Tag: prompt engineering
-
Choosing and Switching Providers Without a Rewrite (AI Engineering Series, Part 29)
Provider lock in for an LLM application does not live in the API call. I compare six portability strategies with measured latency overhead, show the compatibility endpoint failure that cost us three days, and name the one I would ship.
-
Deployment, Versioning and Rollback for Prompts and Models (AI Engineering Series, Part 28)
A model string in three files is not a deployment story. Here is how I pin model snapshots, version prompts in a registry, canary by tenant hash, and get rollback down from 14 minutes to 8 seconds.
-
Prompt Injection and the Security Model of an LLM Application (AI Engineering Series, Part 24)
Prompt injection is not a filtering problem. Here is how an instruction hidden in a support ticket made my assistant fire 63 escalations, and the tool permission model that took attack success from 71.7 percent down to 3.3 percent.
-
Regression Testing Prompts and Model Upgrades Without Shipping a Silent Downgrade (AI Engineering Series, Part 22)
A prompt edit is a code change with no compiler behind it. Here is the pytest gate, the baseline record and the model migration runbook I use so an upgrade cannot quietly make the assistant worse.
-
Automated Evaluation With LLM as Judge, and Where It Lies to You (AI Engineering Series, Part 21)
An LLM judge that agrees with your humans 71 percent of the time can still be worthless, because a judge that passes everything scores 60. Here is how I calibrate one with Cohen kappa, and the four biases that make it lie.
-
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.
-
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.
-
Prompt Patterns That Survive Contact With Real Users (AI Engineering Series, Part 3)
A production prompt is not a string, it is an ordered stack of blocks with different change frequencies. Here is the layout that survived real users, the cache mistake that cost us $612 a month, and why a longer prompt turned out to be 7.7 times cheaper.
-
Calling a Model From Python: SDKs, Messages and Parameters That Matter (AI Engineering Series, Part 2)
Your first model call from Python, with the message format explained, the parameters that actually change behaviour on current reasoning models, and the two failure modes that corrupt output silently before anyone notices.
-
What an AI Engineer Actually Does, vs ML Engineer, Data Scientist and Backend Developer (AI Engineering Series, Part 1)
An AI engineer builds applications on models somebody else trained. Here is what the job contains day to day, how it differs from ML engineering, data science and backend work, and the order I would learn it in.
-
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.
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