Part 2 of 3 of the Meet Posh’s NLP team series.

by: Nicholas Leonard, Boston-based Entrepreneur, Product Leader, and Startup Advisor

Even though I’ve lived in the Northeast for the past decade and a half, Michelle Fullwood — a Natural Language Processing (NLP) Scientist at Posh — spots a tell-tale vowel pattern in my accent that tells her I grew up outside the region. I quickly learn that Michelle’s deft identification shouldn’t come as a surprise; she is a linguist with a PhD in Linguistics from MIT, and a polyglot who has studied over a dozen languages to various degrees of fluency, including French, Mandarin, Japanese, Arabic, and Hieroglyphic Egyptian.

When you were young, what did you want to be?

Part 1 of 3 of the Meet Posh’s NLP team series.

by: Nicholas Leonard, Boston-based Entrepreneur, Product Leader, and Startup Advisor

Language is at the center of communication

I sat down with Rishi Sharma to learn more about the people behind Posh’s Natural Language Processing engine which powers one of FinTech’s most disruptive products: a chatbot for Credit Unions. Immediately, Rishi quickly clarifies: Posh isn’t just building chatbots; it’s fostering natural conversations. Rather than robotically spew answers, Posh’s chatbots seek to understand and delight users, remembering and reincorporating previous parts of a conversation while conveying human connection in addition to quick competence. Rishi is passionately invested in furthering Posh’s mission to make conversational AI more natural because human-like user experiences beget better technology at large. …

by: Michelle Fullwood, NLP Engineer

Image for post
Image for post


Welcome back to Posh’s AI Academy series. Our first post in this series touched on Artificial Intelligence (AI) and Machine Learning (ML). Now, let’s zoom in on a sub-area of the field called natural language processing, or NLP for short, which is basically AI/ML applied to just about any task that involves understanding or generating natural language. Usually, NLP refers to dealing with natural language as written text, and speech processing is used to refer to dealing with natural language as spoken utterances.

We’ll talk about the tasks involved in NLP, focusing on those most pertinent to building a chatbot, like our Posh chatbot, which helps credit unions answer common questions and execute banking tasks for their customers. …

by: Dhairya Dalal, NLP Engineer


Welcome to Posh’s AI Academy Series! As summer closes and school is getting back in session, Posh’s AI Academy will help you get up to speed on AI and machine learning technologies and how they can solve business challenges. No PhD required! Over the next few blog posts, we’ll introduce key AI concepts and technologies with their enterprise applications.

First up is an intro to AI and Machine Learning. …

By: Anna Rychlik, Design Intern

Image for post
Image for post

As I am wrapping up my 14-week internship with Posh Technologies, I have been able to reflect on my experiences and takeaways from this incredible opportunity. I can’t thank the Posh team enough for all of their transformative guidance and support!

Here are my 5 key takeaways:

  1. Be Flexible!

When I applied to Posh, I originally applied to a Business Development Internship role. However, because of my background in design, I was able to quickly pivot into lots of design projects for the company. I was able to work on everything from sales and marketing one pagers, to a pitch deck and some website work. Working on so many simultaneous projects forced me to hyper prioritize and build design assets from the ground up. …

by: Matt McEachern, Posh Co-founder and CTO

Image for post
Image for post

CSRF, which stands for Cross-Site Request Forgery, is a common attack vector for vulnerable web applications with potentially catastrophic consequences. At number 8 in the 2013 OWASP TOP 10*, CSRF is an age-old attack that has been well-known by both hackers and implementers [1].

While there is a multitude of accepted prevention techniques, each has its pros and cons. Amongst the most popular and recommended techniques are ones that implement a CSRF Token. The CSRF Token technique requires that all state-changing endpoints accept an additional parameter (i.e. the CSRF Token) whose value was sent alongside the html/css/js of the web application. Upon each request, the web application’s backend server verifies the correctness of this token and rejects the request if it does not correspond to the session. A decent analogy is that while session cookies authenticate the request’s browser, CSRF Tokens authenticate the code that’s making the request. …

by: Israel Ramirez, Business Development & Software Engineering Intern

Image for post
Image for post

At a time when Americans have many options for financial institutions, many opt for their local credit union for basic financial services. As of 2019, there are 5,236 credit unions supporting 120.4 million members in the United States. So, what exactly are credit unions and how are they different from traditional banks?

Credit unions are member-owned, nonprofit financial institutions that provide basic financial services and credit at competitive rates, while emphasizing the importance of excellent customer service and community involvement.

Credit Unions Require Some Sort of Affiliation to Join

In order to join a credit union, you need to qualify for membership. Credit unions have their own set of qualification requirements which vary depending on the Credit Union’s affiliations. Common affiliations include an employer, school, church, or town. While these requirements may paint credit unions as exclusive, most consumers will have the ability to join a credit union through some means; the easiest ways to qualify tend to be through an employer or residence in a certain location. …

by: Posh’s Business Development and Data Science Intern

Image for post
Image for post

What is a chatbot and how does it work?

Most people have used a chatbot before and probably think of it as “that bubble that pops up when I’m purchasing a flight or having trouble processing a return.” What really is a chatbot, though? The fancier answer: conversational artificial intelligence streamlines human interaction with computers. For simplicity’s sake, though, you can really think of chatbots as another Customer Service Rep. Like humans, they understand human input through written or spoken language. Like reps, they’re designed to hold complex conversations about specific topics.

There are many different types of chatbots in the world today, from e-commerce chatbots to customer service chatbots and virtual assistant chatbots (e.g. Siri or Alexa). …

by: Karoline Lin, Business Development and Analytics Intern

Image for post
Image for post

Given how technologically advanced chatbots have become, many of us perceive them as a contemporary concept. However, these digital helpers have been around for more than half a century!

How did we get to where we are today? Let’s check out the top milestones in chatbot history:


Eliza || 1966

Eliza, the Rogerian therapy-bot, parsed user prompts and matched them to potential scripted responses. It was not only the first chatbot, but also one of the first machines to show a hint of humanity. …


Posh AI

Conversational AI Company that spun out of MIT in 2018 🚀 We create Intelligent Chatbots and Nex-Gen Phone Technology 📲

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store