Forem: Ethan Wayne

I Built an AI Documentation Generator

Ethan Wayne — Fri, 31 Oct 2025 12:54:57 +0000

The Story:

Got laid off earlier this year. Instead of just sending out applications, I decided to build something I wish existed: an AI tool that automatically generates documentation from code.

What It Does:

Connects to your GitHub repos and creates comprehensive documentation using GPT-4 and tree-sitter code parsing.

Features:

Supports 6 languages: Python, JavaScript, Java, Ruby, Go, C++
Generates API docs, function/class references, and technical guides
GitHub OAuth integration
Analyzes code structure intelligently

Try it: https://docs-generator-two.vercel.app

Tech Stack

Backend: FastAPI (Python)
Frontend: React + TypeScript + Vite
Database: PostgreSQL
AI: OpenAI GPT-4
Hosting: Railway + Vercel
Auth: GitHub OAuth

Why I Built This

Documentation is tedious. Every developer I know (including myself) hates writing docs but knows they're critical. I wanted to see if AI could actually do this well.

What I'm Looking For

I need 5 honest beta testers before I productize this.

Questions I need answered:

Does this actually solve a problem?
What's missing?
Would you pay for this?
What features would make it genuinely useful?

The Build Journey

Built in about a month. Some interesting technical challenges:

Getting tree-sitter working with all 6 languages (dependency hell)
Designing prompts that generate useful docs (not just code summaries)
Handling large repos without timeout issues

Try It Out

Demo: https://docs-generator-two.vercel.app
Would love your brutally honest feedback in the comments!

RUBY ON RAILS PROJECT

Ethan Wayne — Mon, 03 May 2021 03:41:42 +0000

I recently did my rails project and it had lots of ups and downs. The ups were I was able to understand the errors I was getting within my project because of my Sinatra project. I built my rails project to help company owners keep jobs in order. You can also view other companies and their jobs.

This project has been the most difficult but most rewarding to me. I started off by building out everything using model generators. Once I did that I started figuring out my associations. After building my associations and creating my schema and migrations I started building controllers. After my controllers I built my views, and added some css too.

I ran into multiple errors when creating this project, (10-20) seems like a good estimate. It was a struggle to figure them out. I ended up asking for help on lots of them and figuring out a lot on my own. A lot of my errors came from pluralization. I had all my pluralization backwards so had to change it. A lot of my errors were also pretty easy to figure out and readable. A lot of the project for me was adding stuff and deleting stuff to make the project look cleaner. I also didn't get to omniauth for this phase so I needed to watch some videos and get help from students. It was pretty neat to understand and use omniauth in a project.

Figuring out errors was one of the most rewarding things I've felt. The best feeling is when you get a project running and then adding additional stuff piece by piece to make it better and better. I plan on going back to this project and making it a serious application at some point too. Overall this project was the most difficult but the most fun and rewarding.

Sinatra Project

Ethan Wayne — Sun, 28 Mar 2021 18:16:21 +0000

I just got my sinatra project done for Flatiron School. My project was called Cars Nation. I'm very interested in cars and have built a few in my life. I chose 3 very famous car collectors for my project.

To start the project I ran corneal to get the simple layout for my project. I ran into a few issues with corneal. For example I had to update everything to only run sqlite3 so there weren't multiple databases, I had to update Active Record, and had to change some code in my config.ru file so it worked properly. I also had to create a database yml file to get corneal to work.

After I sorted these issues I got to work. First I built out my controllers and models. There was a lot of issues within them and are still a few issues on the localhost that I need to fix. I then did .erb files to render everything. I should've done the rendering while I was doing the controllers so I didn't run into issues or as many issues. There are currently a few issues with params and "," and stuff like that.

Lastly I seeded my data in the end and used tux to make sure everything actually worked and had a id like it should. I added some pictures and some comments on the car collections.
Now I am working to finish up the little errors and preparing for my review.

Overall I ran into lots of issues but some help, google, and debugging helped me very much to fix these issues. A lot of my issues were very easy to read cause it specifically said where and on what line the issues were. I'm about done with project just changing some layout stuff and little errors. The project was difficult but it wasn't horrible because I know it's going to help me with ruby on rails. The project also taught me to look at key errors and helped me with debugging. On to the review!!

HELP WITH PYTHON ERROR

Ethan Wayne — Fri, 12 Mar 2021 17:59:31 +0000

So I am currently making a slack bot using python. I am not extremely familiar with python but still know some stuff. For some reason I keep getting this error. I've tried multiple things and can't seem to figure it out. Here's the code.

client = slack.WebClient(token=os.environ['SLACK_TOKEN'])
File "/usr/local/Cellar/python@3.9/3.9.2_1/Frameworks/Python.framework/Versions/3.9/lib/python3.9/os.py", line 679, in getitem
raise KeyError(key) from None
KeyError: 'SLACK_TOKEN'

STAR WARS CLI PROJECT

Ethan Wayne — Tue, 02 Mar 2021 19:40:05 +0000

I currently am enrolled in Flatiron School as a software engineer. I had my first CLI project and I did it on Star Wars it's a simple concept.

First I found an API then I got to work. I ran into a few problems such as using certain API's and not being able to find out how to display them when you ran the code. So I found this Star Wars one which was much simpler and had ID 1-10. It took some time and a lot of trial and error to develop I ran into all sorts of problems with instance methods and class methods(something I need to work on). Got a little help from fellow class mates and ended up getting the project done.

I am still currently reviewing the project and instance vs class methods as I still struggle to an extent. I have my review tomorrow and hopefully all this studying will end up paying off. If you'd like to view the project here is a Github link https://github.com/ewayne08/Starwars-API

CLI PROJECT!

Ethan Wayne — Sun, 15 Nov 2020 03:09:35 +0000

I just completed my first CLI ruby project! For my project I chose scraping Bugatti website. So first I scraped the website and all the models I wanted to present in my program. After that I made the scraper file and got to the CLI stuff. This took a while and was pretty challenging, especially because it is a bit different than what an API looks like. After I completed all the files and code for the project I ran my program. In order to run my program you have to bundle install the gems and then in the terminal type "bin/Bugatti_Models" to run it. It will then present you with 5 models to choose from 1-5 and give you a short description. In order to leave the program type "Exit".
Although there was challenges, lots of patience, google, and a bit of help got me through my first project! Some of the issues I ran into was finalizing the project. For example getting the text in the terminal to output the models in the correct order "1-5" was difficult. I ended up getting some help and researching, although I know little about it I got it done.
From this project I learned a lot. A few things I learned was coding is not as easy as you anticipate. I had to restart multiple times and even tried making an API project cause I was stuck on scraping. In the end I learned that although some things such as this can be challenging there is always a way to overcome and figure them out.

Why I decided to do Software Engineering

Ethan Wayne — Mon, 19 Oct 2020 16:34:58 +0000

I decided to do Software Engineering to learn how to code and develop numerous things and plan on starting some sort of company once I have a job with the knowledge I obtain. My cousin Nathan Latka made a SaaS company named Heyo while attending Virginia Tech. He made all of it happen with some good investors, good coding skills, and some luck. I aspire to hopefully pass him in the business world one day, and plan to make some of my own SaaS(Software as a service) companies.

It's always good to have knowledge and learn high income skills. With the world quickly pursuing in technology, I chose software engineering. At 18 this makes me feel like I am in a pretty good spot by attending Flat Iron School and hopefully working with some great companies and people in the near future that also want to develop some cool businesses!