Do you love ChatGPT?
Do you want a better way to interact with your ecommerce data?
Do you wish you had an always-on employee to help you manage your business?
Meet Willy, your new AI Ecommerce Assistant. Analyzing, managing, and interacting with your business data just became as easy as talking to ChatGPT, within Triple Whale!
Willy is built on Triple Whale’s own machine learning and powered by OpenAI, and can run queries in GPT 3.5, GPT 4, and Natural Language Query (NLQ). It’s basically an AI chatbot Swiss army knife.
You can use Willy in 2 distinct ways.
By accessing the data on your Triple Whale Summary page and our industry benchmarks (coming soon!), Willy helps you review and take action on the hard-to-calculate questions that impact your business.
Willy is pre-loaded with awesome query suggestions, like “What is my ad spend today?” or “What is my best creative over the last week?”
You can click on the suggestions to pull them into the dialogue box and automatically prompt Willy. You can also access previous questions in the chat bubble to the left of the dialogue box.
To get your creative juices flowing, here are some additional prompts to try with Willy.
Note, the above prompts work best when run on the NLQ (Natural Language Query) Model. This model is best for accessing specific metrics from your Shopify store. Below are more tips and tricks to help you get the most out of Willy.
You can choose to use all the information OpenAI has to offer by toggling to “Use ChatGPT” or focus on your own proprietary data set by toggling back to “Use Triple Whale.”
When provided with exact numbers, be sure to double-check them against your data in Summary.
Just like chatting with other AI assistants, Willy remembers what was asked earlier in the conversation. And follow up questions always help when trying to refine the output and get the information you need.
And here are some best practices around each of Willy’s language models:
GPT-3.5 is a series of models trained on a blend of text and code from before Q4 2021. While generally faster than GPT 4, this model is less likely to provide accurate information, particularly numerical.
This is the free version of ChatGPT that we all know and love–use this to generate versions of ad copy, blog outlines, brainstorm ideas, and more.
According to OpenAI, “GPT-4 is a large multimodal model (accepting image and text inputs, emitting text outputs) that, while less capable than humans in many real-world scenarios, exhibits human-level performance on various professional and academic benchmarks.”
“For example, it passes a simulated bar exam with a score around the top 10% of test takers; in contrast, GPT-3.5’s score was around the bottom 10%.”
TL;DR: The difference between GPT 3.5 and GPT 4 is subtle but GPT 4 is more reliable, creative, and can handle more nuanced instructions compared to GPT 3.5.
NLQ (Natural Language Query) is a proprietary machine-learning model based on Triple Whale’s BI. NLQ can access the key metrics from your Shopify store.
We're excited for you to meet Willy 🐳.
This is a real building-in-public experience and we’re thrilled to share it with you. The chatbot will get smarter every week with additional capabilities. Soon everything you can do in Triple Whale, you can talk through with Willy (and much more).
You can chat with Willy (V 0.1) in Triple Whale today.
Join the waitlist to access future iterations of Willy before anyone else -- we're pumped to show you all it can do for your ecommerce operations.
© 2023 Triple Whale Inc. – 7th Floor, Jaffa St 224, Jerusalem, Israel