How to Debug WordPress REST API Errors When an AI Ability Fails
When an AI Ability fails over the WordPress REST API, the error usually tells you a request was rejected without telling you which layer rejected it. Debug…
FROM THE AUTHOR
John C. Mullen
Explore the published guides and contributions from John C. Mullen.
86 published articlesHow to Run a Local RAG Stack on a Single GPU: Hardware Requirements and Bottlenecks
A single-GPU RAG stack works once you decide which process owns the GPU. The most predictable pattern reserves the GPU for generation and keeps embeddings and retrieval…
How to Build a Golden Dataset for Repeatable AI Evaluations
A golden dataset is a curated, versioned set of inputs with reviewed expected outputs or explicit pass criteria, used as the fixed reference you run before every…
How to Evaluate RAG Retrieval Quality with a Small Test Set
Build a small, versioned set of real questions paired with the chunk IDs that should answer them, run only the retriever against it, and gate recall@k and…
How to Use AI for Spreadsheet Analysis and Data Cleaning Without Uploading Sensitive Data
You do not have to choose between AI-assisted spreadsheet work and data protection. A layered approach — define the output, classify the columns, minimise the extract, redact…
How to Sanitize .env Files and Config Snippets Before Asking AI for Help
Sanitizing configuration before AI assistance means replacing every live credential and internal identifier with a role-preserving placeholder, then checking logs, stack traces, and screenshots for the same…
How to Test Local AI Agents for Tool-Calling Reliability
Answer-only grading hides the most common agent failures: the wrong tool called with a plausible-sounding summary. The fix is to capture the tool-call log as a structured…
How to Test AI Integrations: Mocking, Golden Datasets, and Regression Tests
LLM integrations cannot be tested with exact string assertions, because the same input can produce different wording on every call. The workable approach is layered: mock the…
How to Automate WordPress Tasks with Ollama and WP-CLI
WP-CLI handles the deterministic WordPress operations, and a local Ollama model supplies the judgement layer that shell scripts lack. This guide shows how to pipe WP-CLI's JSON…
How to Reproduce a Local Ollama Inference Run Exactly
Exact reproduction of an Ollama run requires pinning five layers at once: the model artifact, the runtime version, the sampling parameters, the prompt and context, and the…
Designing an AI Content Review Rubric with Quality Scores and Rejection Reasons
A review rubric converts subjective approval into two machine-readable outputs: a score per quality axis and a named rejection reason when a draft fails. This guide explains…
GGUF vs Safetensors vs GPTQ: Local Model File Formats Explained
GGUF, Safetensors and GPTQ are not three versions of the same thing. GGUF and Safetensors are container formats, while GPTQ is a quantisation method whose weights are…