Back
Explore EventsExplore ProjectsMy Projects
Breakout Simulator — screenshot 1
Breakout Simulator — screenshot 2
Breakout Simulator — screenshot 3

Breakout Simulator

Predict how your content will break through with the audiences that matter, or you choose matter.

Codex Community Hackathon - Pune

Links

Repository

github.com/riishika/DRS

Website

breaksim.up.railway.app

Demo video

youtu.be/Cf-ya2J8b8g

Additional info

How was your experience building with Codex?

It was really smooth. I built the whole project from the ground up in a single day, including the AI agent pipeline, simulation logic, and UI. Codex made it much easier to move quickly, especially with parallel task execution and tool use. Whenever something failed, I could debug, fix, and keep iterating without losing momentum. It felt like working with an extremely fast pair programmer that could keep up with the pace all day.

Describe your experience using Loops House as the hackathon platform. What worked well, what challenges (if any) did you face, and what improvements would you like to see?

Loops House was easy to use and navigate. The project submission flow and repo linking process were straightforward. I also liked the AI mentor feature for ideation, since it helped me sharpen my pitch early in the process. One improvement I’d suggest is making deadlines and submission status more visible in real time. A countdown timer or completion checklist showing what is done and what is still missing would be very useful near the deadline. I would like to have an option to delete my submissions. Since the option to add team members was not available earlier, my teammates had already submitted their own projects. Now, when I try to add them as members to my submission, it throws an error.

Tell us about your overall experience at Codex Community Hackathon Pune.

The experience was intense, but in a good way. Building a project end to end in one day while surrounded by other people doing the same created a strong sense of momentum. The room had great energy, and I appreciated that the event emphasized actually shipping something rather than only brainstorming. Leaving with a deployed working product felt genuinely satisfying.

What could Codex Community improve to create a better experience for participants?

A little more time would make the experience even better, especially near the end when deployment and debugging issues come up. It would also be helpful to have a short session at the beginning showing practical examples of how past participants used Codex effectively, so newer users can get comfortable faster. Apart from that, the hackathon was well organized.

Team

1 member
  • SA

    SAMARPEET GARAD

    Owner

Overview

Breakout Prediction Simulator is a multimodal pre-flight testing tool for short-form content. Instead of posting a video and waiting to see whether it performs, creators can upload a reel, choose the audience group they want to reach, and simulate how that content might spread before publishing. The system analyzes the uploaded video across multiple signals: sampled visual frames, visible text overlays, audio, and speech transcripts when available. If a video has no human speech, it still works by building a visual narrative from the frames. After analysis, 260 simulated persona agents react to the content in waves, deciding whether they would skip, like, comment, save, or share. A key feature is target-group testing. The creator can select a desired audience, such as Gen Z trend viewers, developers, founders, fitness audiences, foodies, gamers, parents, or designers. The simulator then highlights how that specific group responds and produces edit recommendations tailored to them. The final output is not just a score. The app gives creators actionable guidance: what to change in the first few seconds, what text to add, what payoff to move earlier, and why the selected audience is engaging or dropping off. Built with Next.js, TypeScript, OpenAI GPT-4o vision, Whisper transcription, GPT-4.1 persona agents, and ffmpeg-based video processing, the project demonstrates how multimodal AI and agent simulation can help creators make better publishing decisions before content goes live.

ExploreProjectsMine