Autoplay
Autocomplete
Previous Lesson
Complete and Continue
Ultimate AWS Bedrock Guide: Build & Scale Generative AI Apps
Introduction
Ultimate AWS Bedrock Guide: Build & Scale Generative AI Apps (1:54)
Course Overview (8:44)
Course Projects Explained
Capstone Project 1 Overview: Building Multi Agentic Workflows (10:12)
Capstone Project 2: Building Interruptible Voice Agents (6:56)
Github Links to All Course Resources
Course Updates
Exercise: Meet Your Classmates and Instructor
Course Resources
Initial Setup
Setting Up our AWS Account (5:24)
Login to IAM User Account (4:24)
Getting Started with AWS Bedrock
Introduction to Bedrock Foundation Models (16:12)
Deep Dive Into Inference Configurations (26:37)
Inference Profiles, Model Catalog, Provisioned Throughput and More Theory (18:06)
Prompt Management, Optimization, and More (18:50)
Exploring the Playground in AWS Bedrock (16:19)
Exploring Modal Providers, Modalities, API Invocation and Pricing (15:31)
Quotas, Model Comparison, Guardrails, and More (27:33)
Image Generation in the Playground with Diffusion Models (2:54)
Code Generation Project
Setting Up the Code Generation Project (1:05)
Coding our Lambda Function and Integrating with AWS Bedrock (17:51)
Setting up API Gateway and our Serverless Stack (5:34)
Testing our Live Endpoint (5:57)
Creating our Boto3 Lambda Layer (2:23)
Attaching our Lambda Layer to our Function (2:24)
Testing our Bedrock Model (6:28)
Verifying Final Output of Bedrock (2:24)
Meeting Notes Summarisation Project with Bedrock
Setting up our Lambda Function with Bedrock for Content Summarization (8:43)
Finishing our Lambda Function for Meeting Summarisation (14:10)
Creating new API Gateway Endpoint for this Lambda Function (2:15)
Invoking our Serverless Meeting Notes Summarisation Endpoint (6:30)
Analyzing the Final Results (1:39)
Using Diffusion Models with Bedrock for Image Creation
Project Introduction (10:57)
Stability AI Update Lecture (1:42)
Setting up API Gateway Route (Serverless) for New Generative AI Model Invocation (1:06)
Invoking our Stable Diffusion model for Image Generation (3:48)
Analysing our Final Output (0:46)
Evaluating Large Language Model Performance with AWS Bedrock Evaluator
Set up Evaluation Job for Anthropic's Claude model (4:37)
Possible CORS Error
Evaluating our Results (5:25)
Retrieval Augmented Generation (RAG) with AWS Bedrock
Introduction to AWS Bedrock Knowledge Base (2:57)
Retrieval Augmented Retrieval (RAG) Overview (6:40)
Setting Up Our Own Knowledge Base - Part 1 (8:08)
Setting Up Our Own Knowledge Base - Part 2 (0:50)
Testing our Bedrock Knowledge Base with Antropic's Claude Model (7:20)
Clean Up Resources (1:10)
API Resources (0:42)
Cleanup
Information About Next Video
A Little Cleanup and Congratulations! (3:16)
Building Multi-Agentic AI Workflow
Architecture Diagram of Our Multi Agentic Workflow (6:41)
LLM Model Access, API Rate Limits, Quotas, and AWS Regions (7:47)
Introduction to AWS Bedrock Agents (1:04)
Creating the Restaurant Agent (17:33)
Creating our AWS S3 Bucket To Store Our Data (4:04)
Uploading Restaurant Data to AWS S3 (0:48)
Creating an Action Group For Our Restaurant Agent (13:01)
Finishing Our Lambda Function for our Restaurant Agent (12:26)
Testing Our Restaurant Agent (14:38)
Setting Up the Accommodation Agent (8:45)
Uploading Our Hotel and Airbnb Data to AWS S3 (1:14)
Creating The Lambda Function Action Group For The Accommodation Agent (17:41)
Finishing Our Accommodation Agent (9:49)
Testing the Accommodation Agent (8:20)
Creating and Testing The Supervisor Agent (9:00)
Explaining Agent Collaborators (4:41)
Multi Agent UI Enhancement, Timing Agents (2:51)
Serverless Invocation of the Supervisor Agent using AWS Lambda (11:51)
Setting up AWS API Gateway to Deploy Our Worfklow Through the Internet (3:24)
Testing Our Endpoint Through The Internet with Postman (5:14)
Cleaning Up Resources (2:29)
Deploying Agents with AWS Bedrock AgentCore
What is AWS Bedrock Agent Core (10:51)
Bedrock Agent Core Course Resources
Accessing AgentCore via Sagemaker AI Setup (1:33)
Finishing SagemakerAI Setup (2:53)
AWS Bedrock Agent Core Architecture Diagram
Creating our Test Agent (14:51)
Testing Our Agent (5:20)
Configuring the AgentCore Runtime (9:09)
Deploying the Agent to AgentCore (8:36)
Tracing the Agent Logs in CloudWatch for Observability (15:46)
Don't forget to shutdown the SagemakerAI Server (0:33)
Session Management for Agents (7:51)
Understanding AgentCore Sessions (5:57)
Lifecycle Management for AgentCore Sessions (4:13)
Cost Calculations for AgentCore Runtime (3:08)
Understanding Costs
Adding Short and Long Term Memory To Bedrock Agents via Bedrock AgentCore
Understanding Short Term Memory (10:06)
Short Term Memory Imports (7:53)
Create the Resources for Short Term Memory (6:42)
Verify Agent Memory Creation in the UI (0:54)
Implementing Memory Hooks (11:07)
Creating the Duck Duck Go Web Search Agent (1:24)
Testing our Short Term Memory Agent (12:18)
Understanding the Pricing of Short Term Memory (1:36)
Introduction to Long Term Memory (2:35)
Long Term Memory Strategies: Semantic, Preferences and Summaries (5:51)
Inspecting Short Term Memory (6:37)
Inspecting Long Term Memory (6:49)
Testing our Agent with a Combined Short and Long Term Memory (11:59)
Long Term Memory Pricing (1:29)
2026 Updates: Reinforcement Fine Tuning, BDA, Prompt Router, Batch Mode + more
Prompt Management with AWS Bedrock (14:39)
Watermark Detection, Was this image Created with AI? (1:52)
Detail About Upcoming Video
Reinforcement Fine Tuning with AWS Bedrock (18:24)
Data Automation, Intelligent Document, Video, Image, and Audio Processing Part 1 (14:01)
Data Automation, Intelligent Document, Video, Image, and Audio Processing Part 2 (6:07)
Data Automation, Intelligent Document, Video, Image, and Audio Processing Part 3 (5:45)
Intelligent Prompt Routing with AWS Bedrock (10:38)
Using LLMs in Batch Inference Mode in AWS Bedrock (12:26)
Building Low-Latency, Interruptible Voice Agents with AWS
Setting Up AWS Access Keys (8:35)
Setting Up Files (2:31)
Understanding Speech-to-Speech Models (2:46)
Understanding Bidirectional Streaming (6:03)
Creating Audio Configurations (3:24)
Setting Up Debugging Functions (4:24)
Non-Blocking Asyncio Python (5:11)
Eventloop and Multithreads in Python (9:27)
Getting Guests, Dynamodb Call (2:48)
Getting Reservations, Dynamodb Call (7:28)
Updating Reservations, Dynamodb Call (9:42)
Event Templates Part 1 (7:30)
Event Templates Part 2 (8:25)
Exploring Tools Our Model Has Access To (6:26)
Tool Result Event (1:37)
Initialising the Bedrock Stream Manager Class (6:14)
Initialising the Bedrock Stream (6:23)
Sending Raw Events to Bedrock (2:28)
Processing Audio Input (3:03)
Sending Events to the Bedrock Stream (7:28)
Processing Incoming Responses From Bedrock (7:10)
Handling Tool Requests + Completions (3:51)
Executing Tools + Gracious Closing and Shutting Down (2:50)
Separate Input and Output Streams (4:14)
Finishing the Audio Streamer Class (8:39)
Ending the Stream Clarification (0:55)
Finishing Up Our Final Script (3:06)
AWS Quotas and Credentials (1:59)
Installing Necessary Libraries (3:26)
Setting up DynamoDB (5:01)
First Test of Our Agent (4:46)
Testing Reservation Updates (3:06)
Testing with the Debug Flag (2:19)
Testing the Final Product (7:03)
Cleaning Up (2:10)
Congratulations! (0:49)
Prompt Management, Optimization, and More