What is QuillQuery
QuillQuery, a Minimally Viable Product (MVP), aims to revolutionize email search by leveraging cutting-edge Artificial Intelligence technologies and approaches such as Retrieval-Augmented Generation (RAG) and Large Language Models (LLMs) to empower users lightning-fast, highly accurate email search experiences regardless of how they organize their inbox or what email application they use.
While our MVP is currently hosted as a web browser, our ultimate aim to deliver a plug-in to your browser that provides users a universal, adaptable solution that integrate across diverse email platforms, from Gmail to Outlook.
A unique feature of our product is that it offers users the option of selecting an LLM that best suits their search needs to give you unparalleled flexibility and control over your search experience.. You have a question or a topic that you want more context around; no worries as QuillQuery provides several. Perhaps you do not need those details and just want a straight yes or no answer or piece of information; our LLM offerings include those that are more direct.
Thus, our innovative, platform-agnostic techniques seamlessly integrate with any chosen LLM, maintaining peak performance regardless of the email ecosystem. This empowers individuals to effortlessly find and utilize information buried in their inboxes, boosting productivity and reducing digital clutter while enjoying a familiar, powerful search experience across all their email accounts.
Email, Email, Email
As of 2019, the average emails sent/received per day for business emails was 126. This number likely grew during and following the pandemic due to an increase in remote work and the overall digitization of many different industries. In addition to the sheer quantity of emails an individual receives, average professionals spend 28% of their workday reading and answering emails. With over a quarter of the work day being spent in the inbox, working individuals typically follow one of two approaches to keeping things up to date; zero everything out or retain everything in their inbox. As a result, there’s an opportunity to make the email experience a more productive one for working individuals around the world.
Email services, such as Gmail or Outlook, still use rules-based and keyword searches. Gathering information from your inbox that is pertinent to a search at hand is cumbersome, and most of the time, does not yield what you want it to. With Quill Query, we are designing a way to make the average working experience more curated and more efficient for an improved daily experience.
Furthermore, frontier models for Large Language Models (LLM) continue to develop at a rapid pace, but users are locked into using the models associated with the email provider (e.g. ChatGPT for Microsoft’s Copilot, Gemini for Gmail, etc.). For users that switch between applications for viewing their email or those that use a provider without such a tool, there are inconsistencies across user experiences as a result of many aspects including the features of the LLM (e.g. training data, training features, etc.). The burden, then, is transferred to users who either need to use traditional brittle rules-based queries because a RAG tool does not exist or need to adjust their queries to each application if one does.