Writing materials

Kamban, an India-based AI writing assistant developer

An India-based developer, who goes by the pseudonym Kamban, has developed an AI writing app for Mac called Elephas. It uses the GPT-3 model to help users write all kinds of content, including business documents, long-form articles, emails, social media posts, and even product reviews. Analytics India Magazine contacted Kamban to find out more about this tool.

Elephas – AI Writing Tool

There are many copywriting tools like Copy AI and Content AI, but most of them run on the premium model and don’t offer the “power of GPT-3”, as Kamban puts it. “I created a native application for Mac called Elephas using GPT-3. It runs on top of all your Mac apps and you don’t need to switch windows. I wrote the code in Swift programming language. This app takes your OpenAI keys and uses them for all communication. This is one of the main differences when you compare it to other AI writing tools, where they usually store your information. Elephas does not send your text information to our servers,” Kamban said.

An AI-based research and writing tool for professionals, the way Elephas works is that the user has to select text and options from the menu bar (eg rewrite). Elephas accesses the selected text and converts it into the requested format. Kamban initially built a simple wrapper and posted a sample on the HackerNews discussion board. “It kind of exploded, and Elephas was even trending on the HackerNews homepage for a while,” he said. He admits that even though the release didn’t look great at the time, it helped him get valuable feedback and a few paying customers.

Short product demo (2 min): https://vimeo.com/771041299

The next step was to collect feedback from end users. “What I presented initially was just a wrapper. Now there is a utils section in the app, which you can use to generate Google Sheets formulas to presentations. Suppose you want to write a presentation on the impact of air pollution in India. Just give the title and you will get the ten slides of the presentation. Users can fine-tune the presentation according to their objectives,” explained Kamban.

Kamban has adopted several methods to optimize the application. “I reviewed the key features used by our early adopters and adjusted the landing page to reflect them, resulting in better conversions. I realized that many of my users didn’t understand everything potential of the tool. I implemented a knowledge base tool and organized all the features in an easy to navigate structure. I also created product demo videos, created entirely by AI. With those- here, requests for assistance have plummeted,” he said.

Kamban has been building side projects for four years and has never generated any revenue. For the first time, the Elephas app recently hit $1,000 MRR over a five-month period. Elephas has over 200 professionals and content writers who use it daily.

Play with AI

Elephas isn’t the only product Kamban has built.

One of his projects called SwanSearch – a search engine designed for developers to provide them with in-place answers – offers code search, function search, and JSON validation in addition to displaying answers on the same page without the need to visit other websites in most cases. FlatGA is another active project that Kamban maintains which unifies all website metrics such as analytics, SEO, monitoring, and performance into one tool.

His other projects include a browser tab manager, an AWS cloud savings tool, and a GPT-3-based wellness assistant. Most of its tools are based on GPT-3. “GPT-3 offers features that I couldn’t find anywhere else. For example, it can produce remarkable output for new inputs, which in the past would have required a huge amount of training data and computing power. GPT-3 lowers the barrier to entry for many of my projects,” he said.

He added: “If you notice, companies are already hiring for a position called ‘Prompt Engineers’. We only start with advanced LLMs. GPT-4 could fix some of the shortcomings of GPT-3such as maintaining timeliness, better memory retention and creating good external references.

Kamban places great faith in the advancement of AI, especially large language models. He said LLMs are evolving faster than any other AI, which will have a huge impact on the way the world works – such as more personalized and adaptive learning experiences and increased use of data and analytics to guide the decision making.

He concluded that his ultimate goal was to make AI accessible to ordinary people. “I will focus on providing platforms where people can easily use the potential of AI,” he signed.