About a week ago, NYC Media Lab held a demo day for a dozen new startup teams that graduated from the group’s twelve week “lean launchpad process”, a program which prepares the aspiring new companies to move on to “launch new products and services, participate in accelerator and incubator programs, compete for their next rounds of funding, and make their mark across a range of industries, including media and gaming, health, architecture and construction, and more.”
The companies represented an interesting cross section of ideas that include such technologies as virtual and mixed reality, haptics/wearables and AI. One of the startups focused on AI was VinoHunt, a team which bills its product as a “virtual sommelier” for those looking to imbibe. As with each team that pitched during the demo day, VinoHunt presented their concept (a chatbot interface for selecting wine), their target market (people who like wine but don’t know much about it) and their business model (they take a cut from from each sale they assist with from partner wine shops).
One of the company’s founders, Ben Chang, presented where they saw themselves relative to both online and physical wine retailers and marketplaces:
Since I am a fan of using chatbot interfaces to help make food selections, I decided to check the company’s website out where I was surprised I could actually use their alpha stage product to help find a wine. I clicked on a button that took me to Facebook Messenger and boom, I was chatting with the VinoHunt chatbot.
While it’s clearly a work in progress not ready for commercial rollout (this was a startup demo, after all, not a launch), the overall experience was fairly intuitive.
It first asked me what I wanted to do. I told them ‘find a bottle’:
Then it asked me about delivery options and told me they currently only work with NYC wine shop Astor Wine (just remember: they made this clear in the demo, the team clearly didn’t expect a nerdy analyst type to actually find their product and use it). I said I’d pick it up at the store.
It then asked me what the wine was for (I said ‘pair with foods’) and then asked the type of food I was eating (meat):
It asked me what type of meat (fish) and then asked me my preferred price range:
It then surfaced a selection of wines which, at this point, seemed to be the same across the meat types (again, this is a demo). What I did like is they also allowed me to get some info on the wine or request a tasting note. I asked for my details and it gave a nice description of the wine in a casual, descriptive format.
I then selected the wine and it took me to the wine retailers website.
While VinoHunt is the first Facebook Messenger powered wine sommelier I’ve seen, the company is one of many new efforts to bring AI to the world of wine. Companies such as Wine Ring, Vivino and even Google with their Google Assistant are developing AI-powered wine information products.
Long term, I expect to see an explosion in chat interfaces for applications like this. Like voice interfaces such as the one used for Google’s virtual sommelier ‘My Wine Guide’, chatbots make lots of sense for commerce-based decision making. As with voice, chatbots map well with commerce decision trees, but have the added benefit of being able to surface visually rich information such as showing the bottle of wine you may be about to purchase.
If you want to take an early tour of a work-in-progress virtual sommelier, you can check out VinoHunt here.