-
watsonx Assistant, Conversational Applications End to End (IBM Gen AI Series, Part 16)
How to build a conversational application on IBM watsonx Assistant, from a first action and built-in conversational search to routing hard requests to the agent from Part 15, with the channel and cost trade-offs an architect actually weighs.
-
Building Agents on watsonx Orchestrate with the ADK (IBM Gen AI Series, Part 15)
How to build a native agent on watsonx Orchestrate with the ADK, wire its tools, collaborators, and knowledge, pick the right agent style, and keep multi-agent routing from wrecking your bill.
-
watsonx.ai Training Infrastructure and Scaling on OpenShift (IBM Gen AI Series, Part 14)
Every watsonx tune is a Kubernetes job under the hood. Here is how GPU nodes, the NVIDIA operators, autoscaling to zero, MIG limits, and Kueue quotas fit together on Red Hat OpenShift.
-
Data Prep and Synthetic Data on watsonx.data (IBM Gen AI Series, Part 13)
How to land, clean, and curate real data in the watsonx.data lakehouse, then use the Synthetic Data Generator on watsonx.ai to fill the gaps before a tune. With a worked cost example and a runnable cleaning script.
-
InstructLab on watsonx, from Taxonomy to Aligned Model (IBM Gen AI Series, Part 12)
InstructLab teaches a Granite model new skills from a handful of hand written examples, using a taxonomy, synthetic data generation, and phased training. Here is how it works on watsonx.ai and when to reach for it.
-
Prompt Tuning and Fine-Tuning Granite on watsonx (IBM Gen AI Series, Part 11)
watsonx.ai gives you prompt tuning, LoRA, and full fine tuning for Granite. Here is how each method works and how to pick the right one for the size of your data.
-
Granite Guardian and Hallucination Detection on watsonx (IBM Gen AI Series, Part 10)
Granite Guardian is a judge model that scores watsonx answers for hallucination. Here is where it sits in a RAG pipeline, how groundedness detection works, and where to put your block threshold.
-
RAG on watsonx.data with Milvus Vector Search (IBM Gen AI Series, Part 9)
How to build governed RAG on watsonx.data with the embedded Milvus vector database, from choosing a slate or Granite embedding model to sizing the service and picking an index.
-
watsonx.ai Inferencing and Prompt Engineering, from API to Streaming (IBM Gen AI Series, Part 8)
How to call watsonx.ai foundation models: the generation and chat endpoints, the decoding parameters that steer output, streaming, Prompt Lab, and prompt template assets you can reuse.
-
watsonx.ai Regions, Private Connectivity, and Security (IBM Gen AI Series, Part 7)
The watsonx.ai region you pick is a one-way door, and it quietly decides which models, tuning, and compliance you get. Here is how to choose it, then lock the network with private endpoints and your own keys.
-
GPUs and Running watsonx.ai on OpenShift (IBM Gen AI Series, Part 6)
How watsonx.ai actually uses GPUs on Red Hat OpenShift: the operators that expose a card, why memory sizing decides everything, the single node rule for multi GPU models, and when MIG or time slicing is worth it.
-
watsonx.ai Pricing, Resource Units, CUH, and the Plan Tiers (IBM Gen AI Series, Part 5)
watsonx.ai bills two meters at once, Capacity Unit Hours for compute and Resource Units for inference. Here is what each of the four SaaS plans costs, and the point where Essentials stops being the cheaper choice.
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.
Recommendations & Endorsements
Pranay has very deep technical knowledge and exceptional capabilities. He has strong ability to well-manage complex situations and deliver the customer expectations with high standards of satisfaction. We worked together in one of most complex migration projects and Pranay delivered flawlessly.
Pranay was my VMware Architect on one of our financial accounts at IBM. He was instrumental in documenting and recommending our reference architecture. As a Chief Architect, you are only as good as your team that supports you. Pranay was top notch.
Pranay is proactive, result oriented, responsible and technically sound. Always ready to put all his energy to get the job done. Exceptional troubleshooting skills in Windows Server, virtualization and VMware — a great asset to any company.
Pranay is one of the most talented and dedicated persons I have ever worked with. His vast knowledge from different domains enables him to discuss and help on almost every topic in IT. Needless to say, he is expert of experts in VMware.
DrJha