/sidebar.tsx components/ui/skeleton.tsx components/ui/slider.tsx components/ui/sonner.tsx components/ui/switch.tsx components/ui/table.tsx components/ui/tabs.tsx components/ui/textarea.tsx components/ui/toast.tsx components/ui/toaster.tsx components/ui/toggle-group.tsx components/ui/toggle.tsx components/ui/tooltip.tsx components/ui/use-mobile.tsx components/ui/use-toast.ts components/vapi-widget.tsx hooks/use-mobile.tsx hooks/use-toast.ts lib/utils.ts next.config.mjs package.json postcss.config.mjs README.md scripts/setup-agents.js styles/globals.css tailwind.config.ts tsconfig.json vercel.json ``` ### Dependencies - package.json: @letta-ai/letta-client@latest, @radix-ui/react-accordion@latest, @radix-ui/react-alert-dialog@latest, @radix-ui/react-aspect-ratio@latest, @radix-ui/react-avatar@latest, @radix-ui/react-checkbox@latest, @radix-ui/react-collapsible@latest, @radix-ui/react-context-menu@latest, @radix-ui/react-dialog@latest, @radix-ui/react-dropdown-menu@latest, @radix-ui/react-hover-card@latest, @radix-ui/react-label@latest, @radix-ui/react-menubar@latest, @radix-ui/react-navigation-menu@latest, @radix-ui/react-popover@latest, @radix-ui/react-progress@latest, @radix-ui/react-radio-group@latest, @radix-ui/react-scroll-area@latest, @radix-ui/react-select@latest, @radix-ui/react-separator@latest, @radix-ui/react-slider@latest, @radix-ui/react-slot@latest, @radix-ui/react-switch@latest, @radix-ui/react-tabs@latest, @radix-ui/react-toast@latest, @radix-ui/react-toggle@latest, @radix-ui/react-toggle-group@latest, @radix-ui/react-tooltip@latest, @types/node@^22, @types/react@^18, @types/react-dom@^18, @vapi-ai/web@latest, autoprefixer@^10.0.1, class-variance-authority@^0.7.1, clsx@^2.1.1, cmdk@latest, dotenv@^16.5.0, embla-carousel-react@latest, eslint@^8, eslint-config-next@14.0.0, fs@latest, input-otp@latest, lucide-react@^0.454.0, next@14.2.16, next-themes@latest, path@latest, postcss@^8.5, react@^18, react-day-picker@latest, react-dom@^18, react-hook-form@latest, react-resizable-panels@latest, recharts@latest, sonner@latest, tailwind-merge@^2.5.5, tailwindcss@^3.3.0, tailwindcss-animate@^1.0.7, typescript@^5, vaul@latest, zod@latest ### Recent commits (newest first) - Update README.md - feat: update homepage title to "IntelliAgent" - feat: sync changes from test1 in AIAPTutor project - Update route.ts for Vapi config - fix: move Vapi API key to server side - feat: enhance course content and add Vapi integration - Fix quiz generation API: update Letta client call and response parsing - Fix quiz submission API: update Letta client call and response parsing - Fix Response.json TypeError and Letta response content type - Fix Letta client API call and response parsing - Fix Letta client API call to agents.messages.create and response parsing - Configure Vercel with vercel.json to force pnpm install and build - Add missing dependencies for Vercel build - feat: use existing Letta agents instead of creating new ## Key source files (fetched from GitHub, selected and truncated for size) ### package.json ``` { "name": "ap-tutor-platform", "version": "0.1.0", "private": true, "scripts": { "build": "next build", "dev": "next dev", "lint": "next lint", "start": "next start" }, "dependencies": { "@letta-ai/letta-client": "latest", "@radix-ui/react-accordion": "latest", "@radix-ui/react-alert-dialog": "latest", "@radix-ui/react-aspect-ratio": "latest", "@radix-ui/react-avatar": "latest", "@radix-ui/react-checkbox": "latest", "@radix-ui/react-collapsible": "latest", "@radix-ui/react-context-menu": "latest", "@radix-ui/react-dialog": "latest", "@radix-ui/react-dropdown-menu": "latest", "@radix-ui/react-hover-card": "latest", "@radix-ui/react-label": "latest", "@radix-ui/react-menubar": "latest", "@radix-ui/react-navigation-menu": "latest", "@radix-ui/react-popover": "latest", "@radix-ui/react-progress": "latest", "@radix-ui/react-radio-group": "latest", "@radix-ui/react-scroll-area": "latest", "@radix-ui/react-select": "latest", "@radix-ui/react-separator": "latest", "@radix-ui/react-slider": "latest", "@radix-ui/react-slot": "latest", "@radix-ui/react-switch": "latest", "@radix-ui/react-tabs": "latest", "@radix-ui/react-toast": "latest", "@radix-ui/react-toggle": "latest", "@radix-ui/react-toggle-group": "latest", "@radix-ui/react-tooltip": "latest", "@vapi-ai/web": "latest", "class-variance-authority": "^0.7.1", "clsx": "^2.1.1", "cmdk": "latest", "dotenv": "^16.5.0", "embla-carousel-react": "latest", "fs": "latest", "input-otp": "latest", "lucide-react": "^0.454.0", "next": "14.2.16", "next-themes": "latest", "path": "latest", "react": "^18", "react-day-picker": "latest", "react-dom": "^18", "react-hook-form": "latest", "react-resizable-panels": "latest", "recharts": "latest", "sonner": "latest", "tailwind-merge": "^2.5.5", "tailwindcss-animate": "^1.0.7", "vaul": "latest", "zod": "latest" }, "devDependencies": { "@types/node": "^22", "@types/react": "^18", "@types/react-dom": "^18", "autoprefixer": "^10.0.1", "eslint": "^8", "eslint-config-next": "14.0.0", "postcss": "^8.5", "tailwindcss": "^3.3.0", "typescript": "^5" } } ``` ### app/layout.tsx ```typescript import type React from "react" import type { Metadata } from "next" import { Inter } from "next/font/google" import "./globals.css" import { ThemeProvider } from "@/components/theme-provider" import { Toaster } from "@/components/ui/toaster" const inter = Inter({ subsets: ["latin"] }) export const metadata: Metadata = { title: "IntelliAgent - AI-Powered Learning Platform", description: "Master AP courses with personalized AI tutors", generator: 'v0.dev' } export default function RootLayout({ children, }: { children: React.ReactNode }) { return ( {children} ) } ``` ### app/page.tsx ```typescript import { Card, CardContent, CardDescription, CardHeader, CardTitle } from "@/components/ui/card" import { Button } from "@/components/ui/button" import { Badge } from "@/components/ui/badge" import Link from "next/link" import { BookOpen, Brain, Target, TrendingUp, Settings } from "lucide-react" const courses = [ { id: "ap-biology", name: "AP Biology", description: "Master cellular processes, genetics, evolution, and ecology", color: "bg-green-500", units: 8, difficulty: "Advanced", }, { id: "ap-us-history", name: "AP US History", description: "Explore American history from pre-Columbian to modern era", color: "bg-blue-500", units: 9, difficulty: "Advanced", }, { id: "ap-spanish", name: "AP Spanish", description: "Develop fluency in Spanish language and culture", color: "bg-red-500", units: 6, difficulty: "Advanced", }, { id: "ap-french", name: "AP French", description: "Master French language and francophone cultures", color: "bg-purple-500", units: 6, difficulty: "Advanced", }, { id: "ap-chemistry", name: "AP Chemistry", description: "Understand chemical reactions, bonding, and thermodynamics", color: "bg-orange-500", units: 9, difficulty: "Advanced", }, { id: "ap-csa", name: "AP Computer Science A", description: "Learn Java programming and computer science fundamentals", color: "bg-cyan-500", units: 10, difficulty: "Advanced", }, ] const features = [ { icon: Brain, title: "AI-Powered Tutors", description: "Personalized learning with dedicated AI tutors for each subject", }, { icon: Target, title: "Adaptive Learning", description: "Focus on your weak areas with targeted practice and review", }, { icon: BookOpen, title: "Comprehensive Content", description: "Complete AP curriculum coverage with practice exams", }, { icon: TrendingUp, title: "Progress Tracking", description: "Monitor your improvement with detailed analytics", }, ] export default function HomePage() { return (
{/* Header */}

IntelliAgent

{/* Hero Section */}

Master AP Courses with IntelliAgent

Get personalized tutoring from AI agents specialized in each AP subject. Track your progress, identify weak areas, and ace your exams.

{/* Features */}

Why Choose IntelliAgent?

{features.map((feature, index) => ( {feature.title}

{feature.description}

 ))}
{/* Courses */}

Available AP Courses

{courses.map((course) => (
{course.difficulty}
{course.name} {course.description}

Agent Setup

Welcome to AP Tutor Setup

Since you've already created your Letta AI agents and added the AP course data sources, let's configure the platform to use your existing agents.

Setup Steps:

  1. Click "Load My Agents" to fetch your existing Letta agents
  2. Use "Auto-Configure" to automatically match agents to courses, or manually assign them
  3. Copy the generated environment variables to your .env.local file
  4. Restart your development server
  5. Start using your personalized AP tutors!
) } ``` ### app/api/vapi-token/route.ts ```typescript import { NextResponse } from "next/server" export async function POST() { try { const apiKey = process.env.VAPI_API_KEY if (!apiKey) { return NextResponse.json({ error: "Vapi API key not configured" }, { status: 500 }) } // Return the API key securely from server return NextResponse.json({ token: apiKey, }) } catch (error) { console.error("Error getting Vapi token:", error) return NextResponse.json({ error: "Failed to get API token" }, { status: 500 }) } } ``` ### app/api/vapi-config/route.ts ```typescript import { NextResponse } from "next/server"; export async function POST(req: Request) { try { const body = await req.json(); const { courseId } = body; console.log("Received Vapi config request for courseId:", courseId); // Add this log // Get the assistant ID based on course const assistantId = courseId === "ap-spanish" ? process.env.VAPI_SPANISH_ASSISTANT_ID : process.env.VAPI_FRENCH_ASSISTANT_ID; if (!assistantId) { console.error( `Error: Assistant ID not found for courseId: ${courseId}. Check VAPI_SPANISH_ASSISTANT_ID or VAPI_FRENCH_ASSISTANT_ID environment variables.` ); // More specific error return NextResponse.json( { error: "Assistant not configured for this course" }, { status: 400 } ); } if (!process.env.VAPI_API_KEY) { console.error("Error: VAPI_API_KEY environment variable is not set."); // New log return NextResponse.json( { error: "Vapi API key not configured" }, // More specific error message for client { status: 400 } // Or 500, depending on how you want to expose this ); } console.log("Successfully retrieved assistantId:", assistantId); // Success log // Return only the assistant ID - API key stays on server return NextResponse.json({ assistantId, hasApiKey: !!process.env.VAPI_API_KEY, // This should always be true if the check above passes }); } catch (error) { console.error("Error getting Vapi config:", error); return NextResponse.json( { error: "Failed to get configuration" }, { status: 500 } ); } } ``` ### app/courses/[courseId]/page.tsx ```typescript import { CourseLayout } from "@/components/course-layout" import { notFound } from "next/navigation" const courses = { "ap-biology": { name: "AP Biology", description: "Master cellular processes, genetics, evolution, and ecology", color: "bg-green-500", units: [ "Chemistry of Life", "Cell Structure and Function", "Cellular Energetics", "Cell Communication and Cell Cycle", "Heredity", "Gene Expression and Regulation", "Natural Selection", "Ecology", ], }, "ap-us-history": { name: "AP US History", description: "Explore American history from pre-Columbian to modern era", color: "bg-blue-500", units: [ "Period 1: 1491-1607", "Period 2: 1607-1754", "Period 3: 1754-1800", "Period 4: 1800-1848", "Period 5: 1844-1877", "Period 6: 1865-1898", "Period 7: 1890-1945", "Period 8: 1945-1980", "Period 9: 1980-Present", ], }, "ap-spanish": { name: "AP Spanish Language and Culture", description: "Develop fluency in Spanish language and culture", color: "bg-red-500", units: [ "Families and Communities", "Science and Technology", "Beauty and Aesthetics", "Contemporary Life", "Global Challenges", "Personal and Public Identities", ], }, "ap-french": { name: "AP French Language and Culture", description: "Master French language and francophone cultures", color: "bg-purple-500", units: [ "Families and Communities", "Science and Technology", "Beauty and Aesthetics", "Contemporary Life", "Global Challenges", "Personal and Public Identities", ], }, "ap-chemistry": { name: "AP Chemistry", description: "Understand chemical reactions, bonding, and thermodynamics", color: "bg-orange-500", units: [ "Atomic Structure and Properties", "Molecular and Ionic Compound Structure", "Intermolecular Forces and Properties", "Chemical Reactions", "Kinetics", "Thermodynamics", "Equilibrium", "Acids and Bases", "Applications of Thermodynamics", ], }, "ap-csa": { name: "AP Computer Science A", description: "Learn Java programming and computer science fundamentals", color: "bg-cyan-500", units: [ "Primitive Types", "Using Objects", "Boolean Expressions and if Statements", "Iteration", "Writing Classes", "Array", "ArrayList", "2D Array", "Inheritance", "Recursion", ], }, } interface CoursePageProps { params: { courseId: string } } export default function CoursePage({ params }: CoursePageProps) { const course = courses[params.courseId as keyof typeof courses] if (!course) { notFound() } return } ``` ### app/api/submit-quiz/route.ts ```typescript import { LettaClient } from "@letta-ai/letta-client"; import { NextResponse } from 'next/server'; // <-- Import NextResponse // Course-specific agent IDs const COURSE_AGENTS = { "ap-biology": process.env.LETTA_AGENT_AP_BIOLOGY, "ap-us-history": process.env.LETTA_AGENT_AP_US_HISTORY, "ap-spanish": process.env.LETTA_AGENT_AP_SPANISH, "ap-french": process.env.LETTA_AGENT_AP_FRENCH, "ap-chemistry": process.env.LETTA_AGENT_AP_CHEMISTRY, "ap-csa": process.env.LETTA_AGENT_AP_CSA, } // Helper to extract text content from a message (copied from chat/route.ts for consistency) function extractTextContent(content: any): string { if (typeof content === 'string') { return content; } // Assuming 'content' could be an array like [{ type: 'text', text: '...' }] if (Array.isArray(content)) { return content.map(item => (item && typeof item === 'object' && 'text' in item ? item.text : '')).join(''); } return ''; // Return empty string if content is neither string nor array } export async function POST(req: Request) { try { const { courseId, quizResults, quizType, unit } = await req.json() const agentId = COURSE_AGENTS[courseId as keyof typeof COURSE_AGENTS] // Calculate performance metrics const totalQuestions = quizResults.length const correctAnswers = quizResults.filter((result: any) => result.correct).length const score = Math.round((correctAnswers / totalQuestions) * 100) // Identify weak areas const incorrectQuestions = quizResults.filter((result: any) => !result.correct) const weakUnits = [...new Set(incorrectQuestions.map((q: any) => q.unit))] let recommendations = "" if (agentId && process.env.LETTA_API_KEY) { try { // Initialize Letta client const client = new LettaClient({ token: process.env.LETTA_API_KEY, }) // Send performance data to the agent for memory storage const prompt = `Student completed a ${quizType} quiz${unit ? ` on ${unit}` : ""}. Performance Summary: - Score: ${score}% (${correctAnswers}/${totalQuestions}) - Quiz Type: ${quizType} - Date: ${new Date().toLocaleDateString()} ${ incorrectQuestions.length > 0 ? ` Areas needing improvement: ${incorrectQuestions.map((q: any) => `- ${q.unit}: ${q.question.substring(0, 100)}...`).join("\n")} Weak units identified: ${weakUnits.join(", ")} ` : "Excellent performance! All questions answered correctly." } Please update your memory of this student's progress and provide personalized recommendations for improvement. Keep your response concise and actionable.` console.log("Sending quiz results to Letta agent with prompt:", prompt); // Added logging // CHANGE START: Correct Letta API call const response = await client.agents.messages.create(agentId, { messages: [{ role: "user", content: prompt }], // Send the prompt as a user message }); // CHANGE END console.log("Letta response received for quiz results:", response); // Added logging // CHANGE START: Correct response extraction if (response.messages && response.messages.length > 0) { // Look for the last message that is of type 'assistant_message' for (let i = response.messages.length - 1; i >= 0; i--) { const message = response.messages[i]; // Check for 'assistant_message' and ensure it has content if (message.messageType === "assistant_message" && message.content) { recommendations = extractTextContent(message.content); break; // Found the last assistant message, exit loop } // Also consider tool returns if the agent might use a tool to provide recommendations if (message.messageType === "tool_return_message" && message.toolReturn) { // You might decide how to incorporate tool returns. // For simplicity, here we'll prioritize an assistant message, // but if only a tool return is there, we'll use it. if (!recommendations) { // Only assign if no assistant message found yet recommendations = extractTextContent(message.toolReturn); } } } } // CHANGE END } catch (error) { console.error("Error sending results to Letta agent:", error) } } // Fallback recommendations if Letta is not available or failed if (!recommendations) { console.log("Using fallback recommendations."); // Added logging recommendations = score >= 80 ? "Excellent work! You have a strong understanding of this material. Consider moving on to more challenging topics or taking a practice exam." : score >= 60 ? "Good progress! Focus on reviewing the areas where you missed questions. Consider additional practice in those specific units." : "This material needs more review. I recommend going back to study the fundamental concepts and taking additional practice quizzes." } return NextResponse.json({ // <-- Changed score, totalQuestions, correctAnswers, weakUnits, recommendations, performance: score >= 80 ? "excellent" : score >= 60 ? "good" : "needs_improvement", }) } catch (error) { console.error("Quiz submission error:", error) return NextResponse.json({ error: "Failed to process quiz results" }, { status: 500 }) // <-- Changed } } ``` ### app/api/chat/route.ts ```typescript import { LettaClient } from "@letta-ai/letta-client"; import { NextResponse } from 'next/server'; // <-- Added for Response.json alternative // Course-specific agent IDs const COURSE_AGENTS = { "ap-biology": process.env.LETTA_AGENT_AP_BIOLOGY, "ap-us-history": process.env.LETTA_AGENT_AP_US_HISTORY, "ap-spanish": process.env.LETTA_AGENT_AP_SPANISH, "ap-french": process.env.LETTA_AGENT_AP_FRENCH, "ap-chemistry": process.env.LETTA_AGENT_AP_CHEMISTRY, "ap-csa": process.env.LETTA_AGENT_AP_CSA, } // Fallback responses for each course const getFallbackResponse = (courseId: string, userMessage: string) => { const courseResponses = { "ap-biology": `As your AP Biology tutor, I'd be happy to help you with "${userMessage}". While I'm setting up my full capabilities, I can tell you that this topic relates to the AP Biology curriculum. Would you like me to explain any specific biological concepts or help you prepare for the AP exam?`, "ap-us-history": `As your AP US History tutor, I can help you understand "${userMessage}" in the context of American history. This connects to the broader themes we study in AP History. Would you like me to provide historical context or help with exam preparation?`, "ap-spanish": `¡Hola! Como tu tutor de AP Español, puedo ayudarte con "${userMessage}". Esto se relaciona con los temas culturales y lingüísticos que estudiamos. ¿Te gustaría practicar conversación o trabajar en algún tema específico?`, "ap-french": `Bonjour! En tant que votre tuteur AP Français, je peux vous aider avec "${userMessage}". Cela se rapporte aux thèmes culturels et linguísticos que nous étudions. Aimeriez-vous pratiquer la conversación ou trabajar en un tema específico?`, "ap-chemistry": `As your AP Chemistry tutor, I can help explain "${userMessage}" using chemical principles. This relates to the fundamental concepts we study in AP Chemistry. Would you like me to break down the chemistry concepts or help with problem-solving strategies?`, "ap-csa": `As your AP Computer Science A tutor, I can help you understand "${userMessage}" in the context of Java programming and computer science concepts. Would you like me to explain the programming concepts or help with coding practice?`, } return courseResponses[courseId as keyof typeof courseResponses] || courseResponses["ap-biology"] } // Helper to extract text content from a message (handles string or array of TextContent) function extractTextContent(content: any): string { if (typeof content === 'string') { return content; } // Assuming 'content' could be an array like [{ type: 'text', text: '...' }] if (Array.isArray(content)) { return content.map(item => (item && typeof item === 'object' && 'text' in item ? item.text : '')).join(''); } return ''; // Return empty string if content is neither string nor array } export async function POST(req: Request) { try { const body = await req.json() const { messages, courseId } = body console.log("Chat API called with:", { courseId, messageCount: messages?.length }) if (!courseId) { console.error("No courseId provided") return NextResponse.json({ error: "Course ID is required" }, { status: 400 }) // <-- Changed } if (!messages || !Array.isArray(messages) || messages.length === 0) { console.error("No messages provided") return NextResponse.json({ error: "Messages are required" }, { status: 400 }) // <-- Changed } const agentId = COURSE_AGENTS[courseId as keyof typeof COURSE_AGENTS] const latestMessage = messages[messages.length - 1] console.log("Agent ID:", agentId) // Use the helper function to safely extract content from latestMessage const latestMessageContent = extractTextContent(latestMessage?.content); console.log("Latest message content:", latestMessageContent); // If no agent ID is configured, use fallback if (!agentId) { console.log("No agent ID found, using fallback response") return NextResponse.json({ // <-- Changed role: "assistant", content: getFallbackResponse(courseId, latestMessageContent || "your question"), }) } // If no Letta API key, use fallback if (!process.env.LETTA_API_KEY) { console.log("No Letta API key found, using fallback response") return NextResponse.json({ // <-- Changed role: "assistant", content: getFallbackResponse(courseId, latestMessageContent || "your question"), }) } try { // Initialize Letta client console.log("Initializing Letta client...") const client = new LettaClient({ token: process.env.LETTA_API_KEY, }) console.log("Sending message to Letta agent...") // Send message to Letta agent using the correct API method const response = await client.agents.messages.create(agentId, { messages: [{ role: "user", content: latestMessageContent }], // <-- Used extracted content }); console.log("Letta response received:", response) // Extract the assistant's response let assistantResponse = ""; if (response.messages && response.messages.length > 0) { // Look for the last message that is of type 'assistant_message' for (let i = response.messages.length - 1; i >= 0; i--) { const message = response.messages[i]; // Check for 'assistant_message' and ensure it has content if (message.messageType === "assistant_message" && message.content) { assistantResponse = extractTextContent(message.content); // <-- Used helper here too break; // Found the last assistant message, exit loop } // Optionally, handle tool return messages if needed for display if (message.messageType === "tool_return_message" && message.toolReturn) { assistantResponse = extractTextContent(message.toolReturn); // <-- Used helper here too // You [truncated — 1323 more characters] ``` ### app/api/generate-practice-test/route.ts ```typescript import { LettaClient } from "@letta-ai/letta-client" import { z } from "zod" import { NextResponse } from "next/server" // Schema for practice test generation const PracticeTestSchema = z.object({ questions: z.array( z.object({ id: z.string(), question: z.string(), type: z.enum(["short-answer", "long-essay", "data-analysis", "synthesis"]), points: z.number(), timeLimit: z.string(), rubric: z.string(), unit: z.string(), difficulty: z.enum(["easy", "medium", "hard"]), }), ), }) // Course-specific agent IDs const COURSE_AGENTS = { "ap-biology": process.env.LETTA_AGENT_AP_BIOLOGY, "ap-us-history": process.env.LETTA_AGENT_AP_US_HISTORY, "ap-spanish": process.env.LETTA_AGENT_AP_SPANISH, "ap-french": process.env.LETTA_AGENT_AP_FRENCH, "ap-chemistry": process.env.LETTA_AGENT_AP_CHEMISTRY, "ap-csa": process.env.LETTA_AGENT_AP_CSA, } // Helper to extract text content from a message function extractTextContent(content: any): string { if (typeof content === "string") { return content } if (Array.isArray(content)) { return content.map((item) => (item && typeof item === "object" && "text" in item ? item.text : "")).join("") } return "" } // Enhanced fallback practice test questions for each course const getFallbackPracticeTest = (courseId: string) => { const fallbackTests = { "ap-biology": [ { id: "bio_frq_1", question: "Explain the process of cellular respiration, including the three main stages. Describe how ATP is produced in each stage and explain the role of oxygen in the process. Include specific details about where each stage occurs in the cell.", type: "long-essay" as const, points: 10, timeLimit: "25 minutes", rubric: "4 points for explaining glycolysis, 3 points for citric acid cycle, 3 points for electron transport chain", unit: "Cellular Energetics", difficulty: "medium" as const, }, { id: "bio_frq_2", question: "A student conducted an experiment to test the effect of different pH levels on enzyme activity. Analyze the data provided and explain the relationship between pH and enzyme function. Predict what would happen at extreme pH values.", type: "data-analysis" as const, points: 8, timeLimit: "20 minutes", rubric: "3 points for data analysis, 3 points for explanation of enzyme structure, 2 points for predictions", unit: "Chemistry of Life", difficulty: "medium" as const, }, ], "ap-us-history": [ { id: "hist_frq_1", question: "Evaluate the extent to which the American Revolution was a radical departure from previous forms of government. In your response, consider political, social, and economic changes that occurred during and after the Revolution.", type: "long-essay" as const, points: 15, timeLimit: "40 minutes", rubric: "Thesis (1 pt), Contextualization (1 pt), Evidence (3 pts), Analysis (4 pts), Reasoning (6 pts)", unit: "Period 3: 1754-1800", difficulty: "hard" as const, }, ], "ap-chemistry": [ { id: "chem_frq_1", question: "A student performs a titration of a weak acid with a strong base. Given the data below, calculate the Ka of the weak acid and explain the shape of the titration curve. Include discussion of buffer regions and equivalence point.", type: "data-analysis" as const, points: 12, timeLimit: "30 minutes", rubric: "4 points for calculations, 4 points for curve explanation, 4 points for chemical reasoning", unit: "Acids and Bases", difficulty: "hard" as const, }, ], } return fallbackTests[courseId as keyof typeof fallbackTests] || fallbackTests["ap-biology"] } export async function POST(req: Request) { let courseId: string | undefined try { const body = await req.json() courseId = body.courseId const questionCount = body.questionCount || 3 console.log("Practice test generation request:", { courseId, questionCount }) const agentId = COURSE_AGENTS[courseId as keyof typeof COURSE_AGENTS] if (!agentId) { console.log(`No agent ID found for course: ${courseId}, using fallback`) return NextResponse.json({ questions: getFallbackPracticeTest(courseId), metadata: { courseId, generatedAt: new Date().toISOString(), fallback: true, error: "Agent not configured", }, }) } if (!process.env.LETTA_API_KEY) { console.log("LETTA_API_KEY not found, using fallback") return NextResponse.json({ questions: getFallbackPracticeTest(courseId), metadata: { courseId, generatedAt: new Date().toISOString(), fallback: true, error: "API key not configured", }, }) } try { // Initialize Letta client console.log("Initializing Letta client for practice test generation...") const client = new LettaClient({ token: process.env.LETTA_API_KEY, }) // Create the practice test generation prompt const courseName = courseId.replace("ap-", "AP ").replace("-", " ").toUpperCase() const prompt = `Please generate a ${questionCount}-question AP practice test with free response questions for ${courseName}. IMPORTANT: Respond with ONLY a valid JSON object in this exact format: { "questions": [ { "id": "unique_id", "question": "Detailed free response question text here...", "type": "long-essay", "points": 10, "timeLimit": "25 minutes", "rubric": "Detailed scoring rubric", "unit": "Unit name", "difficulty": "medium" } ] } Requirements: - Generate authentic AP-style free response questions - Include a mix of question types: "short-answer" [truncated — 3655 more characters] ``` [72 more indexed source files omitted to keep this export small. The full file list is in the Codebase structure section above.]