[SEO Subhead]
This Guidance shows how to increase employee productivity by using generative AI to transcribe meeting discussions and generate searchable meeting minutes and action items. This streamlines note-taking, helping meeting participants focus on the discussion at hand. Additionally, you can integrate a comprehensive knowledge base with this Guidance to help answer employee questions about the discussions held and decisions made during meetings. Finally, this Guidance helps you satisfy regulatory requirements by keeping all data within your private AWS environment.
Note: [Disclaimer]
Architecture Diagram
[Architecture diagram description]
Step 1
AWS CloudFormation deploys the right services and features with the necessary configurations. AWS Key Management Service (AWS KMS) controls the cryptographic keys that are used to protect your data at rest and in transit.
Step 2
The meeting host includes the Amazon Connect agent in the meeting invite. This permits Amazon Simple Email Service (Amazon SES) to store meeting invite details in an Amazon Simple Storage Service (Amazon S3) bucket.
Step 3
Upon ingestion of the meeting invite upload, Amazon S3 invokes an AWS Lambda function, which calls Amazon Bedrock APIs to identify important meeting details (such as the date and time of the meeting and the meeting app). We recommend testing at least three large language models (LLMs) for your use case with Amazon Bedrock.
Step 4
The Lambda function stores the data generated by Amazon Bedrock in an Amazon DynamoDB table.
Step 5
The Lambda function creates an Amazon EventBridge event, which will invoke a Lambda function on a scheduled cron at the date and time of the meeting to inject an Amazon Connect agent into the meeting.
Step 6
Attendees join the meeting at the appropriate date and time. The Amazon Connect agent automatically joins to start recording the meeting. Amazon Connect supports meetings hosted on web clients, mobile applications, and desktop clients.
Step 7
Amazon Connect stores the meeting’s voice transcription in an Amazon S3 bucket.
Step 8
Amazon S3 invokes a Lambda function, which runs an Amazon Transcribe call on the transcription to convert voice to text.
Step 9
The Lambda function takes the newly generated text file and calls Amazon Bedrock APIs to summarize the meeting and action items.
Step 10
The Lambda function takes the generated text output from Amazon Bedrock and creates an email to attendees, sent using Amazon SES.
Step 1
AWS CloudFormation deploys the right services and features with the necessary configurations. AWS Key Management Service (AWS KMS) controls the cryptographic keys that are used to protect your data at rest and in transit.
Step 2
The meeting host includes the Amazon Connect agent in the meeting invite. This permits Amazon Simple Email Service (Amazon SES) to store meeting invite details in an Amazon Simple Storage Service (Amazon S3) bucket.
Step 3
Upon ingestion of the meeting invite upload, Amazon S3 invokes an AWS Lambda function, which calls Amazon Bedrock APIs to identify important meeting details (such as the date and time of the meeting and the meeting app). We recommend testing at least three large language models (LLMs) for your use case with Amazon Bedrock.
Step 4
The Lambda function stores the data generated by Amazon Bedrock in an Amazon DynamoDB table.
Step 5
The Lambda function creates an Amazon EventBridge event, which will invoke a Lambda function on a scheduled cron at the date and time of the meeting to inject an Amazon Connect agent into the meeting.
Step 6
Attendees join the meeting at the appropriate date and time. The Amazon Connect agent automatically joins to start recording the meeting. Amazon Connect supports meetings hosted on web clients, mobile applications, and desktop clients.
Step 7
Amazon Connect stores the meeting’s voice transcription in an Amazon S3 bucket.
Step 8
Amazon S3 invokes a Lambda function, which runs an Amazon Transcribe call on the transcription to convert voice to text.
Step 9
The Lambda function takes the newly generated text file and calls Amazon Bedrock APIs to summarize the meeting and action items.
Step 10
The Lambda function takes the generated text output from Amazon Bedrock and creates an email to attendees, sent using Amazon SES.
Get Started
Well-Architected Pillars
The AWS Well-Architected Framework helps you understand the pros and cons of the decisions you make when building systems in the cloud. The six pillars of the Framework allow you to learn architectural best practices for designing and operating reliable, secure, efficient, cost-effective, and sustainable systems. Using the AWS Well-Architected Tool, available at no charge in the AWS Management Console, you can review your workloads against these best practices by answering a set of questions for each pillar.
The architecture diagram above is an example of a Solution created with Well-Architected best practices in mind. To be fully Well-Architected, you should follow as many Well-Architected best practices as possible.
-
Operational ExcellenceRead the Operational Excellence whitepaper
CloudFormation lets you deploy infrastructure as code, using templates to correctly configure services and features. This helps you avoid the potential for error that comes with manual intervention. Amazon CloudWatch monitors metrics and logs and proactively alerts you of unexpected behaviors so that you can quickly troubleshoot issues.
-
SecurityRead the Security whitepaper
You can use AWS KMS to create and control the cryptographic keys that protect your data at rest and in transit. By delegating encryption key management to this highly secure and scalable AWS service, you can better protect data and adhere to encryption best practices. Additionally, this Guidance scopes all AWS Identity and Access Management (IAM) policies down to the minimum permissions required for the service to function properly. This enables you to restrict unauthorized access to resources and enhance your overall security posture.
-
ReliabilityRead the Reliability whitepaper
This Guidance uses fully managed AWS services like DynamoDB, Amazon Transcribe, Amazon S3, and Amazon Connect. Because AWS handles the underlying infrastructure, you can avoid the burden of operational overhead and reduce the risk of human errors that could impact reliability. These services scale automatically and are designed to provide data replication and fault tolerance and maintain high availability, even during increased traffic or system failures.
-
Performance EfficiencyRead the Performance Efficiency whitepaper
Lambda uses serverless compute, which scales seamlessly on the backend, and you can configure resource consumption to match the demand of your use case. DynamoDB is a fully serverless option that provides single-digit-millisecond latency to store and retrieve data quickly. Additionally, you can use performance metrics from CloudWatch to proactively reconfigure your resources to meet performance requirements. Finally, this Guidance uses Amazon Transcribe and Amazon Bedrock, fully managed AI services that only require you to call the APIs to work through the Amazon S3 data.
-
Cost OptimizationRead the Cost Optimization whitepaper
Lambda scales automatically to meet demand and bills per request, helping you optimize costs, especially for sporadic workloads. Amazon Bedrock provides access to pretrained AI models, eliminating the need for expensive model training and infrastructure. Additionally, Amazon S3 provides low-cost, scalable storage and offers lifecyle policies to optimize the cost of objects. Together, these services minimize operational costs and maximize resource efficiency, making this Guidance ideal for cost-effective AI and machine learning workloads.
-
SustainabilityRead the Sustainability whitepaper
This Guidance supports sustainability by maximizing efficiency and minimizing resource waste. Lambda uses a serverless model that scales automatically to achieve efficient resource utilization and reduce wasted capacity. Amazon S3 scales automatically to avoid overprovisioning, and it reduces object storage redundancy to avoid unnecessary backups. Additionally, Amazon Bedrock optimizes model deployment, leading to a more efficient use of compute power. Together, these services help you operate more sustainably by lowering your energy consumption and the environmental impact of your cloud operations.
Related Content
[Title]
Disclaimer
The sample code; software libraries; command line tools; proofs of concept; templates; or other related technology (including any of the foregoing that are provided by our personnel) is provided to you as AWS Content under the AWS Customer Agreement, or the relevant written agreement between you and AWS (whichever applies). You should not use this AWS Content in your production accounts, or on production or other critical data. You are responsible for testing, securing, and optimizing the AWS Content, such as sample code, as appropriate for production grade use based on your specific quality control practices and standards. Deploying AWS Content may incur AWS charges for creating or using AWS chargeable resources, such as running Amazon EC2 instances or using Amazon S3 storage.
References to third-party services or organizations in this Guidance do not imply an endorsement, sponsorship, or affiliation between Amazon or AWS and the third party. Guidance from AWS is a technical starting point, and you can customize your integration with third-party services when you deploy the architecture.