Flo Health adopts Databricks platform to power analytics and AI

FemTech firm Flo Health has adopted a data intelligence platform from Databricks to power its analytics and AI initiatives and deliver personalised menstrual cycle predictions.

The team implemented the Databricks solution to replace fragmented data systems and legacy infrastructure that made it difficult to deliver cohesive, AI-powered user experiences at scale.

Roman Bugaev, chief technology officer at Flo Health, said: “Our previous systems couldn’t handle the scale and complexity of our data.

“Databricks’ Data Intelligence Platform provided the centralised data and AI platform we needed to innovate much faster and create a purpose-driven data strategy with data democratisation at its core.”

Since adopting the platform, Databricks says that Flo Health has improved its data management and utilisation, strengthened data governance and enhanced its ability to deliver personalised health insights to its users worldwide.  

Its internal monthly active users have increased by 45% and weekly active users by 57%. 

The Flo team is using Databricks to fine-tune large language models for ‘Ask Flo’, its generative AI-powered health assistant, using Mosaic AI, Databricks’ solution for domain-specific AI agent systems.  

To meet stringent compliance requirements, including those relating to data privacy, Flo Health uses Unity Catalog, an open governance solution for data and AI, to enforce access controls and data governance throughout its data workflows — enabling features like ‘anonymous mode’ to safeguard sensitive customer data. 

Nearly half (46%) of Flo Health employees, including engineers, data scientists and business analysts, actively use Databricks each month to make informed decisions. 

The team has also been piloting AI/BI Genie, a capability within Databricks that leverages generative AI to help business teams interact with their data using natural language to ask questions like “What were our active users for last month?” and receive instant answers. 

Flo Health has also used Databricks Assistant, a conversational AI assistant, to streamline structured query language (SQL) query debugging.

As part of a broader initiative called ‘Copilot’, with Databricks’ Assistant as the foundation, Flo Health is empowering product managers and analysts to work with SQL.  

“Ensuring that our employees are data-driven and can interact with data in natural language is paramount to us offering the best possible service to our customers.

“The Databricks Data Intelligence Platform offers the privacy, scalability, security, and ease of use to help us make a positive impact on women’s healthcare, and I’m excited by where the partnership can go next,” Bugaev said.

Nico Gaviola, vice president of emerging enterprise and digital natives at Databricks, said: “Digital natives like Flo Health are looking for smarter, faster, more reliable ways to translate vast amounts of data, safely and securely, to aid innovation on a global scale.

“Flo Health and Databricks share a commitment to using data and AI for societal benefit, so we’re thrilled the team has found so much value in Databricks Data Intelligence Platform to make a real difference in people’s lives.”

The partnership comes as Flo Health faces trial in the US over allegations that it shared users’ sensitive health data with firms, including Meta, between 2017 and 2019.