AWS_AI_Series
AWS AI Series
AWS
+2
Jul 11, 2026
•
7 min read
SL#98 - AWS AI Series (30/30) - The Capstone: The Full Architecture, the Real Bill, and What to Keep
Thirty tutorials, one running stack. This is the reference architecture we built, the monthly bill it produces at real traffic, and the honest decision guide for what to keep and what to delete.
AWS
+2
Jul 10, 2026
•
10 min read
SL#97 - AWS AI Series (29/30) - Lock Down Your Agent Stack: A Security Audit With the Agentic AI Lens, IAM Boundaries, and Per-Step Guardrails
We ran an agent stack for 28 episodes. Now we audit it: import the Well-Architected Agentic AI Lens, write a Python auditor for IAM boundaries and wildcard policies, and add a per-step guardrail with the new InvokeGuardrailChecks API.
AWS
+2
Jul 9, 2026
•
9 min read
SL#95 - AWS AI Series (28/30) - GenAI Observability End to End: Ship a CloudWatch Dashboard and a Quality-Regression Alarm for Your Agent
Your agent runs green while returning wrong answers. We wire an AWS Strands agent into CloudWatch GenAI Observability, then add the one signal the built-in metrics cannot give you: an online eval that scores live responses and fires a CloudWatch alarm when quality drops. Plan for about two hours.
AWS
+2
Jul 8, 2026
•
8 min read
SL#94 - AWS AI Series (27/30) - When Bedrock Isn't Enough: Deploy an Open-Weights Model on SageMaker AI With JumpStart and Autoscaling
Deploy an open-weights LLM to a real-time SageMaker endpoint in a few lines with JumpStart, put a target-tracking autoscaling policy in front of it, and get a decision table for when to reach for this instead of Bedrock.
AWS
+2
Jul 6, 2026
•
9 min read
SL#92 - AWS AI Series (26/30) - S3 Vectors vs OpenSearch: Build the Tiered Setup and Do the Latency-Cost Math
We'll put a corpus into Amazon S3 Vectors, benchmark its real query latency, write the cost model that tells you when to keep vectors cheap versus when to promote them to OpenSearch, then export the hot subset to an OpenSearch Serverless collection. Plan for about 90 minutes.
AWS
+2
Jul 5, 2026
•
8 min read
SL#91 - AWS AI Series (25/30) - Real-Time RAG: Stream Documents Through Kinesis Into an S3 Vectors Index That's Searchable in Seconds
Build a streaming pipeline where a document dropped onto a Kinesis stream is embedded, indexed in S3 Vectors, and answerable by a RAG query within seconds. No search cluster required.
AWS
+2
Jul 4, 2026
•
9 min read
SL#90 - AWS AI Series (24/30) - Zero-ETL in Practice: Query Live DynamoDB Data in Redshift With No Pipeline Code
Wire a DynamoDB table to a Redshift Serverless workgroup so operational data lands in your warehouse automatically, then query it with SQL. All of it from boto3 and the Redshift Data API. Plan for 90 minutes, most of it waiting on AWS to provision.
AWS
+2
Jul 3, 2026
•
11 min read
SL#88 - AWS AI Series (23/30) - Clean Your RAG Corpus Before It Poisons Your Answers: A Glue 5.1 Dedup and Quality Gate
Build a serverless Glue 5.1 job that strips junk, removes exact and near-duplicate chunks, and refuses to write the output unless it passes a Data Quality ruleset.
AWS
+2
Jul 1, 2026
•
10 min read
SL#87 - AWS AI Series (22/30) - Athena as Your Data API: Feed Bedrock Prompts From Serverless SQL on S3
Build a feature-extraction layer that turns raw S3 data into compact prompt context with one Athena query, then injects it into a Bedrock call. No database to run, no pipeline to babysit. Plan for 60 to 90 minutes.
AWS
+2
Jun 27, 2026
•
9 min read
SL#84 - AWS AI Series (21/30) - Build an Iceberg Lakehouse on S3 Tables: Time Travel and Auto-Compaction, Queried From Two Engines
Stand up a managed Apache Iceberg table on Amazon S3 Tables, then query it from both Athena SQL and Spark, travel back to an earlier version, and watch S3 compact the files for you with zero maintenance jobs.
AWS
+2
Jun 26, 2026
•
9 min read
SL#83 - AWS AI Series (20/30) - From S3 to Insights in Under an Hour with SageMaker Unified Studio Serverless Notebooks
Stage your own data in S3, onboard into SageMaker Unified Studio with one click, then query it three ways in a single serverless notebook: Athena SQL, Athena for Spark, and a natural-language Data Agent.
AWS
+2
Jun 25, 2026
•
10 min read
SL#82 - AWS AI Series (19/30) - Build a Company Assistant Over S3 and Confluence With a Custom Action in Amazon Q Business
Build an Amazon Q Business application that indexes your S3 documents, connects to Confluence, and runs a custom plugin action that hits your own API. Plan for 2 hours if you have used IAM Identity Center before, 3 if you have not.
AWS
+2
Jun 23, 2026
•
8 min read
SL#80 - AWS AI Series (18/30) - Upgrade a Legacy Java 8 App to Java 21 With AWS Transform's Agentic CLI
Hand a legacy Java 8 Spring Boot app to an AWS agent and get back a Java 21 branch with a green build and a reviewable, commit-by-commit diff. About 60 to 90 minutes, most of it watching builds run.
AWS
+2
Jun 21, 2026
•
9 min read
SL#77 - AWS AI Series (17/30) - Ship a Feature Through Kiro Specs With Property-Based Tests
Take one small, invariant-heavy feature, a fair money splitter, all the way through Kiro's spec workflow: EARS requirements, design, tasks, generated code, and a property-based test suite that actually tries to break it.
AWS
+2
Jun 20, 2026
•
8 min read
SL#75 - AWS AI Series (16/30) - Build and Ship Your Own MCP Server on AWS Lambda
Write a custom MCP server with three tools and session memory, deploy it to Lambda behind API Gateway with Streamable HTTP, verify it with the MCP Inspector, and connect it to Claude.
AWS
+2
Jun 17, 2026
•
10 min read
SL#74 - AWS AI Series (15/30) - Nova Act: Script a Browser Agent That Extracts Data and Fills Forms on a Real Site
Build a Python browser agent with the Amazon Nova Act SDK that navigates a site, pulls structured data into typed Python objects, and fills out a form, all driven by natural language. Plan for 60 to 90 minutes if you have used Playwright or Selenium before.
AWS
+2
Jun 16, 2026
•
8 min read
SL#73 - AWS AI Series (14/30) - Multi-Agent Patterns in Strands: Agents-as-Tools, Swarm, and Graph (and When Each Is Wrong)
Build the same research/writer/reviewer pipeline three ways with the Strands Agents SDK, then learn which pattern to actually reach for.
AWS
+2
Jun 6, 2026
•
8 min read
SL#59 - AWS AI Series (3/30) - Bedrock Guardrails: Build a Guarded Chatbot Endpoint That Actually Blocks the Attacks
Build a support-assistant endpoint protected by Amazon Bedrock Guardrails, then run four attacks against it and watch each one get blocked or masked. Plan for 60 to 90 minutes if you have used boto3 before.
AWS
+2
Jun 4, 2026
•
8 min read
SL#57 - AWS AI Series (1/30) - One API, Two Model Families: Build a Bedrock CLI with Converse, Streaming, and Validated JSON
Episode 1 of the AWS AI Series: a Python CLI that talks to Amazon Nova 2 and Claude Sonnet 4.6 through one identical code path, streams tokens, and returns schema-validated JSON. About an hour, end to end.