reference deployment

Agilisium Conversational BI Bot on AWS

Build an AI-powered, web-based chat interface for gaining insights on your data

This Quick Start automatically deploys the Agilisium Conversational BI Bot into a new or existing virtual private cloud (VPC) on the Amazon Web Services (AWS) Cloud in about 25 minutes.

The Quick Start provisions a web-based chat interface to interact with the BI bot by using AWS services such as Amazon Lex, Amazon Redshift, Amazon Simple Storage Service (Amazon S3), AWS Lambda, and Amazon Cognito. Through this interface, the user opens a chat window on the bot website, converses with the bot, and enters questions to gain data insights. The bot responds with a mix of visuals and text.

The example scenario is an automotive dealership, where a business stakeholder—such as an executive—converses with the bot to derive sales and revenue insights, based on a predefined set of questions.

micro focus logo

This Quick Start was developed by Agilisium Consulting in collaboration with AWS. Agilisium Consulting is an APN Partner.

  •  What you'll build
  •  How to deploy
  •  Cost and licenses
  •  What you'll build
  • Use this Quick Start to set up the following environment on AWS:

    • A highly available architecture that spans two Availability Zones.*
    • A VPC configured with public and private subnets, according to AWS best practices, to provide you with your own virtual network on AWS.*
    • In the public subnets, managed NAT gateways to allow outbound internet access for resources in the private subnets.*
    • In the private subnets, serverless Lambda functions and Redshift cluster resources.
    • A static webhost using Amazon S3 to provide an effective and convenient bot user interface.
    • An Amazon Cognito identity pool to provide connectivity from the static webhost to access AWS resources.
    • AWS Identity and Access Management (IAM) roles for the Lambda functions and Cognito pool.
    • Amazon CloudWatch logs, which are created by serverless Lambda functions.
    • Amazon Lex resources, including a bot, intents, and slots.

    * The template that deploys the Quick Start into an existing VPC skips the components marked by asterisks and prompts you for your existing VPC configuration.

  •  How to deploy
  • To deploy the Conversational BI Bot on AWS, follow the instructions in the deployment guide. The deployment process includes these steps:

    1. If you don't already have an AWS account, sign up at https://aws.amazon.com, and sign in to your account.
    2. Launch the Quick Start. Each deployment takes about 25 minutes. You can choose from two options:
    3. Test the deployment.
    4. Customize the Conversational BI Bot. For example, you can add new bot webpages or modify an existing one. You can also inject your own data, and customize Amazon Lex to add new intents and slots.
  •  Cost and licenses
  • You are responsible for the cost of the AWS services used while running this Quick Start reference deployment.

    There are no additional license costs involved for using the Quick Start.

    The AWS CloudFormation template for this Quick Start includes configuration parameters that you can customize. Some of these parameters, such as instance type, will affect the cost of deployment. For cost estimates, see the pricing pages for each AWS service you will be using. Prices are subject to change.

    Tip     After you deploy the Quick Start, we recommend that you enable the AWS Cost and Usage Report to track costs associated with the Quick Start. This report delivers billing metrics to an Amazon Simple Storage Service (Amazon S3) bucket in your account. It provides cost estimates based on usage throughout each month, and finalizes the data at the end of the month. For more information about the report, see the AWS documentation.