Evolv’s core business revolves around an AI-powered SaaS platform that allows launching multiple UX experiments at a scale never possible before. The platform’s concept and part of its functionality are based on Sentient Ascend, a world’s known conversion optimization tool. Initially, we provided our service to Sentient Technologies; however, it was dissolved in 2019, and the Sentient Ascend technology got acquired by Evolv.
Maintaining and upgrading such a robust system requires significant development resources. Since the Redwerk team had already worked with Sentient Technologies and was familiar with the platform’s business logic, Evolv decided to continue our partnership.
Evolv helps brands improve their customers’ digital experiences by working out a custom-tailored digital strategy, generating UX improvements and their multiple variations, and evaluating those changes with the AI-based A/B testing platform. The active learning approach implemented in Evolv’s system ensures real-time response to best-performing UX combinations, allowing businesses to save time and traffic during the experiment.
Here is a typical example of how Evolv’s solution is applied in real life. A business owner comes to Evolv with a clear optimization target in mind, such as increasing the user inflow to the order confirmation page and an established KPI (for instance, the correlation of completed orders to the number of product page unique visitors). After that, the client decides on the page for the experiment (any product or service page), platform (web, desktop, mobile, or combined), and audience location for Evolv’s team to start the ideation process. The latter entails that Evolv uses their own UX research to identify areas for improvement and outline multiple changes and their variations that can positively impact conversion.
Of course, all the UX suggestions are discussed with the client, and the approved ones go to the so-called “Experiment Deсk.” From there, the UX improvements are coded and tested in Web Editor and then exported to Manager for the actual release. Once the experiment is launched, each variant’s performance is evaluated in relation to the control candidate (original version) in the standard A/B testing mode, with the worst-performing candidates automatically excluded. Once the system has aggregated a sufficient amount of traffic to move to the evolution phase – EVO- it starts combining variants from different variables using an active learning approach. Because the system reacts to customer feedback in real-time, it continuously trains its machine learning model to predict the best-performing combinations within a short time. Having detailed statistics on each combination, the business owner clearly sees what UX changes will drive sales.