Developing an Email-First AI Virtual Assistant Using GPT-3 and a Custom NLP Model.

Company

Intersog

Industry

Technology

Headquarters

United States

Client Since

2021

Technologies

DatabasesMachine LearningArtificial IntelligencePythonNode.jsReactMongoDB

Team Location

Ukraine

Team Size

5-9

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.

Idea

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:

Key Features

Plan events and tasks
Track expenses, bills, invoices, and more
Manage files stored locally and in the cloud
Find necessary information on the web (white papers, articles, news)
Summarize and paraphrase documents
Find routes and locations on the map

Team

As Intersog already had a sufficient experience in AI development, we quickly formed a team that included these roles:

NLP Model

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.

Natural, human-like conversations

CONTEXTUAL

Deana.AI® understands what you're saying as she maintains the conversation context by learning more about your preferences relating to your communication style.

CONVERSATIONAL

Use simple text or voice to chat with Deana.AI® assistant. She comprehends your intent and responds fast in a human-like manner.

OMNICHANNEL

Use email, messengers (WhatsApp, Viber, Telegram), or voice assistants (Siri, Alexa, Google Assistant) to chat with Deana.AI® at any time.

CONFIDENTIAL

Deana.AI® employs encryption and security protocols to keep sensitive user information 100% confidential.

UI and Integrations

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.

Release and Development Plans

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.

Others Case Studies

    Tell Us About Your Project

    I give my consent to Intersog to process and retain my personal data as set out in the retention section of the Privacy Policy.

    How can we help you?

    Book a meeting

    Meet our client success specialist. We'd love to hear from you.

    Get inspired

    Discover why Fortune-500 companies trust Intersog.

    Hire talented developers

    We fill IT roles within 2 weeks. Choose the tech skills you need.

    TRUSTED BY:

    TOP RATED BY: