# Project export: rankup.ai

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 2026
- Tagline: Complete AI analysis of gameplay that gives feedback and criticism.
- Devpost: https://devpost.com/software/rankup-ai
- GitHub: not linked
- Team: contributor stats unavailable

## Devpost submission (written by the team)

### Inspiration

The video game industry is an industry that continues to grow. If you ever played video games, I'm sure you have been in this position before, you are stuck in the same rank losing to the same strategies. You could go down a never ending youtube rabbit hole, or you could get instant curated feedback and criticism on your gameplay. With Large Language Model's (LLMs) the latter becomes a reality.

### What it does

Using demoparser, awpy, and redis, our application takes in a Counter Strike .Dem file, which contains the entire history of the match. It then analyzes the entire game, giving a round by round summary on what you actually did and what you could have done better. It also creates a general summary of advice along with drills that you could follow to better your gameplay. Using Redis the application keeps track of all of the bad habits that you have as a player, and tells you what percentage of games you are making this bad habit.

### How we built it

Frontend: The front end was created using react, our application initially opens up to a general home page giving information on what it is. Clicking try now leads you to the main page which offers a modern interface that allows the user to input a .dem file of their own. It then breaks the game down to them in an easy to digest way. Backend:

### Challenges we ran into

AI Hallucinated callout names - to combat this we implemented a framework to use a mesh map to define callout regions Deploying on the cloud - upgrade redis plan (redis blocked on university wifi), implement error message if redis is not working correctly Generating visual display - implemented a map to recreate moments from the game in 2d

### Accomplishments we're proud of

We are proud to have a unique and functional demo to show after our first hackathon. We had a lot of fun building our app and experiencing the hackathon.

### What we learned

We learned how to use technologies like Redis. We also deepened our understanding of technologies like React, Python, Claude, and Docker.

### What's next

In the future, we could expand functionality for Counter Strike, support other games with .dem files, and eventually support games without .dem files. For that, we could potentially use computer vision to analyze replies or live gameplay.

## 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.
- Docker (technology) — claimed on Devpost, not found in the code
- Python (language) — claimed on Devpost, not found in the code
- React (technology) — claimed on Devpost, not found in the code
- Redis (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.