July 19, 2024
Amplitude taps AI to improve data quality, accelerate product analytics

Head over to our on-demand library to view sessions from VB Transform 2023. Register Here

San Francisco-based Amplitude, the product analytics player that helps companies study consumer behavior to make necessary optimizations and drive better returns, today expanded its core platform with new AI smarts, namely new features called Data Assistant and Ask Amplitude.

The capabilities use large language models (LLMs) to help enterprises consistently measure their data quality and more quickly go from business questions to insights. It marks the latest generative AI effort in the data and analytics space, following similar moves from players like Databricks and Akkio.

“At Amplitude, we want to bring the power of AI and LLMs to everyone who builds products. First in the form of features like Ask Amplitude that help our customers ask questions and learn more quickly from their product data, but eventually in the form of a whole suite of product infrastructure and tools that make building AI products easy,” Joseph Reeve, software engineering manager at Amplitude, said in a blog post.

The offerings are currently being tested and can be tried out by all customers starting today, the company said.


VB Transform 2023 On-Demand

Did you miss a session from VB Transform 2023? Register to access the on-demand library for all of our featured sessions.


Register Now

Measuring data quality with Data Assistant

As the company explained, the new capabilities target two specific areas within Amplitude: data governance and chart preparation. 

The Data Assistant looks at different events being tracked within Amplitude and considers a combination of factors — including the number of queries on each data point and the event volume — to determine an overall data quality score.

Amplitude Data Assistant
Amplitude Data Assistant

Once the score is ready, it evaluates each event against certain pre-defined best practices to come up with automatic bite-sized suggestions — prioritized in terms of impact — to improve quality and make the datasets clearer and more consistent.

For instance, the assistant could suggest grouping similar events into categories, helping other Amplitude Analytics users find the event they’re looking for more easily. Or it could recommend adding descriptions powered by OpenAI’s LLMs to high-priority events. 

The user just has to accept the suggestions to have them applied and improve their data governance posture.

Ask Amplitude accelerates product analytics

With Ask Amplitude, on the other hand, the platform is simplifying analytics consumption for its users. Until now, people using Amplitude had to construct charts step-by-step in the UI. The process was faster than writing SQL queries but still took some time.

Ask Amplitude is addressing this gap by giving users the ability to go from questions to insights right away. The user just has to ask their question in plain natural language.

“When you ask a question like, ‘Which of my videos has the highest conversion rate from watching to subscribing on iOS?’, the goal of Ask Amplitude is not just to tell you what the latest viral videos are. It’s to teach you how to build a funnel analysis; which events in your taxonomy represent watching videos and subscribing; and which properties contain the video and platform information. The resulting chart is a foundation of knowledge for you to build on and answer all sorts of follow-up questions on your own,” Reeve explained in the blog post.

As the user puts in a query, the offering first uses semantic search to check if an existing chart within the platform answers the question. If not, it uses a series of LLM prompts to convert the question into a JSON definition that can be passed to the company’s custom query engine and render a chart.

More to come

While Amplitude customers can test out both these features, it is important to note that this is just the beginning. The company plans to build on this effort and launch more AI-powered capabilities to transform how large enterprise teams drive insights from their product data and make business-critical decisions.

“It’s incredible what advancements in AI and LLMs have enabled in such a short time, but we know Ask Amplitude is only the beginning of how this technology will impact the way we do analytics. We’re rethinking the entire experience of how our customers understand their product data from the ground up — and we could not be more excited about the possibilities,” Reeve said.

So far, Amplitude’s product analytics platform has been adopted by more than 2,300 companies, including Atlassian, Instacart, NBC Universal, Shopify and Under Armour.

VentureBeat’s mission is to be a digital town square for technical decision-makers to gain knowledge about transformative enterprise technology and transact. Discover our Briefings.

Source link