Join the Newsletter

Stay up-to date with food+ag+climate tech and investment trends, and industry-leading news and analysis, globally.

Subscribe to receive the AFN & AgFunder
newsletter each week.

Big data and artificial intelligence concept. Machine learning and cyber mind domination concept in form of women face outline outline with circuit board and binary data flow on blue background.

Meet the AI-powered cannabis app that wants to help you find the exact high that you’re looking for

July 30, 2019

Tired? Anxious? Chronic pain? Trouble sleeping? There’s probably a strain of cannabis for that and Namaste Technologies is using an AI-powered app to help you find it.

Cannabis is one of the fastest-growing consumer industries, but there’s a serious lack of data about the unique characteristics of different strains of cannabis, according to Namaste Technologies’ CEO Meni Morim.

“I had a chat with a dispensary owner in Colorado and I asked him what happens when people walk into your dispensary and ask which strains to use to achieve certain effects like treating a symptom. A lot of people self-medicate with cannabis; it’s not just about getting baked,” Morim told AFN. “He said it’s a coin toss. Some bartenders know and some don’t. And even those who know don’t always have the right information to help a patient make the right decision and that’s a problem.”

The startup’s new app, Uppy, uses AI technology to track customers’ usage patterns, medical needs, and product reviews for the purpose of offering more personalized recommendations. Customers can also make notes about their experience with different strains of medical cannabis so that the app can help them get closer to the strain that’s best suited for their particular ailment.

Having spent the last several decades as a highly controlled substance, there haven’t been many opportunities to perform research on cannabis or to collect information from consumers. And for users who purchased cannabis through illegal channels, it was incredibly difficult to know the specific strain for each purchase.

“It gives patients a tool that allows them to quantify what a specific strain does for them – whether it is a positive or negative impact on their symptoms, the time of day they used it, the quantity, all of those things,” Morim explains. “On the back end, we collect all of this data anonymously and use it to train the machine learning models so that the app can tell a patient with specific symptoms which strain had the best results for people who also had those symptoms.”

Machine learning is becoming a popular tool in the foodtech space, as more startups are aiming to help finders find solutions faster. Machine learning can seem like a confusing concept, but if you’ve ever raised a toddler, the gist is all too familiar to you.

A machine learning algorithm is only as good as the information it’s fed, Morim explains, and obtaining the right output is a matter of correctly teaching the algorithm the difference between certain data points. If you want to teach a child what the color blue is, you show it a few different things that are blue and say, “This is blue.” Eventually, they will be able to see something that is blue and make the identification on their own. But if you show it things that are orange and tell the algorithm that they are blue, the algorithm won’t offer useful answers.

Part of Uppy’s challenge is managing the integrity and consistency of users’ input regarding their experiences with various strains. Cannabis consumption can be an incredibly subjective experience and it’s not always easy to put into words the way a particular strain or product makes you feel.

“There are two ways that we overcome this. The first way is controlling the openness of the input that each user can provide. It’s not free text; it’s specific choices such as providing us with a current severity of symptoms on a scale from one to 10. They can also report feelings like sleepy, happy, confused, or uplifted,” he explains. “We also clean the data before we put it in the algorithm in a programmatic way based on statistical deviation models.”

Morim is no stranger to the software space, having spent more than 19 years creating tools to help retailers keep digital shoppers happy including Findify, an AI-based turnkey solution that enables e-commerce sites to personalize search results, recommendations, and product collections based on a user’s specific behavior and proprietary machine learning technology. 

He’s also one of the few agritech entrepreneurs to openly admit that there are challengers in the space in lieu of giving the standard canned answer that he lacks competitors because his technology is so differentiated.

Medical marijuana data analytics company Strainprint is Uppy’s closest competitor by his account, and a few younger companies are creating comparable solutions. The primary difference is that Uppy hopes to convert app users to purchasers of products on its e-commerce platform CannMart, which is a Canada-based wholly-owned subsidiary of Namaste Technologies.

“Uppy is free and always will be. Once we can really integrate Uppy into CannMart, you will be able to search for the strain that meets your needs, click on the recommendation, and it will direct you right to CannMart where you can make the purchase,” Morim explains. “And all the while we are still collecting quality, structured data for the machine learning algorithm.”

Join the Newsletter

Get the latest news & research from AFN and AgFunder in your inbox.

Join the Newsletter
Get the latest news and research from AFN & AgFunder in your inbox.

Follow us:

AgFunder Research
Join Newsletter