The winners of the Nylas & AI: Email and Calendaring for the future hackathon

Come and meet the Winners and Runner-ups of the Nylas & AI: Email and Calendaring for the future hackathon

The winners of the Nylas & AI: Email and Calendaring for the future hackathon

On August 8th, 2023, we launched the very first Nylas Hackathon. It was an online hackathon that lasted until October 2nd, 2023. It was an excellent opportunity for people worldwide to discover, learn and build using the Nylas APIs for email, calendar, and contacts. Let’s go over the hackathon and highlight the top projects!

What are we going to talk about?

Mosaic Virtual Assistant – Hackathon Winner

Congratulations and a big round of applause for our Hackathon Winners:

Nylas & AI Hackathon Winners

Jose Herminio Parreno

Lucia Fargallo

Jean Francois Gutierrez

Who built the Mosaic Virtual Assistant project:

Mosaic - Nylas & AI Hackathon winner project

What it does

Mosaic is an AI-powered virtual assistant that goes beyond the typical features. It fully leverages the capabilities of the Nylas API, Langchain, and OpenAI’s GPT-4 to offer unparalleled experience in managing your digital communications. Alongside intelligent email categorization, calendar management, and contact organization, Mosaic also provides image generation and speech-to-text recognition functionalities. These features make Mosaic not just an assistant but a comprehensive tool that integrates deeply with Nylas to make your life easier.

How they built it

The heart of Mosaic lies in its seamless integration with the Nylas API, which is central to all its functionalities:

  • Backend (Node.js): Developed specifically around the Nylas API, this backend fetches and manages email, calendar, and contact data.
  • Backend (Python): Houses the Langchain Framework and connects to OpenAI’s API, adding layers of intelligence for natural language processing, image generation, and speech-to-text recognition.
  • Frontend (React): Crafted to provide an intuitive interface, making the Nylas-powered features easily accessible.
  • Nginx Proxy: Manages web traffic, directing it to the appropriate services.

Here’s the project on GitHub.

VoiceCal AI – Hackathon Runner-up

Congratulations to the first runner-up of our Hackathon:

VoiceCal - First Hackathon runner up

What it does

VoiceCal AI allows users to interact with their calendars using natural voice commands. Users can add, edit, and manage events effortlessly. Additionally, it integrates with the Nylas API to provide real-time event updates and a comprehensive dashboard.

How they built it

I built VoiceCal AI by leveraging the following technologies and tools:

  • Nylas API for calendar integration.
  • Node.js for the backend server.
  • Speech recognition technology for voice commands.
  • AI tools for natural language processing.

The development process involved carefully integrating these components to create a seamless and user-friendly experience.

Here’s the project on GitHub.

NAP (Nylas & AI Project) – Hackathon Runner-up

Congratulations to the second runner-up of our Hackathon:

NAP - Second Hackathon runner up

Overview of the project

This project allows you to get more meaningful insights and data from your contacts & emails. As it is incorporating Nylas, so fetching and syncing up data from your email and contact provider is as easy as a breeze. As this is all happening inside the Coda environment, AI will automatically work upon the fetched data and will provide a lot of detailed output. From syncing in emails from different accounts and getting their tones/summary, getting the summary of all conversations in a thread, to wishing your loved ones happy birthdays, you can do many things. Do read the content below and watch the video to understand what this project provides.

Here’s the project on GitHub.

Nylas-Care – Hackathon Runner-up

Congratulations to the third runner-up of our Hackathon:

Nylas Care - Third Hackathon runner up

What it does

Nylas Care is a Secured Online Medical Appointments Booking System Powered by Nylas EMail, Events & Calendar API, ChatGPT AI, Pangea Sensitive Data Redaction AI, Expert.AI Data Summary & Sentimental AI.

Patients – Doctors Medical Appointments Booking Made Easy with Nylas API & AI

  • Nylas Email API: For sending Email Notifications when Patients book medical appointments. It is also used for Doctors-Patients Communications and also for sending Drug Prescription to Patients’ Email Addresses
  • Nylas Events and Calendar API: For Storing and querying  Medical Data to and from Nylas Events AI Cloud System. All Appointments data are seen on Google Calendar
  • ChatGPT AI: for prescribing drugs for patients and then automatically sending the prescribed drugs to Patients’ Email Addresses via Nylas Email API
  • Pangea Sensitive Data Redaction AI: (https://pangea.cloud/) Used to safeguard and protect Patients Medical Sensitive Data(PII) from being sent as part of Medical Data during Appointment booking to help prevent Sensitive Data Compromised
  • Sentiments API (https://expert.ai): To help Doctors run a sentimental analysis of Patients’ Medical Appointments Data to break down the Contents into more easily, understandable and digestible forms. It analyzes each patient’s Email Medical Data for Positivity, negativity or neutral statements
  • Keyphrases(Summary) API (https://expert.ai): To help Doctors pinpoint all the Keywords keyphrases and ultimately provide the summary of the Medical Data and, thereby saving Time and Energy

How they built it

PHP, MYSQL, Nylas API, Pangea AI, Expert AI and ChatGPT AI.

Here’s the project on GitHub.

Nylasum – Hackathon Runner-up

Congratulations to the fourth runner-up of our Hackathon:

Nylasum - Fourth Hackathon runner up

What it does

  • This project can showcase the most recent e-mail messages specified by the user, displaying each one’s Message ID, Subject, Sender, and Unread Status.
  • If the user is intrigued by one of these messages, they can view its body in text format by supplying the desired Message ID.
  • Should they wish to summarize that message, they can do so with a significant language model by providing the desired Message ID.
  • The model’s generated response is then saved in a database for faster viewing.
  • After this, the user can choose to post this summary on Twitter/X if the message has any news the user wants to share with the world, including
    • Product launches
    • Hiring news
    • Technological developments
  • They are presented with the summary for review and must confirm they want to post it on Twitter.
  • Should the summary be longer than 260 characters, it is released as a thread of posts, each 260 characters long.

How they built it

They constructed this with the Nylas Email API at the core, as it gave us access to all the data we needed for messages. When searching a message’s body, the API provides the message as an HTML string, and we clean this into a text-only format through BeautifulSoup.

To perform summarization, we used a large language model for our artificial intelligence component. More specifically, we used llama-2-7b-chat-hf. One reason why we chose this model was because of how Meta open-sourced the model. This allowed us to set up our local instance of the model, and this ensures users their e-mails, some of which are confidential, are secure. Additionally, we used the 7B parameter version as this could run on the NVIDIA T4 GPU provided by Google Colab’s free tier. We needed Transformers to use the model and LangChain to create a template for prompts. It takes the model some time to generate summaries of messages, so we use an SQLite3 database to store summaries and retrieve them for the user when needed.

Letting users tweet their messages was made possible by Tweepy accessing the Twitter/X API. We segmented the string by 260 characters instead of 280 characters because of newline characters potentially exceeding the limit. All of these components are stitched together and operate within Python3. The user interacts with the program in a Colab notebook using a text-based interface and can view shared summaries on their Twitter/X account.

To use this project, credentials for both the Nylas and Twitter/X APIs are needed.

Alongside this, a token to a Hugging Face account approved to use LLaMa 2 by Meta is needed.

Here’s the project on GitHub.

LinkLoom – Hackathon Runner-up

Congratulations to the fifth runner-up of our Hackathon:

VoiceCal - Fifth Hackathon runner up

What it does

LinkLoom allows users to collaborate within email threads by adding annotations. Users could highlight specific parts of an email, leave comments, and share these annotations with other authorized collaborators. This would be valuable for teams working together on projects or handling complex email discussions.

How they built it

They used Django to develop the API with Postgresql as the DBMS, Nylas Email API for retrieving emails, and openAI for auto-generating annotations.

Here’s the project on GitHub.

Let’s meet the judges

Being our first Hackathon, we want only Nylas people judging the projects. We thank our judges for their time and their insights:

Nylas & AI Hackathon Judges

Let’s meet the Managers

Thanks to our managers, for making sure that the Nylas Hackathon ran smoothly.

Judge Blag
Judge Ram

What were the prizes?

A Hackathon cannot be a hackathon without prizes, for our first Nylas Hackathon we had this:

Hackathon Prizes

Watch the official announcement

You May Also Like

Transactional Email APIs vs Contextual Email APIs
Best email tracker
Find the best email tracker and elevate your app’s email game
How to create and read Webhooks with PHP, Koyeb and Bruno

Subscribe for our updates

Please enter your email address and receive the latest updates.