Introducing Tidepool!

The Aquarium team is thrilled to launch our new product, Tidepool! Tidepool does product analytics for AI text interfaces. With Tidepool, product teams can find patterns in their user text interactions to help make better product decisions.

It’s been very exciting to see all of the cool products that people have built with generative AI in the last year – from hobbyists to startups to big companies, it’s easier than ever to go from coming up with an idea to building a production AI app!

We’ve spent the last few months iterating on this product with a small set of design partners, and we’re excited to finally get it out into the world for everyone to use.

Solving ML problems -> solving product problems

The release of accessible large language models (LLMs) like ChatGPT, Bard, Llama 2 and others have massively reduced the technical barriers to deliver AI-enabled applications. Thousands of teams all over the world are now figuring out how to create compelling product experiences around LLMs, and we saw an opportunity to build a product analytics solution tailored to these new text-first interfaces.

In traditional visual user interfaces, users can click on buttons or navigate to different pages, generating interaction metadata that can be logged. Product analytics tools help you understand user behavior by constructing user funnels of which button users click, which pages they visit in what sequence, whether users convert, etc.

LLM apps have introduced a new paradigm for interacting with software, where users can work iteratively with the software via a natural language interface, generating user inputs and model responses consisting of unstructured text. Traditional analytics techniques don’t deal well with large amounts of unstructured text – it’s hard to summarize, it’s hard to aggregate, and it’s hard to effectively sample. AI developers resort to digging through a pile of hundreds to hundreds of millions of datapoints of unstructured text to understand how users interact with their product.

It’s critical to have tooling to get meaningful insights from these unstructured text interactions. With better insights into user behavior, teams can make better product decisions and get to product-market fit faster with this first generation of LLM-enabled products.

Enter Tidepool

Tidepool is a product analytics platform that solves these problems using a technology known as neural network embeddings. After you upload user text interaction events, Tidepool will:

  1. Automatically group your data by similarity. Tidepool runs embedding clustering on your users’ text interactions to surface interesting attributes: things like prompt topics, prompt languages, and common usage patterns that can be turned into shortcuts.
  2. Summarize common attributes in your data, using LLMs to determine what each cluster “contains.” For example, understanding that the most common topics that users discuss are business, education, and art.
  3. Track attributes in production traffic, allowing you to uncover how a specific attribute might be correlated to good / bad product outcomes. We utilize lightweight models running on foundation model embeddings to scalably extract these attributes from hundreds of millions of production interaction events.

Finally, Tidepool integrates into existing product analytics stacks so it’s easy for teams to get started:

  • Public API. Developers can easily import / export user activity data via a REST API.
  • CDP Support. We also support common CDPs (e.g. Segment) for production scale integration. 
  • Integration with existing tooling. Whether you use Segment, Hightouch, Census, or want to send events directly from your app, Tidepool works with your data and the tools you already use.

Aquarium’s mission has been to make it easier for people to build and improve production ML systems that solve real-world problems. While we started with computer vision in a world of custom model training, we’re excited to utilize the technology and expertise we’ve developed over the past few years to support the new wave of AI applications that is going to change the world!

If this is interesting to you, feel free to try the product out for yourself, join our Slack community and leave some thoughts, or schedule some time with us to talk.

Cofounder and CEO at Aquarium. Formerly an early employee at Cruise, deep learning researcher at UC Berkeley, and intern at Pinterest + Khan Academy.