Deana.AI® is a virtual assistant that uses GTP-3 and a custom NLP model behind the scenes to understand and execute user commands. Users communicate with Deana.AI® using simple text by email and in messengers and web chatbots.
Email is a traditional way of digital communication between people in business and everyday life. Services like Gmail and Outlook help us exchange sensitive information and plan activities in advance.
Our idea was to use email to interact with artificial intelligence (AI) and give it commands. Email acts as a communication interface between the user and AI.
For example, you send the AI an email, "lunch with Dave at 5 pm," to have your schedule updated and the invitation sent to Dave. After business lunch with Dave, you email the AI a photo of the restaurant receipt. Then the system automatically recognizes the items and amounts on the bill and adds this information to your online expense report. In the end, sending these text commands to the AI takes just 5-10 seconds, saving you much time as you don't have to update your schedule and report yourself.
Here are a few more use cases for our email-first AI assistant:
As Intersog already had a sufficient experience in AI development, we quickly formed a team that included these roles:
We chose between several NLP models to find the one best fitting our technical expertise and project requirements. After some experiments, we decided on GPT-3 (Generative Pre-trained Transformer 3), which demonstrated the best results in our tests.
We programmed in Python and Node.js. We fine-tuned the GPT-3 model in our knowledge domain. As a result, we created a custom NLP model that ran on Nvidia's GeForce 3000 series GPU.
Our model required both automatic and manual correction. Humans analyzed the answers generated by the model, found errors, and corrected them to improve the model further. In this way, we minimized errors and improved the model's functioning.
In early prototypes, Deana.AI® worked through email. First, the user could email a command as free text. Then, the system used its NLP model to classify the received data, formulate an adequate response, and do the user's command.
Later, we developed an interface in the form of an AI virtual assistant that can embed on any website. After that, we integrated Deana.AI® with Viber chatbot, Amazon Alexa, Google Assistant, Apple Siri, and Telegram bot, which allowed users to communicate with the assistant from mobile.
After six months of prototyping and development, we released Deana.AI's first version designed for individual users. This solution was positioned as an email-first virtual assistant to interact with the AI via email and simple text.
After a month of improvements and updates, we started developing a new version for business users. The idea was to make an enterprise intelligence system for searching and organizing business data using Deana.AI's custom NLP model. Currently, our team continues to develop this version.