Gyst Technology Overview

Gyst is a web API for enhancing the Customer Experience (CX) in Voicebots and IVR Systems.

The product is comprised of the Gyst CX service for optimizing voice applications, and Gyst Analytics, for gaining high resolution insight into caller behavior in the voice channel.

Gyst (Patent Pending) is implemented on a per voice application basis and the service is provided to the client under a SaaS billing model. Once application setup is complete, clients are billed only for the services they use.


Successfully navigating modern voice applications, even well designed ones, depends not only on the users cognitive abilities, but also on their ability to deal with distractions, the calling environment, poor mobile signals, and background noise. Another factor is that the caller may or may not have advance knowledge of the dialog flow itself.

To help overcome some of these hurdles, and to improve voice self-service rates, Gyst allows each user to get their own unique experience, custom tailored on the fly, based on their demonstrated abilities at navigating the dialog flow. Users that are skilled and accurate at navigating the voice application, as compared to other users of the same application, hear the voice prompts at gradually, almost imperceptible, increasing playback speeds. Slower, less skilled or less knowledgeable users (distracted, mobile users in poor signal areas, elderly) hear the dialog progress at a slower pace. Gyst accommodates and tailors the experience for everyone in between too. This adjustment and readjustment process takes place every time the user responds to a voice prompt.

When implemented for a particular voice application, Gyst first gathers data on how your users currently use and navigate their way through the dialog flow. This is done anonymously and in the aggregate for a statistically significant sample of your existing users. Skill measurement samples are taken at each dialog interaction point (called a Gyst Node) to determine how well (or how poorly) your customers respond to application requests for speech and/or DTMF directed dialog input, natural language interaction, or any input request needed to allow the user to accomplish tasks and goals in the voice application. This is called the Auto-Learn process.

When the Auto-Learn process is complete, the technology then adjusts the speaking rate (words per minute spoken) and optionally, the response time allowed, the best mode of input (speech or touch-tone), the inflection and message content, and other parameters to suit each individual user as they progress through the dialog flow. This provides a significantly better customer experience and allows a greater number of users to self-serve in the voice channel.

With Gyst's advanced features, struggling users can get additional instructions and additional time to respond to the voice prompts, while more skilled users may hear abbreviated instructions in order to further speed them through the dialog.

Gyst also provides very high resolution analytics for deep insight into how your customers use your voice applications, and how and where improvements can be made. This capability allows to quickly find and clean up legacy applications and to help guide your digital transformation strategies.

Implementation Overview

Gyst has been designed from the ground up to be secure, reliable, and highly scalable. We also designed it to be extremely fast and easy to use in new and existing voice applications - both premise and cloud based. Voice applications are optimized with Gyst by adding http calls to the Gyst API as shown below and as described here.

Secure Operation

Because this personalization is driven via the users exhibited behavior, and not using stored, static user profiles, there's no need to share account numbers, PIN's or any other type of personal information to achieve significant CX and self-service or automation improvements. This provides a level of personalization above and beyond more traditional, profile based CX improvement techniques.