Automation with Amazon Q

In this session, we explore Amazon Q, a generative AI service from AWS, and understand its scope in solving enterprise-level problems. The session starts with a comparison of general-purpose generative AI tools like ChatGPT and GitHub Copilot and highlights the limitations of using public data for enterprise use cases.

We then dive into how Amazon Q acts as an umbrella of services—Q for Developers, Q Business, Q Connect, Q QuickSight, and Q Supply Chain. Special focus is given to Q Developer and Q Business, which address the challenges enterprises face in code generation, debugging, testing, and decision-making using private and internal data sources.

Key topics covered include:

• Introduction to Generative AI and its real-world usage
  

• Amazon Q as a service umbrella with multiple sub-services
  

• Differences between general-purpose AI tools vs. enterprise-specific AI
  

• Role of Q Developer in code generation, debugging, and transformation
  

• Role of Q Business in handling enterprise use cases and decisions
  

• How AWS leverages its 17+ years of internal knowledge base for Q

By the end of the session, you will clearly understand the positioning of Amazon Q in the generative AI landscape, how it differs from other tools like ChatGPT or Copilot, and why it is designed specifically to solve enterprise challenges with security, optimization, and industry relevance

In this session, we explore Amazon Q Business, a generative AI service designed to leverage internal enterprise knowledge. The session highlights how Q Business integrates with proprietary company data sources, enabling AI-powered chat and information retrieval for various teams such as HR, finance, and legal. We also discuss the underlying technologies, including Foundation Models (FMs) within AWS Bedrock, and walk through setting up an Amazon Q Business application in the AWS Cloud.

Key topics covered include:

• Amazon Q Business explained as an LLM-powered tool using FMs from AWS Bedrock

  
  

• AWS Bedrock overview and its FM providers (Anthropic, OpenAI, Meta, Amazon Titan)

  
  

• Q Business vs. general-purpose AI tools like ChatGPT

  
  

• Enterprise use cases: HR, finance, and legal applications

  
  

• Connectivity with 70+ business tools and data sources (S3, Salesforce, Slack, Gmail, on-prem systems)
  

• The "Retriever" concept for fetching relevant data from connected sources
  

• Security and data protection with encryption and compliance features
  

• Brief overview of other Q services: Q Site, Q Connect, Q Supply Chain
  

• Practical walkthrough: creating an application, setting up IAM Identity Center, configuring retrievers, and testing with and without data sources

  
  

By the end of this session, you will have a clear understanding of Amazon Q Business’s architecture, its value proposition in unlocking internal company data, and a practical overview of how to deploy it securely within the AWS ecosystem.

This session introduces the hands-on usage of Amazon Q Developer for automating AWS services. The focus is on how developers can integrate Q Developer with IDEs like Visual Studio Code to generate, debug, and optimize cloud automation code.

The session emphasizes why AWS’s Q Developer outperforms tools like Copilot in enterprise cloud automation, as it is built on AWS’s deep knowledge of its own services.

Key topics covered include:

• Setting up Amazon Q Developer in VS Code
  

• Difference between Q Developer and other AI coding assistants
  

• Using Q Developer for Infrastructure as Code (IaC) with Python (Boto3) and Terraform
  

• Advantages of AWS’s 17+ years of cloud knowledge in generating optimized code
  

• Understanding that Q Developer was formerly known as CodeWhisperer
  

• Availability, free-tier tokens, and regional limitations (currently in Virginia region)

By the end of the session, you will be able to set up Amazon Q Developer in your IDE, understand how it differs from other AI-based coding assistants, and start generating automation code for AWS services with better accuracy, optimization, and compliance

In this session, we dive deeper into the practical usage of Amazon Q Developer to generate, test, debug, and optimize AWS automation code. The training shows how prompts and comments inside code files can be used as triggers for generating working code automatically.

A step-by-step demonstration is provided where an EC2 instance is created using Python and Boto3, followed by improvements to make the code enterprise-ready with security compliance.

Key topics covered include:

• Writing prompts as comments to auto-generate code
  

• Generating AWS automation scripts (example: launching EC2 instances)
  

• Debugging and fixing errors like missing AMIs
  

• Enhancing scripts with security, logging, and compliance best practices
  

• Generating test cases using Python unit test and mock libraries

  
  

• Role of better prompts in improving accuracy of generated code

By the end of the session, you will know how to generate automation scripts directly from comments, enhance them for enterprise-grade security and compliance, and even generate test cases for validation. This highlights Amazon Q Developer’s unique advantage in solving real industry use cases compared to Copilot or ChatGPT

This session explores the flexibility of Amazon Q Developer in working across multiple programming languages and frameworks, beyond just Python. A practical demonstration shows how Terraform code can be generated automatically for creating an EKS (Kubernetes) cluster.

It also shows how developers can use Q Developer to analyze, explain, and fix existing code in services like AWS Bedrock and Polly.

Key topics covered include:

• Generating Terraform code for AWS infrastructure (e.g., EKS cluster)
  

• Auto-detection of code language based on file extension
  

• Using Amazon Q Developer to explain unfamiliar code
  

• Debugging, fixing, and optimizing existing AWS service scripts
  

• Applying security compliance and industry best practices automatically

By the end of the session, you will see how Amazon Q Developer supports multi-language development (Python, Terraform, etc.), improves existing codebases, and ensures enterprise-grade compliance and optimization in cloud automation

In this session, we conduct a hands-on demonstration of Amazon Q for Business, focusing on integrating it with internal data sources and setting up an AI-powered enterprise search application. The session highlights Q’s unified AI search capability, which goes beyond standard keyword searches by leveraging natural language understanding.

Key topics covered include:

• Q for Business as a unified AI search across company data sources
  

• Building custom AI applications (e.g., sales or workflow apps) with Q Business
  

• AWS Cloud login and region selection (supported regions: Virginia, Oregon)
  

• Application creation process: naming the app, automatic IAM role creation, skipping encryption keys for simplicity
  

• Setting up the application portal and configuring user authentication with IAM Identity Center
  

• Adding users (e.g., HR team members) and onboarding them through email invitations
  

• Configuring data sources with the native retriever and indexing (supports 40+ sources: S3, MySQL, Oracle, Confluence, Gmail, Teams, Dropbox, etc.)
  

• Option to manually upload PDFs and documents as data sources
  

• Demonstrating an unconfigured application: logging into the portal and observing responses without connected data (“no source attest”)

By the end of this session, you will gain practical experience in creating and configuring an Amazon Q Business application, managing user access, and connecting data sources, laying the foundation for building AI-driven enterprise search solutions.

This session shifts focus to Amazon Q Business, which is designed for enterprises to connect multiple data sources and query them using natural language prompts. Instead of writing SQL or complex queries, users can simply upload or connect sources like Google Drive, Excel, or PDFs and ask questions directly.

Key topics covered include:

• Connecting external and cloud data sources to Amazon Q Business
  

• Uploading files (PDF, Excel, CSV) and indexing them for search
  

• Querying data in natural language instead of SQL
  

• Retrieving structured insights like names, phone numbers, leads, or campaign details
  

• Maintaining security, authentication, and privacy across sources

By the end of the session, you will understand how Amazon Q Business enables enterprises to connect diverse data sources and perform powerful natural language search and analytics, without requiring technical query knowledge

This session extends the capabilities of Amazon Q Business by showing how enterprises can create custom apps for their teams using prompts. With minimal input, Q Business can generate ready-to-use web apps tailored for tasks such as lead management, customer reports, or sales tracking.

Key topics covered include:

• Creating custom apps using natural language prompts
  

• Example: Building a Facebook lead management app
  

• Uploading files and integrating them into apps for data processing
  

• Publishing and sharing apps with teams for collaborative usage
  

• Role of apps in simplifying enterprise workflows

By the end of the session, you will know how to create, customize, and publish enterprise-ready apps using Amazon Q Business, empowering teams to work more efficiently without needing advanced technical expertise