Multi-Agent vs Single-Agent Workflows: When More Agents Add Complexity
Vendor and analyst guidance converges on the same default: start with one agent and add more only when a specific failure demands it. This guide explains what…
FROM THE AUTHOR
John C. Mullen
Explore the published guides and contributions from John C. Mullen.
86 published articlesHow to Design Prompts That Make AI Ask Clarifying Questions
A clarify-before-answer gate is an explicit prompt rule that tells a model to ask, declare its assumptions, or stop when a request is missing something it needs.…
How to Create a WordPress AI Content Style Guide for Consistent Brand Voice
A WordPress AI content style guide turns brand voice into explicit rules that AI tools can follow. Start with the 3 Cs—Character, Consistency, Context—then encode tone, image…
How to Choose Quantization Settings for Local Models Without Breaking Output Quality
Start with Q4_K_M, then let the model repository override that default. This guide explains what GGUF quantization actually changes, how to read the documented quality, size, and…
Prompt Caching and Prefix Caching in Local LLMs: How They Reduce Memory and Latency
Prompt caching and prefix caching both reuse the key-value (KV) state a model already computed for an unchanged prompt prefix, so a new request can skip that…
How to Prevent Secrets from Leaking into RAG Knowledge Bases and Vector Databases
Secrets leak into RAG when ingestion pipelines index everything without classification, scanning, or access metadata. The fix is layered: keep credentials out of source documents, scan and…
How to Use Function Calling with Local Models for Workflow Automation
Function calling lets a local model request a specific function by name and arguments, while your application decides whether and how to run it. This guide explains…
How to Stream AI API Responses Without Blocking Your UI
Setting stream: true on an AI API request is only half the work. This guide explains how to enable streaming, parse server-sent events without corrupting split chunks,…
How to Design a Trace ID Strategy for AI Workflows and Debugging
A trace ID strategy is a small contract: one trace ID per unit of autonomous work, one span ID per step, a parent link for every child,…
How to Test RAG Pipelines for Retrieval Quality and Answer Faithfulness
A RAG pipeline can fail in two different places, and one end-to-end score will not tell you which. Test retrieval and generation separately: score Precision@k and Recall@k…
How to Write Acceptance Criteria for AI Agent Workflows
Acceptance criteria for AI agent workflows are the observable conditions an output must meet before it counts as complete: the expected artifact, the evidence behind it, its…
How to Use Ollama Tool Calling and Structured JSON Output
Ollama supports two distinct capabilities that are easy to confuse: tool calling, where a model requests a named function that your app executes, and structured outputs, where…