# Project export: Pitch Perfect

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: GitHub repo → pitch deck, deep market research analysis, and elevator pitch (Bring your ideas to life! Apply to YC!)
- Devpost: https://devpost.com/software/pitch-perfect-qwi8v3
- GitHub: not linked
- Demo: http://10.40.126.156:3000/
- Video: https://www.youtube.com/embed/pZ6PH7g57YA?enablejsapi=1&hl=en_US&rel=0&start=&version=3&wmode=transparent
- Team: contributor stats unavailable

## Devpost submission (written by the team)

### Overview

Problem Code is the most powerful form of language, but it’s often hard for keyboard warriors to express their vision and think of commercial applications for the things they build. Our target audience are startup founders, researchers, and hackathon competitors. What We Built 🔁 Transform your GitHub repo into a fully fledged pitch deck 📈 Find commercial applications for your code and generate a comprehensive report of target markets 🗣️ Draft an elevator pitch to share your idea with any VC! Technical Tools Used ⚙️ Next.js powered Vercel frontend with a FastAPI backend 🧠 Agentic processing pipeline An Agentic Process Our approach is inspired by the Mixture of Experts (MoE) paradigm, composed of the following agents: Code Agent (MULTIMODAL) Traverses the repo recursively, finds images to inform detailed reports (especially useful when a paper is linked in the README.md). Code Agent (MULTIMODAL) Traverses the repo recursively, finds images to inform detailed reports (especially useful when a paper is linked in the README.md). Summary Agent Summarizes code descriptions into slide format and generates an elevator pitch. Summary Agent Summarizes code descriptions into slide format and generates an elevator pitch. Deep Research Agent (WEB AGENT MCP, REASONING MODEL) Produces a market analysis report with advanced reasoning capabilities and the ability to search the web. Deep Research Agent (WEB AGENT MCP, REASONING MODEL) Produces a market analysis report with advanced reasoning capabilities and the ability to search the web. Slides Agent (SLIDES MCP) Creates stellar interactive slides, balancing content clarity with visual impact. Slides Agent (SLIDES MCP) Creates stellar interactive slides, balancing content clarity with visual impact. Sponsors Used 🌐 Google Cloud: Gemini API ⚡ Groq: Groq API 🧠 Anthropic: Claude API ▲ Vercel: Frontend deployment and hosting

## README (from the GitHub repository)

No README available.

## Detected evidence (automated analysis)

No repository was indexed for this project. Claimed technologies below could not be checked against code.
- FastAPI (technology) — claimed on Devpost, not found in the code
- Google Gemini (technology) — claimed on Devpost, not found in the code
- JavaScript (language) — claimed on Devpost, not found in the code
- Python (language) — claimed on Devpost, not found in the code
- TypeScript (language) — claimed on Devpost, not found in the code
- Vercel (technology) — claimed on Devpost, not found in the code

## Codebase structure

No repository index available.

## Key source files

No repository index available; no source files included.