Gyst is a web API based service for optimizing your Amazon Connect and Amazon Lex voice applications. It delivers easier, better, faster, and more cost effective customer self-service. You can watch the movie below for a quick overview of the Gyst For Amazon implementation, learn about what makes Gyst unique here, or skip right to the technical details. You can also check out Gyst on the AWS Marketplace site here.

Overview - Gyst For Amazon

Want to learn more? Talk to an expert.

Anonymous Personalization

Gyst allows your voice applications to adjust dynamically to individual user skills, cognitive abilities, noisy or distracted calling environments, familiarity with the dialogue flow, and other factors. It does not require any personal information to be shared in order to provide significant improvements in the customer experience and measurable cost savings.

While static, profile based user personalization is helpful for reducing the number of interactions a user needs to make in order to achieve a specific goal in your voice channel, it does not account for these user and environmental factors critical to modern day voice interactions.

What Makes Gyst Different?

Technical Implementation

Figure 1 below provides a list of the files required to add Gyst to your Amazon Connect and Amazon Lex voice applications. These files are located in the Amazon S3 Gyst bucket named “gyst-distribution”. Details on how to access these files are provided at the time of purchase.

Figure 1

The GystForAmazon_Architecture.png and GystForAmazon.docx are part of the product documentation. After becoming familiar with the product documentation, the user begins by generating the Gyst Stack as shown in Figures 2 and 3 below, via the supplied AWS Cloud Formation Template named GystForAmazon_CloudFormation.yml.

Figure 2

Figure 3

The key AWS resources generated via the CloudFormation Template are the Gyst EC2 instance and Gyst Lambda functions as shown in Figures 2 and 3.

The Gyst EC2 instance supports the Gyst web API, an HTTP based restful API that is directly callable from the clients Amazon Connect instance, and from the Lambda function supporting any Amazon Lex based voice bot the client is leveraging for this, or any other Amazon Connect instance. The clients existing Lambda function simply calls the Gyst Lambda named “Gyst API”. This Lambda in turn, calls the Gyst Web API that is supported via the Gyst EC2 instance.

The specifications on the HTTP get/post responses and API usage are detailed in a secure area of the Gyst online documentation resource. A passcode to enable access this documentation is provided at the time of purchase.

Figure 4 below shows an Amazon Connect call flow for a demo voice application that implements Gyst Technology. The template for this call flow is in the aforementioned S3 bucket and is named GystForAmazon_ConnectFlow.json. Additionally, the GystAPI.js.zip and the AddressHelper.js.zip code for the required Lambda functions are contained in the Gyst Installation S3 bucket, as is the Demo Lex Bot, named AddressHelper_GystLexBot.zip.

It is highly recommended that the user download all files, build the Gyst Stack as shown, and then ping the Gyst EC2 instance via a dedicated Elastic IP and per the API calling instructions contained in the Gyst Online documentation. Ultimately, the user will want to dial in to the Connect instance and hear the call flow from beginning to end. This assures that the Gyst Installation procedures have been carried out correctly, and that the Gyst EC2 instance is ready for service for the clients Connect and Lex voice applications.

Figure 4

In production, the clients Amazon Connect and Lex instances call the Gyst API each time the caller responds. A single Gyst API call is also added at the beginning and end of each phone call. In both Lex and Connect, the SSML prosody tag is adjusted based on caller behavior in each service. Examples of how to implement this in the Connect blocks and Lambda code are given in the demo.

The Gyst Recommendation Engine, which is supported via the Gyst EC2 instance and reachable via the Gyst API, handles all audio playback speed change recommendations based on machine learning techniques and our proven algorithms for learning caller behavior. Also included are recommendations for caller timeout adjustments, input modality switching, and alternate voice content messaging. The service also includes Gyst’s high resolution caller behavior analytics which analyze performance metrics in real time, and report on the overall voice application efficiency over time.

While the CloudFormation template and documentation provided at the time of purchase will fully implement the services outlined below, it is anticipated that the client will require some additional guidance from Gyst Technologies to accomplish this. This guidance is provided as part of the initial sale to the client.

Gyst For Amazon - Direct EC2 Configuration

This guide provides step-by-step instructions on how to launch a Windows Server Instance (WSI) to support the Gyst Service Environment on Amazon Web Services.

For additional information on launching and maintaining AWS instances, load balancers, security groups, and other services, see Amazon's Documentation for AWS here.

While a WSI will run under various Microsoft Windows Server versions, Windows Server 2016 and 2019 are recommended. Additionally, a WSI can run privately on a client’s physical, firewall protected server, a client’s virtualized server instance - including those running under VMWare, or on Microsoft Azure or an equivalent cloud service provider. This document relates to a WSI running on AWS.

For AWS, the WSI uses Amazon’s Elastic Compute Cloud (EC2) based instances. Some familiarity with the AWS Dashboard and Instance Configuration and Launch Tools is required for the following procedures, as is knowledge of and access to the client’s AWS User Account and Security details. 

Additionally, this document outlines the procedure for small capacity Gyst Service Environments (1 - 10 simultaneous conversations). You can scale accordingly for larger capacity environments. See the Gyst Installation and Service Configuration document for further details on the storage and processing requirements of the WSI.

Step 1. Sign in to AWS and select an appropriate Windows Server 2016 instance. 

For small capacity Gyst Service Environments, you can select a Micro or Free Tier, if available. Note that while Amazon may, from time to time, offer free and paid instance configurations with containers, SQL, and other services, the WSI does not require anything other than the base Windows Server 2016 configuration. 

Step 2. Select a specific instance type with appropriate CPU and storage capacity.

See the Gyst Installation and Service Configuration document for further details on the storage and processing requirements of the WSI.

Step 3. Configure the instance details as indicated… 

Step 4. Select appropriate Storage Capacity as indicated…

Step 5. Add tags as key-value pairs to identify the instance. 

Step 6. Assign an existing security group or create a new one per local guidelines.

Step 7. Select an existing key pair, or create a new one and launch the instance.

You can use the retrieved credentials to log in to this newly created WSI and install and configure the Gyst Software as detailed in the Gyst For Windows page.