Author: Dr. Pranay Jha
-
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.
-
Amazon SageMaker JumpStart, Foundation Models and Private Hubs (AWS Gen AI Series, Part 18)
SageMaker JumpStart gives you open-weight and proprietary foundation models on your own SageMaker endpoint. Here is how it differs from Bedrock, what it costs, and when the instance bill is worth it.
-
Amazon Bedrock Model Distillation, End to End (AWS Gen AI Series, Part 17)
Amazon Bedrock Model Distillation trains a small student model to answer like a big teacher for a narrow task. Here is how the job runs, which model pairs are allowed, and why Provisioned Throughput, not the training, decides the cost.
-
Amazon Bedrock Fine-Tuning and Continued Pre-Training (AWS Gen AI Series, Part 16)
When a bigger prompt stops paying off, you change the model itself. A practical walk through fine-tuning and continued pre-training on Amazon Bedrock: which models qualify, what a job costs, and how Nova on-demand hosting changed the math.
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