How ChatGPT improved my Elixir code. Some hacks are included.

I have been working as an Elixir developer for quite some time and recently came across the ChatGPT model. I want to share some of my experience interacting with it.

During my leisure hours, I am developing an open-source Elixir initiative, Crawly, that facilitates the extraction of structured data from the internet. 

Here I want to demonstrate how ChatBot helped me to improve the code. Let me show you some prompts I have made and some outputs I’ve got back.

Writing documentation for the function

I like documentation! It’s so nice when the code you’re working with is documented! What I don’t like — is writing it. It’s hard, and it’s even harder to keep it updated. 

So let’s consider the following example from our codebase:

My prompt:

Reasonably good for my taste. Here how it looks like after a few clarifications:

Improving my functions

Let’s look at other examples of the code I have created! Here is an example of code I am not super proud of. Please don’t throw stones at me; I know I should not create atoms dynamically. Well, you know how it can be- you want to have something, but you don’t have enough time with idea to improve things later and that later never happens. I think every human developer knows that story.

Suggesting tests for the code

Writing tests is a must-have in the modern world. TDD makes software development better. As a human, I like to have tests. However, I find it challenging to write them. Can we use the machine to do that? Let’s see!

Regarding tests, the response code needs to be more accurate. It might be possible to improve results by feeding chatBot with Elixir test examples, but these tests are good as hints.

Creating Swagger documentation from JSON Schema

I like using JSON schema for validating HTTP requests. The question is — is that possible to convert a given JSON schema into a Swagger description so we don’t have to do double work?

Let’s see. Fortunately, I have a bit of JSON schema-type data in Crawly. Let’s see if we can convert it into Swagger.

Well, it turns out it’s not a full Swagger format; which is a bit of a shame. Can we improve it a bit so it can be used immediately? Yes, let’s prompt engineer it a bit:

Now I can preview the result in the real Swagger editor, and I think I like it:


What can I say? ChatGPT is a perfect assistant that makes development way less boring for regular people. 

Using ChatGPT when programming with Elixir can bring several advantages. One of the most significant advantages is that it can provide quick and accurate responses to various programming queries, including syntax and documentation. This can help programmers save time and improve their productivity.

Additionally, ChatGPT can offer personalised and adaptive learning experiences based on individual programmers’ skill levels and preferences. This can help programmers learn Elixir more efficiently and effectively.

The use of AI and NLP in programming is likely to become more widespread in the near future. As AI technology continues to improve, it may become more integrated into the programming process, helping programmers to automate repetitive tasks and improve their overall productivity. ChatGPT is just one example of how AI is already being used to improve the programming experience, and more innovations in this field will likely emerge in the future. 

Honestly, I am super excited and would love to explore the possibilities of AI even further!

Balancing Innovation and Technical Debt

Balancing Innovation and Technical Debt

Nelson Vides explores the intricate balance between innovation and technical debt.

Instant Scalability with MongooseIM and CETS

Instant Scalability with MongooseIM and CETS

Explore the enhanced scalability features of MongooseIM 6.2.1 with its improved CETS in-memory storage backend, offering flexible solutions for managing unpredictable XMPP server traffic.

The Golden Age of Data Transformation in Healthcare

The Golden Age of Data Transformation in Healthcare

In today's healthcare industry, data is the lifeline driving advancements and improving patient outcomes. However, the true value of this data is realized only when it is accessible and interoperable across systems.