NLP Powered Email Assistant

Managing a cluttered inbox is a daily struggle for millions of email users. Over time, subscriptions, promotional content, and non-urgent updates pile up, making it harder to notice essential messages and stay productive. Many users find themselves spending unnecessary time sorting, archiving, or deleting emails to keep up with their workload.

To address this, we developed a Chrome extension that enables users to automatically organize their inbox, categorize messages by intent, and unsubscribe from unwanted emails directly within Gmail. The extension utilizes a fine-tuned transformer model to accurately and efficiently classify emails, providing users with a clean inbox with minimal effort.

By combining intelligent automation with tight browser integration, the solution empowers users to regain control of their inbox without requiring complex setup or ongoing maintenance.

Traditional keyword rules were not sufficient. Understanding nuanced email intent needed a strong NLP model fine-tuned on real-world inbox data.

Inference speed needed to be fast enough to classify emails in real time without disrupting the user experience.

The extension needed to work seamlessly with Gmail’s UI and Gmail API without requiring server-side access to user email content.

The system had to accommodate thousands of daily users with consistent performance and reliability, while minimizing infrastructure costs.

To solve the classification problem, we fine-tuned a BERT model on a custom dataset built from hundreds of thousands of anonymized email samples categorized by real users. This dataset captured a wide variety of promotional, transactional, personal, and spam emails, which greatly improved model accuracy across edge cases.

To meet performance requirements, we distilled the BERT model and exported it to the ONNX format, optimizing it for inference to enable lightweight and fast predictions within the Chrome extension.

The extension integrated directly with Gmail’s API to read metadata and content from emails and then displayed intuitive UI options to filter, categorize, or unsubscribe.

All the services were deployed using AWS infrastructure for a low-maintenance and cost-efficient solution that could scale without manual intervention.