Examples
What apps can Pythagora build?
One question that many people ask is what can Pythagora actually build?
So, we're listing here examples that were created with Pythagora
GPTOptimizely
GPTOptimizely is an app for A/B test marketing copy. The way it works is that it creates a code snippet that you have to embed on your website. It injects version1 of HTML to 50% of users and a different version2 of HTML to the other 50% of users. Then it tracks the number of clicks on both copies and shows results in dashboard.
Time spent to create this app - 3days
Files created - 25
Live Demo
Code Chat
Code Chat is an app that enables you to ask the LLM questions about your codebase. You paste in the link to a public Github repo; it scrapes the code from Github, chunks it, sends it to the LLM for analysis that creates a description about what the code does and saves the descriptions into the database. Then, you can ask the app a question about the codebase and the codebase shows you the response.
Time spent to create this app - 7H
Files created - 20
Vanish Talk
Vanish Talk is a sample app created to showcase real time messaging features but so it's not too easy, other features are added. It has the ability to authenticate the user, send verification email, create real time chatting room with or without a password, join any open room, and has a cronjob running that deletes all the messages every hour.
Time spent to create this app - 4H
Files created - 42
Prompt Lab
OpenAI Playground on steroids – it enables you to load a conversation from a JSON array or enter it manually, run the conversation with the LLM an X number of times, save the conversation to the database, and load it back in. We actually use this app when we engineer a prompt and want to see how it behaves. We choose how many times we want to run it and let the app run the prompt repeatedly. Once it’s finished, we can go into analyzing the results.
Time spent to create this app - 2D
Files created - 31
SQLite Analyser
OpenAI Playground on steroids – it enables you to load a conversation from a JSON array or enter it manually, run the conversation with the LLM an X number of times, save the conversation to the database, and load it back in. We actually use this app when we engineer a prompt and want to see how it behaves. We choose how many times we want to run it and let the app run the prompt repeatedly. Once it’s finished, we can go into analyzing the results.
Time spent to create this app - 2D
Files created - 36
Star History
A clone of star-history.com where you paste in Github URLs, it fetches the star count change over time and compares them on a graph with the ability to zoom in and out and save comparisons. It scrapes Github repos for stargazers, saves them into the database, plots them on a graph, and enables the graph to be zoomed in and out.
Time spent to create this app - 6H
Files created - 19