A Guide to Analyze Amazon Lex Conversation Log Data with Amazon Managed Grafana

Introduction

Organizations are increasingly using conversational interfaces for their business processes. These interfaces, like chatbots or virtual assistants, bring benefits such as increased availability, better service, and cost savings. As these conversational tools become more crucial, it’s essential to keep an eye on how well they’re performing and how effective they are in helping users.

To do this, organizations often use tools like Amazon CloudWatch Logs Insights. This tool helps analyze the logs generated during conversations with services like Amazon Lex (a chatbot service). While Amazon CloudWatch Logs Insights is powerful, some users might prefer a simpler way to analyze logs without navigating the complexities of the AWS console.

Amazon Managed Grafana (AMG) is a user-friendly dashboard tool that allows organizations to easily analyze and monitor the performance of conversational interfaces, like chatbots, without the complexity of the AWS console. With rich visualizations, AMG helps users understand metrics, logs, and traces across various data sources. It offers scalability, high availability, and enterprise-level security, making it a preferred choice for creating interactive dashboards that drive continuous improvements in the effectiveness of conversational interfaces.

One cool thing about AMG is that it can automatically adjust its size based on your needs, and it’s designed to be super secure for enterprise-level use. So, you get a tool that grows with your demands and ensures your data stays safe.

Prerequisites

1. An AWS Account
2. AWS IAM Identity Center (successor to AWS Single Sign-On) enabled
3. Required AWS IAM permission of Amazon Lex, Amazon CloudWatch, and Amazon Managed Grafana
4. An Existing Amazon Lex Chatbot

Solution Approach Architecture

Step-by-Step Guide

Step 1: Create an Amazon CloudWatch log group for an existing chatbot to capture their text logs

We will create an Amazon CloudWatch log group for an existing chatbot. Snapshots are given under.

1. Go to the AWS Management Console, search Amazon CloudWatch under it, select log group, and create it.

Step 2: Enable conversation logs of your existing Amazon Lex chatbot

1. In the Amazon Lex console, under bot, choose your existing bot. In my case, it is “OrderFlowers”.

2. Under Alias, choose the existing alias of your bot. In my case, it is “BotAlias”.

3. Click on Manage Conversation Logs and enable text logs. Select the log groups we created on Amazon CloudWatch and save them. It will capture your chatbot conversation logs in Amazon CloudWatch, which will be used later for Analysis in Amazon Managed Grafana.

Step 3: Create a workspace in Amazon Managed Grafana to access the conversation logs

1. Go to the Amazon Managed Grafana console and click “Create Workspace”.
2. Give the name of the workspace as “OrderFlower” and click on next to add additional configuration.

3. Choose the authentication method as AWS IAM Identity Center (AWS SSO), leave the rest as a default, and click next.

4. In AWS IAM permission access settings for the data source, select Amazon CloudWatch and click on next.

5. In the final steps, review the details and click on Create Workspace. It will create an Amazon Managed Grafana workspace.

6. In the “orderflower” workspace authentication tab, choose “Assign new user or group” and select the user so that they will have full permission to create and customize the Amazon Managed Grafana data source.

Step 4: Create a data source for Amazon Managed Grafana

1. Go to the Amazon Managed Grafana workspace summary and click on the Amazon Managed Grafana URL.

2. It will open the Amazon Managed Grafana console.

3. Click on Data Source, select Amazon CloudWatch as a data source, leave all the configuration as default, and click “save & test”.

Step 5: Create a dashboard for analysis

1. Go to the Amazon Managed Grafana console Home and click “Dashboard” to create a new dashboard and panel.

2. Choose Amazon CloudWatch, and for Query, choose Amazon CloudWatch Logs, created in earlier steps. And run the query.

3. In this way, you can create multiple panels.

We have successfully visualized the Amazon Lex conversation logs in Amazon Managed Grafana.

Conclusion

This guide explored the activation and utilization of conversation logs to extract these insights. Leveraging Grafana, we illustrated how to represent and report on crucial metrics visually. Begin constructing your dashboards and delve deeper into the seamless integration of Amazon Managed Grafana with Amazon CloudWatch to elevate your analytics capabilities.

Drop a query if you have any questions regarding Amazon Managed Grafana 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 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, AWS Training Partner, AWS Migration Partner, AWS Data and Analytics Partner, AWS DevOps Competency Partner, Amazon QuickSight Service Delivery Partner, Amazon EKS Service Delivery Partner, Microsoft Gold Partner, AWS Microsoft Workload Partners, Amazon EC2 Service Delivery Partner, and many more.

To get started, go through our Consultancy page and Managed Services Package, CloudThat’s offerings.