Tag: AWS Gen AI Series
-
AWS Generative AI vs the Field, the Verdict (AWS Gen AI Series, Part 30)
After thirty parts on the AWS generative AI stack, the verdict: where Bedrock, Amazon Nova, and AWS silicon earn the default, and the exact cases where Azure, Google Cloud, or IBM watsonx fit better.
-
Bedrock Reference Architectures for Chatbot, RAG, Agentic, and Batch (AWS Gen AI Series, Part 29)
Most AWS generative AI features are one of four shapes: chatbot, RAG, agentic, or batch. Here is how each maps to Amazon Bedrock services, what it costs, and which one to reach for first.
-
LLMOps and CI/CD for Amazon Bedrock and SageMaker (AWS Gen AI Series, Part 28)
LLMOps on AWS is two pipelines, not one. Version Bedrock prompts as code, gate every change on evaluation, register and deploy models through SageMaker, and keep a rollback you have actually tested.
-
Responsible AI and Watermark Detection on Amazon Bedrock (AWS Gen AI Series, Part 27)
A practical walk through responsible AI on AWS: the eight dimensions AWS documents, invisible watermarking on Titan and Nova, the DetectGeneratedContent API, and bias checks with SageMaker Clarify.
-
Amazon Bedrock Cost Governance and FinOps on AWS (AWS Gen AI Series, Part 26)
Bedrock cost is driven by tokens, model choice, and inference tier. Here is how I attribute spend by team, cut it with batch and prompt caching, and put budgets and anomaly alerts around it before the bill surprises anyone.
-
Amazon Bedrock Observability with CloudWatch and Invocation Logging (AWS Gen AI Series, Part 25)
Bedrock ships almost no history by default. Here is how I turn on model invocation logging, pick the CloudWatch metrics worth an alarm, and pull token cost per model straight from the logs.
-
Amazon Bedrock Data Automation for Multimodal Content (AWS Gen AI Series, Part 24)
A practical walk through Amazon Bedrock Data Automation: standard output versus custom blueprints, the async API, real per-page and per-minute pricing, and when to wire it into a Knowledge Base.
-
Amazon Bedrock Model Evaluation, Automatic to LLM-as-a-Judge (AWS Gen AI Series, Part 23)
Amazon Bedrock has three ways to score a model: programmatic metrics, an LLM judge, and human review. Here is what each measures, what it costs, and how to run a judge job without fooling yourself.
-
Amazon Q Business and Amazon Q Developer, Explained for Builders (AWS Gen AI Series, Part 22)
Amazon Q is two products under one name. Here is what Q Business and Q Developer each do in 2026, what they cost, and why Q Developer is moving into Kiro.
-
Amazon Bedrock Multi-Agent Collaboration, Supervisor and Collaborator Agents (AWS Gen AI Series, Part 21)
One supervisor agent, a few specialist collaborators, and a hard step budget. How multi-agent collaboration works on Amazon Bedrock in 2026, what it costs in latency and tokens, and why the Agents Classic cutoff changes where you should build.
-
Amazon SageMaker HyperPod for Resilient Model Training (AWS Gen AI Series, Part 19)
How Amazon SageMaker HyperPod runs resilient GPU and Trainium clusters for multi-week training: Slurm versus EKS, automatic node recovery, checkpointless training, task governance, and what the cluster actually costs.
Architect’s Toolkit
PJ’s Tools
VMware Cloud Foundation
- VCF Documentation
- VCF 9 Planning & Preparation Workbook
- VCF Bill of Materials (BoM)
- VMware Compatibility Guide
- VMware Interoperability Matrix
- VMware Configuration Maximums
- VMware Ports & Protocols
- VMware Hands-on Labs
- RVTools Download
Nutanix
AI & Cloud-Native Platform
- NVIDIA Build (Model Catalog)
- NVIDIA AI Enterprise Reference Architecture
- NVIDIA NIM Performance Benchmarking
- NVIDIA NGC Catalog
- NeMo Microservices Helm Chart
- Helm Charts Repository
- Hugging Face Models
Architecture & Design
About the Author
Dr Pranay Jha
Dr. Pranay Jha is a Cloud and AI Consultant with 18+ years of experience in hybrid cloud, virtualization, and enterprise infrastructure transformation. He specializes in VMware technologies, multi-cloud strategy, and Generative AI solutions. He holds a PhD in Computer Applications with research focused on Cloud and AI, has published multiple research papers, and has been a VMware vExpert since 2016 and a VMUG Community Leader.
You May Have Missed
DrJha