
Please download the slides used in the lectures below
All the code and associated files are provided in the individual sections.
Explore the evolution of generative AI and how artificial intelligence, machine learning, and deep learning interrelate, with examples like self-driving cars and recommendation engines.
Discover how machine learning, a subset of artificial intelligence, trains algorithms on historical data and labeled data to build models that predict insights, covering supervised, unsupervised, and reinforcement learning.
Explore how artificial neural networks mimic the brain with input, hidden, and output layers; understand weights, bias, activation function, and backpropagation that drive deep learning.
Explore the fundamentals of generative AI, including how foundation models generate text, images, and other data, with examples from OpenAI's GPT and AWS Nova models on Bedrock.
Learn how prompts become inputs to foundation models like GPT, Claude, or Amazon Nova, producing completions. See how the end-to-end inference process sends prompts and returns completions.
Discover how a prompt is tokenized into tokens and token IDs, processed in a context window to predict the next word, then de-tokenized into a completion with inference and streaming.
Foundation models are deep neural networks trained on massive unlabeled internet data, enabling text generation, summarization, Q&A, and code generation, with tokens, parameters, and temperature shaping outputs.
Discover Amazon Bedrock, managed serverless service exposing base models via API from Amazon and third parties; pick a model ID, set prompts, and call Bedrock via console, cli, or sdk.
Explore Amazon Bedrock architecture, including the service and escrow accounts, runtime inference, and model endpoint routing. See how private link and VPC interface endpoints secure requests and data.
Explore the Amazon Bedrock console walkthrough to learn the model catalog, serverless and marketplace models, API keys, testing, and inference options including cross-region, batch, and provisioned throughput.
Explore Amazon Bedrock's multi-agent framework, flows, knowledge bases, and data automation to build generative ai workflows with drag-and-drop simplicity, harness rag and automated reasoning, guardrails, and prompt management.
Explore how inference parameters shape foundation model behavior on Amazon Bedrock, detailing randomness and diversity controls—temperature, top K, top P—and length controls such as max tokens and stop sequences.
Build a production-ready generative AI powered equipment SME assistant to reduce wind turbine downtime by summarizing field incident logs with Amazon Bedrock foundation models, boosting productivity and revenue.
Design a PoC-to-production workflow that streams wind turbine logs from a streamlet UI through API gateway to Lambda, using Amazon Bedrock Nova Pro with system prompts and inference parameters.
Build and deploy an AWS Lambda function to send the Equipet SME logs to Amazon Bedrock, invoke the Nova Pro foundation model for summarization, and return results via API Gateway.
Learn how to invoke Amazon Bedrock from Lambda by crafting the request with the model id, a body containing user input and inference parameters, and optional guardrails and latency settings.
Implement bedrock invocation in lambda using a system prompt to summarize logs, configure inference parameters, and return the final response to aws api gateway.
Build and secure a REST API with AWS API Gateway connected to a Lambda function, configure resources and mapping templates, and deploy to a prod stage for end-to-end testing.
Test your API externally with Postman by sending a POST request to the API gateway, using the prod stage and a JSON body to receive a three-line Lambda summary.
Deploy a frontend for the wind turbine equipment SME with Streamlit, detailing VS Code, Python, virtual environment setup, and connecting to an AWS API Gateway invoke URL.
Implement observability for generative AI on Bedrock by monitoring errors, cost, and latency, with invocation logging, CloudWatch metrics, alarms, and SNS notifications.
Set up observability for generative AI on AWS by enabling Bedrock logging and CloudWatch metrics. Configure log groups, retention, data types (text, images, embeddings), and alarms with SNS.
Apply Amazon Bedrock Guardrails to protect generative AI apps with content filters, denied topics, word filters, sensitive information filters, and contextual grounding checks to mitigate hallucinations and toxicity.
Implement AI guardrails in Amazon Bedrock to block toxic language, deny non maintenance topics, filter PII, and test guardrails before integrating into code.
Enable bedrock guardrails in the equipment SME assistant by configuring guardrail id and version, deploying code, and validating through test events and api gateway to ensure toxic prompts are blocked.
Learn how to select foundation models for your use case by evaluating modality, context window, guardrails, cost, latency, and regional availability, using Bedrock and Nova Pro as examples.
Explore foundation model selection on AWS Bedrock by evaluating modalities, context window, guardrails, cost, regional availability, and quotas to choose the right model.
Learn Bedrock model evaluation strategies for a GenAI equipment SME app, using programmatic, llm-as-judge, and human evaluations with prompt datasets, jsonl prompts, reference responses, and metrics.
Hands-on bedrock model evaluation by using an LLM as a judge to assess quality and AI metrics, with a prompt data set in S3 and an evaluation report.
Explore model customization on Amazon Bedrock by comparing prompt engineering, RAG (retrieval augmented generation), and the three customization techniques: model distillation, fine-tuning, and continued pre-training to improve foundation model performance.
Optimize foundation model outputs through prompt engineering by crafting contextual prompts, clear task and output specifications, and exploring zero-shot to few-shot prompting plus retrieval augmented generation.
Learn how model distillation transfers knowledge from a large teacher model like Nova Pro to a smaller Nova Lite using prompts, achieving near large-model accuracy at lower latency and cost.
Explore hands-on model distillation on AWS Bedrock by creating a distillation job that trains a student model from a larger teacher model using synthetic data and S3 datasets.
Utilize supervised fine tuning with labeled prompt–response data on Amazon Bedrock, triggering a SageMaker training job to tailor a model's style and format for tasks like summarization and Q&A.
Extend model knowledge through continued pre-training on proprietary unlabeled data, such as medical journals, to improve domain-specific physician note summarization within Amazon Bedrock using SageMaker-backed training.
Explore a mental model for foundation model adaptation strategies, including prompt engineering, retrieval augmented generation, distillation, fine-tuning, and continued pre-training. Evaluate trade-offs in speed, cost, accuracy, and enterprise data use.
Follow a five-step roadmap to become a generative and agentic AI architect on AWS, mastering genai foundations, bedrock fundamentals, rag, and bedrock agent core deployment.
Trace AWS's AI-powered software development evolution from code whisperer to Amazon Q developer and finally Kiro, a spec-driven approach that generates requirements, designs, and code with iterative refinement.
discover how kiro, AWS's agentic coding service, drives spec driven development from prompts to requirements, design, code, and tests with a clear, traceable workflow.
Explore Kiro architecture and its eight capabilities that execute prompts from planning to build and deploy, using steering files, Kiro IDE, and MCP tools.
Install the Kiro IDE on Windows, macOS, or Linux, accept licensing, and authenticate via Google or AWS IAM Identity Center, using 50 free credits and a paid plan.
Learn to install and set up Kiro with IAM Identity Center on AWS, using Frankfurt or US East region, creating users, sending invitations, and choosing a Kiro plan with credits.
Learn to build an agentic ai solution on Kiro to automate fleet repair resolution using driver chats, vehicle lookup, maintenance history, and knowledge base to generate estimates.
This lecture demonstrates using Kiro to transform a vehicle diagnostic feature into a set of requirements in a markdown file (requirements.md), capturing AI-driven diagnostic conversations and interaction history.
Generate design.md and task.md files with Kiro from the requirements, analyze requirements for consistency, and log key design decisions while creating a task list and MVP plan.
Kiro integrates with external tools within enterprise via Model Context Protocol to push user stories and design documents to Jira and Confluence, translating natural language queries into tool calls.
Learn to integrate Kiro with an MCP server using Jira and Confluence, configure MCP, push user stories from requirements.md to Jira, and publish a design document to Confluence.
Learn how steering files guide kiro with product, tech, and structure context to standardize architecture, tools, and coding across workspace, global, and team levels.
Implement steering files in FleetMate by configuring DynamoDB-backed AP layer with API gateway, Bedrock, and Lambda, integrating product.md, tech.md, and structure.md for contextual responses.
Execute all mandatory tasks from the requirements, build FleetMate end-to-end, and deploy the cloud infrastructure, frontend, and backend on AWS using SAM, CloudFormation, and Kiro.
Automate repetitive development tasks with Kiro hooks by triggering agent prompts or shell commands on IDE events, updating documentation and tests to speed delivery and improve quality.
Set up hooks in Kiro to automate tasks triggered by events, including a security pre-commit scanner, and define actions like running commands or asking Kiro, while updating the agent context.
Discover kiro powers, pre-packaged bundles of documentation, steering files, and MCP configurations, enabling context-aware loading and standardized outputs. See how power.md semantic matches activate the right MCP tools, reducing tokens.
Explore hands-on use of Kiro powers to install and configure AWS observability tools. Monitor CloudWatch logs, metrics, alarms, and application signals across us-east regions.
Explore Kiro model options and AWS recommendations for selecting the right model for each task, starting with auto, and using Opus for complex problems or Haiku for quick iterations.
Master Python basics with hands-on examples in print, variables, dictionaries, lists, and data types, and learn retrieving values from nested dictionaries for AWS Lambda development.
Master a Python refresher for AWS developers, covering dictionaries, lists, nested structures, indexing, slicing, type checks, and functions with def and lambda, illustrated with boto3 examples.
Generative AI on AWS: Build Production-Ready GenAI Applications
Learn how to design, build and deploy real-world Generative AI applications on AWS using Amazon Bedrock, RAG, serverless architectures and AWS Kiro.
This hands-on course takes you from Generative AI fundamentals to building enterprise-ready applications, guided by a practising AWS GenAI Architect and best-selling Udemy instructor.
What You Will Build – 3 Real-World Projects
Project 1: GenAI Equipment SME Assistant – PoC to Production
Build serverless GenAI applications using Amazon Bedrock, Lambda and API Gateway.
Implement Responsible AI using Bedrock Guardrails.
Explore Model Evaluation, Fine-Tuning, Observability and CloudWatch Monitoring.
Project 2: Serverless Agentic RAG E-Learning Application
Build an intelligent RAG-powered application using Amazon Bedrock and AWS serverless services.
Project 3: FleetMate Using AWS Kiro
Build an application using AWS Kiro, an AI-powered IDE for agentic software development.
What You Will Learn
AI, Machine Learning and Generative AI fundamentals.
Foundation Models, LLMs, prompts and inference.
Amazon Bedrock architecture, models and inference parameters.
Building production-ready GenAI applications on AWS.
Retrieval-Augmented Generation (RAG) and Agentic AI.
Responsible AI using Amazon Bedrock Guardrails.
Model evaluation, customization and fine-tuning.
GenAI observability and monitoring.
AI-powered application development using AWS Kiro.
Course Curriculum
Introduction to the Course
Evolution of Artificial Intelligence and Machine Learning
Generative AI and Foundation Models
Amazon Bedrock – Deep Dive
Project 1 – GenAI Equipment SME Assistant
Project 2 – Serverless Agentic RAG E-Learning Application
Project 3 – FleetMate Using AWS Kiro
Python Fundamentals Refresher
AWS Lambda Refresher
Amazon API Gateway Refresher
Who Should Take This Course?
AWS Developers looking to enter Generative AI.
Solution Architects designing enterprise GenAI applications.
Cloud engineers transitioning into GenAI and Agentic AI roles.
IT professionals interested in Amazon Bedrock, RAG and AWS Kiro.
Prerequisites: Basic AWS knowledge is recommended. No prior AI/ML or Generative AI experience is required. Python, Lambda and API Gateway refreshers are included.
Recommended AWS GenAI Learning Path
Want to become an AWS Generative AI Developer or Architect? I recommend following this learning path:
Hands-On Learning Track
Beginner – Amazon Bedrock, Amazon Q & AWS Generative AI.
Intermediate – Build Production-Ready AI Agents on AWS: Bedrock, CrewAI & MCP.
Advanced – Amazon Bedrock AgentCore: Deploy AI Agents on AWS.
Certification Track
AWS Certified AI Practitioner (AIF-C01).
AWS Certified Generative AI Developer – Professional (AIP-C01).
My recommendation is to prioritize hands-on skills and real-world project experience, while using certifications to validate your knowledge.
Don't just learn Generative AI. Learn how to build production-ready enterprise AI applications on AWS!