My First Executive AI Win

Most of my experience with machine learning and artificial intelligence has been in art. (More on that below, for the curious.)

Today I’m excited to share my first “win” using AI as a business executive: Mendable. I can’t really take much credit other than to say that I’ve been keeping my eyes open, but the impact that Mendable will have on polySpectra is going to be truly transformative.

TL;DR - with Mendable I was able to train, test, and deploy a customer support chatbot on our full technical and product documentation in about 4 hours (and I will explain below how it could have been 40 mins.) If you run a business, have someone on your team try it today…you’ll thank me.

To put it simply, my team and I spend way too much time answering customer questions that are clearly in the documentation. “What printers can I use with COR?”, “What is the UTS of COR Black?”, etc. It’s not a great use of time for our team, but it’s clearly a necessary part of bringing prospects and customers up to speed.

I’m as guilty as anyone for not reading the instructions before opening something. (Including some close calls where I really should have read the MSDS before opening the package.) I’m not blaming our customers - we’re all under duress with today’s information overload. Not reading is simply necessary for survival.

But in manufacturing, optical equipment, and chemical safety - it is very important to read the documentation. So I had been on the hunt for a way to leverage the new developments in LLMs to help offload some of this burden. I also hate Intercom and other “dumb” chatbots - so I didn’t want to implement something that I wouldn’t be excited to use myself. A true win-win would be a chatbot that is helpful and properly trained on the product details and documentation, to help our customers get the information that they need in a matter of seconds, while keeping those “trivial” customer questions out of our inboxes. (The humans will answer the tough questions, for now.)

A major hat-tip to Mayo Oshin for turning me onto Mendable (via his execellent newsletter). I was actually considering learning LangChain myself to try to build out this idea. In this case, I’m incredibly grateful that someone built it first.

Starting the clock at when I clicked the link to from Mayo’s email, the sign up took a few minutes and I had successfully trained it on the product information from our Shopify account in less than an hour. Because we use Cloudflare to host our website, I ran into a technical hiccup where the Mendable bot was being blocked from scraping our documentation site from the sitemap, which thankfully the Mendable team was quickly able to work through with me over a couple of hours. Between lunch and dinner, I went from cold traffic to fully-onboarded customer running the app live on I was really impressed with the results from my test interactions with the bot, without any fine-tuning at all. I would encourage you to put my bot to the test!

In summary, I am currently the #1 fanboy of Mendable.

For the curious (& because I promised above):

My first machine learning application was for a composition for the Princeton Laptop Orchestra (PLOrk) entitled G, which was “an experiment in on-the-fly gestural machine learning, which utilized Rebecca Fiebrink’s Wekinator to translate motion into music.”

Many years later I briefly fell down another “AI art” rabbit hole with neural style transfer and guided diffusion, here are some fun results: