Building an Intelligent Support Assistant with Amazon Lex and ServiceNow

Introduction

Chat-based assistants have transformed customer service by enabling automated, efficient, and accessible solutions. This post explores building an intelligent assistant using Amazon Lex, Amazon Bedrock Knowledge Bases, and ServiceNow to deliver 24/7 automated incident management support. Amazon Lex facilitates natural language interactions, enhanced by Bedrock foundation models and knowledge bases for retrieving and summarizing information. When integrated with ServiceNow’s IT workflow platform, this solution empowers businesses to streamline support and enable self-service for customers and employees.

Solution overview

Deployment with AWS CloudFormation console

1. To construct the AWS CloudFormation stack, create a stack on the AWS CloudFormation console after ensuring you are in the appropriate AWS Region.
2. Download the AWS CloudFormation template and upload it in the Specify template. Select
3. For the Stack name, enter a name such as ServiceNowBedrockStack.
4. In the Parameters section, for ServiceNow details, provide the values of ServiceNow host and ServiceNow username created earlier.
5. Keep the other values as default. Under Capabilities on the last page, select I acknowledge that AWS CloudFormation might create AWS IAM resources. Choose Submit to create the AWS CloudFormation stack.
6. After successfully deploying the whole stack from the Outputs tab, note the output key-value BedrockKnowledgeBaseId because you will need it later when creating the Amazon Lex assistant.

Store the secrets in AWS Secrets Manager

1. To narrow down search results, type “secrets” into the Resources tab of the AWS CloudFormation dashboard. Choose the console URL of the AWS Secrets Manager secret you generated with the AWS CloudFormation stack under Physical ID.

2. On the AWS Secrets Manager console, on the Overview tab, under Secret value, Select Retrieve secret value.

3. Select Edit and enter the username and password of the ServiceNow instance you created earlier. Make sure that both the username and password are correct.

Download knowledge articles

1. If you don’t already have a knowledge base, create one. To keep your knowledge base current, you might need to sync it sometimes.
2. Follow the directions at ServiceNow to use Amazon AppFlow to sync the data from ServiceNow to Amazon S3. Alternatively, you may extract ServiceNow data using AWS Glue Studio in an Amazon S3 data lake and analyze it using Amazon Athena. AWS Glue is utilized to ingest data from ServiceNow to Amazon S3.
3. Get a sample article by downloading it.

Sync Amazon Bedrock Knowledge Bases

1. To narrow down search results, type “S3” into the Resources tab of the AWS CloudFormation dashboard. Choose the URL for the Amazon S3 bucket made using the AWS CloudFormation stack under Physical ID.

2. Upload the previously downloaded knowledge articles to this Amazon S3 bucket.

3. To filter search results, type “Knowledge” into the Outputs tab of the AWS CloudFormation interface. Choose the console URL for the knowledge bases you established using the AWS CloudFormation stack under Value. Launch the URL in a separate tab of your browser.

4. Scroll down to Data sourceand select the data source. Choose

Amazon Lex setup

1. On the AWS CloudFormation console, on the Outputs tab, copy the value of BedrockKnowledgeBaseId. You will need this ID later in this section.
2. On the Outputs tab, under Outputs, enter “bot” to filter search results. Choose the console URL of the Amazon Lex assistant you created using the AWS CloudFormation stack. Open that URL in a new browser tab.

3. On the Amazon Lex Intents page, choose Create another intent. On the Add intent dropdown menu, choose Use built-in intent.

4. On the Use built-in intentscreen, under Built-in intent, choose QnAIntent- Gen AI feature.

5. For the Intent name, enter BedrockKb and select Add.

6. In the QnA configuration section, under Select model, choose Anthropic and Claude 3 Haiku or a model of your choice.

7. Expand Additional Model Settings and enter the Guardrail ID for the guardrails you created earlier. Under Guardrail Version, enter a number corresponding to the number of versions you created.

8. Enter the Knowledge base for the Amazon Bedrock Id you captured earlier in the CloudFormation outputs section. Choose Save intent at the bottom.

9. Return to the intents list by choosing Back to intents list in the navigation pane.

10. Select Build to build the assistant.

A green banner with the statement at the top of the English (US) page has been successfully put into the servicenow-lex-bot, indicating that the Amazon Lex assistant is now available.

Conclusion

This approach not only streamlines operations but also reduces the workload on support teams, enabling them to focus on more complex tasks. By adopting these technologies, businesses can stay ahead in delivering innovative and scalable solutions that meet the evolving demands of modern users.

Drop a query if you have any questions regarding Amazon Lex, Amazon Bedrock, or ServiceNow and we will get back to you quickly.

About CloudThat

CloudThat is a leading provider of Cloud Training and Consulting services with a global presence in India, the USA, Asia, Europe, and Africa. Specializing in AWS, Microsoft Azure, GCP, VMware, Databricks, and more, the company serves mid-market and enterprise clients, offering comprehensive expertise in Cloud Migration, Data Platforms, DevOps, IoT, AI/ML, and more.

CloudThat is the first Indian Company to win the prestigious Microsoft Partner 2024 Award and is recognized as a top-tier partner with AWS and Microsoft, including the prestigious ‘Think Big’ partner award from AWS and the Microsoft Superstars FY 2023 award in Asia & India. Having trained 650k+ professionals in 500+ cloud certifications and completed 300+ consulting projects globally, CloudThat is an official AWS Advanced Consulting Partner, Microsoft Gold Partner, AWS Training Partner, AWS Migration Partner, AWS Data and Analytics Partner, AWS DevOps Competency Partner, AWS GenAI Competency Partner, Amazon QuickSight Service Delivery Partner, Amazon EKS Service Delivery Partner,  AWS Microsoft Workload Partners, Amazon EC2 Service Delivery Partner, Amazon ECS Service Delivery Partner, AWS Glue Service Delivery Partner, Amazon Redshift Service Delivery Partner, AWS Control Tower Service Delivery Partner, AWS WAF Service Delivery Partner, Amazon CloudFront, Amazon OpenSearch, AWS DMS and many more.