Highlights
- Understand core generative AI concepts and their potential applications in IT environments
- Navigate and utilize AWS Bedrock to implement foundation models in practical scenarios
- Apply effective prompt engineering techniques to achieve desired AI outputs
- Develop integration patterns for incorporating generative AI into existing systems and workflows
- Implement basic Retrieval-Augmented Generation (RAG) systems on AWS
- Configure proper security controls and permissions for AWS generative AI services
- Estimate and manage costs associated with generative AI implementations
- Create a structured roadmap for generative AI adoption in their organisation
- Identify appropriate AWS services for different generative AI use cases
Course Details
Module 1: Introduction to Generative AI on AWS
- Understanding the foundations of generative AI and how it differs from traditional AI approaches
- Exploring the evolution and capabilities of Large Language Models (LLMs)
- Navigating AWS’s generative AI service ecosystem and understanding the role of each service
- Identifying practical generative AI use cases relevant to IT departments and operations
- Understanding the technical requirements and infrastructure considerations for AI implementation
- Exploring the business value proposition and ROI considerations for generative AI projects
Module 2: AWS Bedrock Fundamentals
- Understanding AWS Bedrock as a managed service for foundation models
- Exploring available foundation models in Bedrock (Anthropic Claude, Meta Llama, etc.)
- Comparing model capabilities, strengths, and appropriate use cases
- Understanding model parameters and their impact on performance and cost
- Navigating the AWS Bedrock console and API interfaces
- Exploring model inference options and configuration settings
Module 3: Hands-on Lab: First Steps with AWS Bedrock
- Setting up AWS Bedrock access and configuring necessary permissions
- Exploring the AWS Bedrock console and available foundation models
- Implementing effective prompt engineering techniques and best practices
- Creating basic text generation applications using the Bedrock API
- Understanding and adjusting key model parameters (temperature, top-p, tokens)
- Building simple conversational interfaces with foundation models
- Testing and evaluating model outputs across different scenarios
Module 4: AWS GenAI Integration Patterns
- Designing effective architectural patterns for generative AI integration
- Implementing serverless AI solutions using AWS Lambda with Bedrock
- Understanding when to use Amazon SageMaker for custom model training and deployment
- Exploring AWS SDK integration options for different programming languages
- Implementing security best practices for generative AI applications
- Developing effective caching strategies to optimize performance and cost
- Understanding API throttling, quotas, and scaling considerations
Module 5: Hands-on Lab: Building Your First AWS GenAI Solution
- Developing a document analysis system using AWS Bedrock and supporting services
- Implementing Retrieval-Augmented Generation (RAG) with Amazon OpenSearch and Bedrock
- Configuring AWS S3 for efficient document storage and retrieval
- Setting up proper IAM roles and permissions for secure operation
- Building API interfaces to your generative AI solution
- Testing and troubleshooting common integration issues
- Implementing basic monitoring and logging for your application
Module 6: Cost Management & Optimization
- Understanding AWS generative AI pricing models and cost components
- Analyzing the cost implications of different foundation models and parameters
- Implementing architectural patterns to optimize cost efficiency
- Setting up AWS Budgets and cost alerts for generative AI workloads
- Understanding token usage optimization techniques
- Implementing caching strategies to reduce redundant API calls
- Balancing cost, performance, and capability in model selection
Module 7: Implementation Planning
- Developing a framework for identifying high-value generative AI opportunities
- Creating a structured 30-60-90 day implementation roadmap
- Understanding governance considerations for responsible AI deployment
- Exploring strategies for measuring success and demonstrating value
- Navigating available resources for continued learning and development
- Addressing common challenges and pitfalls in generative AI implementation
- Open Q&A session for specific implementation questions
Who should attend
-
IT professionals and cloud engineers who manage or support AWS environments.
-
Developers and software engineers building applications that use generative AI.
-
Data engineers, data scientists, and AI practitioners exploring LLMs and RAG solutions.
-
Solution architects and technical leads designing AI-driven systems on AWS.
-
Product managers and IT leaders evaluating generative AI use cases and ROI.
-
Business analysts and automation teams identifying opportunities for AI-enabled workflows.
Feedback
4.8 out of 5 average
"Our tailored course provided a well rounded introduction. It covered topics that we needed to know. The instructor genuinely cared about our learning. We felt supported from start to finish and left with knowledge that truly mattered to our work." Brian Leek, Data Analyst, May 2024
“JBI did a great job of customizing their syllabus to suit our business needs and also bringing our team up to speed on the current best practices. ” Brian F, Team Lead, RBS, Data Analysis Course, 20 April 2022