Behavior-tracking software firm Amplitude Inc. is adding artificial intelligence capabilities to its products by launching a data quality adviser and generative AI capabilities that make it easier to construct queries.

Ask Amplitude enables users to shortcut constructing queries by stating them in natural language. It’s meant to be a coach rather than a black box, wrote Software Engineering Manager Joseph Reeve in an Aug. 8 blog post.

“The goal of Ask Amplitude is not just to tell you the latest viral cat videos. 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,” he wrote. “The resulting chart is a foundation of knowledge for you to build on and answer all sorts of follow-up questions on your own.”

Semantic search

The digital assistant uses semantic search — a technique that looks for terms that are similar to those queried but not an exact match — to comb through the content inside the user’s Amplitude instance. The intent is to find relevant content that is already in the system and doesn’t require a new query.

Ask Amplitude also uses a series of large language model prompts to convert a user’s question into a JavaScript object notation definition that can be passed to Amplitude’s own query engine.

“We’re the first company in this space to actually come out with something that a lot of companies have talked about but haven’t released publicly,” said Chief Executive Officer Spenser Skates. “A lot of other companies have moved from pointing and clicking to a chat interface but they haven’t taken the next step, which is how to provide intelligent insights.”

Self-service analytics has been growing in popularity as businesses’ efforts to become more data-driven have been hampered by an overwhelming volume of requests their data science and engineering teams need to field. Allied Analytics LLP’s market research arm expects the market for self-service business intelligence to grow 15% annually through 2026, to more than $14 billion.

Smarter governance

Data Assistant automate some of the manual elements of data governance by providing intelligent recommendations for improving data quality. “For example, a purchase event on an e-commerce site is likely more critical to your business than viewing a product detail page,” wrote Alan Okada, principal product manager for Amplitude. “Our AI-powered Data Assistant looks at a combination of factors — including the number of queries on each data point and the event volume — to determine an importance score.”

The assistant evaluates each event against the best practices Amplitude has gleaned from its customer base to group similar events into categories and deliver a list of suggestions for improving data quality. “For example, instead of just identifying that several unrelated events are missing categories, Data Assistant finds similar events and suggests a category grouping appropriate to these events” derived from patterns in a company’s own data and semantic embedding, which categorizes data elements based upon their similarity to other terms, Okada wrote.

Skates said AI has enormous potential in business intelligence. “Right now analytics is just passive, where you’re just reporting stuff out,” he said. “With AI changes you can actually make analytics proactive and tell the application to do things like run an experiment, turn on a feature flag or customize the text or images. It can proactively improve the product without human intervention.”

Both features will be a standard part of Amplitude’s software-as-a-service.

Image: xresch/Pixabay