Category: Computing

Machine Learning Infrastructure at x.ai

For over 5 years now, at x.ai we have been applying machine learning to the problem of meeting scheduling. Our AI scheduling assistants  Amy and Andrew interact with humans through an email dialog and we have created machine learning models that capture relevant time, location and people information to help the virtual agents schedule meetings…
Artificial Intelligence, Computing, Product Updates

Reflecting on our tech stack in 2017

It has been three and half years since we founded x.ai. We have built an AI scheduling assistant. Our assistant (which goes by the names Amy and Andrew Ingram) is a fully autonomous agent. To build Amy and Andrew, we’ve needed to collect and process an enormous amount of scheduling related emails (5 million and…
Computing, Data, Startup

Amy now responds to your emails 2x faster

Amy and Andrew are performing in ways that even the best human assistant can’t match: they don’t sleep, they don’t take breaks, they never take a day off. x.ai’s approach to building a fully automated intelligent agent means our agents can operate with unrivaled speed and reliability. Over the past two weeks, we’ve halved the…
Artificial Intelligence, Computing, Data

Aspects of Deep Learning: Activation Functions

At x.ai, we have an organizational concept called “practices.” A practice is a group of people that come up with the best practices for a given area. Some of these practices are in the areas of data science, javascript, data engineering, and user testing. Some members of a practice are highly skilled in that area,…
Artificial Intelligence, Computing, Data

A peek at x.ai’s data science architecture

Amy and Andrew are AI personal assistants who schedule meetings for you. There’s no app. Nothing to download. Once you’ve agreed to meet with someone, just cc amy@x.ai and she’ll take over from there. You won’t hear from her again until she’s successfully negotiated a time and place to meet. We modeled Amy and her…
Artificial Intelligence, Computing, Data

How x.ai uses MongoDB to build Amy

Building and training your meeting scheduling assistant, Amy, from scratch requires an immense volume of data, flexible design models and a database that can handle it all. Our CTO and co-founder, Matt Casey, explains how as we see more and more use cases its important to have a Schemaless database that would support the dynamically…
Artificial Intelligence, Computing, Data

The Data Science that Animates Amy

Data science is at the core of Amy Ingram, our AI personal assistant, and Data Scientists make up a big part of our team. To animate Amy (and her twin brother Andrew), we are teaching her to understand scheduling related emails. Teaching machines to parse natural language alone is a daunting challenge (and represents an…
Artificial Intelligence, Computing, Data