Category: Career Aspirants
-
Agent Loops and Planning, and When an Agent Is the Wrong Answer (AI Engineering Series, Part 15)
An agent loop is a cost decision before it is an architecture decision. This part covers how the loop works, why per step accuracy compounds against you, the four workflow patterns that beat an agent in production, and the decision table I use to choose between them.
-
Tool Calling From First Principles, With Python and a Real Loop (AI Engineering Series, Part 14)
Tool calling is a protocol, not a capability the model gains. Here is the full loop in Python, the schema decisions that cut wrong calls, and the two errors every tool calling app hits in its first week.
-
Retrieval Evaluation for RAG, Separated From Answer Evaluation (AI Engineering Series, Part 13)
Most RAG teams report one number and tune the wrong component. Here is how I split retrieval evaluation from answer evaluation on a 120 query set, with ranx, real metric output and the failure attribution table that came out of it.
-
Hybrid Search and Reranking for RAG Retrieval (AI Engineering Series, Part 12)
Dense retrieval cannot find an error code. This part adds BM25, fuses the two ranked lists with reciprocal rank fusion, and reranks the survivors with a cross encoder, with measured nDCG and latency for each step.
-
Vector Stores in Practice: pgvector, Chroma and Qdrant Compared (AI Engineering Series, Part 11)
pgvector, Chroma and Qdrant measured on the same 50,000 chunk corpus: build time, p95 latency, resident memory and the filtered recall collapse that default settings will hand you. With the configuration fixes that actually work.
-
Choosing an Embedding Model: Benchmarking, Dimensions and Cost (AI Engineering Series, Part 10)
Embedding model choice sets your recall ceiling and, far more expensively, the memory your vector index needs forever. Here is the sizing arithmetic, a recall benchmark run on a real corpus, and why 3072 dimensions is rarely the right default.
-
Chunking Strategies for RAG and How to Choose One (AI Engineering Series, Part 9)
Chunk size, overlap, header aware splitting and atomic tables, measured on a real documentation page with langchain-text-splitters 1.1.2. Includes the orphaned table row that cost me three weeks.
-
Document Ingestion for RAG: Parsing, Cleaning and Formats That Break (AI Engineering Series, Part 8)
A rate limit table came out of our handbook PDF as a vertical column of orphaned numbers, and retrieval answered 18 of 40 questions wrong for three weeks before anyone checked. Ingestion decides what your assistant can ever know.
-
Why Retrieval Beats Fine Tuning for Most Business Problems (AI Engineering Series, Part 7)
Retrieval is not cheaper per request; it made our documentation assistant 2.1x more expensive per call. What it buys is a cheap unit of change, and that is the trade that decides most business projects.
-
Errors, Retries, Rate Limits and Timeouts in LLM Applications (AI Engineering Series, Part 6)
Stock SDK retry settings send three requests in 1.5 seconds when the server asked you to wait two minutes. Here is what the defaults actually do, measured, and the retry policy I ship instead.
-
Token Budgets, Context Limits and Cost per LLM Request (AI Engineering Series, Part 5)
One tool schema adds 389 tokens to every request. A newer tokenizer can add 30 percent to your bill with no price change. Here is how to measure token cost before a request leaves your process, and what our documentation assistant actually costs per 1,000 calls.
-
Structured Output From an LLM: JSON Mode, Schemas and Validation That Does Not Fail Silently (AI Engineering Series, Part 4)
Constrained decoding guarantees the shape of a model response, not its truth. Here is how JSON mode, strict JSON schemas and a second validation layer fit together, with the errors you will actually hit.
Architect’s Toolkit
PJ’s Tools
- Infra 360 Hub – All Series
- VCF 9 Interactive Walkthroughs
- VCF Design Cheatsheet
- VCF Upgrade Planner
- VCF 9 Series Hub
- VCF Deployment Hub
- AI Stack Hub
- AI Infra Sizing & Cost Calculator
- LLM & RAG Cost Calculator
- DrJhaGPT – Ask Pranay
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