Tell AI what wins. One of the things that will degrade AI performance the most – and silently – is conflicting instructions where the AI has to determine what you mean. If you look at the reasoning traces (internal chat) when you give conflicting instructions, you’ll see AI models literally chasing their tails. It looks…
Summary In today's episode, I walk through a three-layer framework for training large language models to capture a specific brand voice instead of sounding like generic corporate copy. Here's what this means for you. You gain a repeatable system that combines good and bad examples, prompts aligned to how models think, and quantitative QA loops…
_Almost Timely News: 🗞️ What Would A Purely AI-Generated Newsletter Look Like? (2026-08-30) :: View in Browser_ The Big Plug ✍️ Enroll in my new course, AI for Writers and learn how to make AI write better. Content Authenticity Statement 100% of this week’s newsletter was made by me, the human, BUT you will see…
Disclosure: 100% of this document is AI-generated, made by GLM-5.3-Flash on DeepInfra using the OpenCode harness. The silent stretch where your customers go dark Somewhere in your CRM right now sits a customer who bought from you almost a year ago. They opened everything you sent them for the first few weeks after the purchase.…
Summary In today's episode, I tackle Nathan's question about whether building a content-focused website still makes sense in the age of AI, when search engines scrape and summarize content without sending traffic back. Here's what this means for you. You'll gain a clear framework for treating machines as a distinct audience alongside humans, leaning into…
“Without pulling up the document, tell me what’s in it.” That one sentence tells you in seconds whether or not something is AI slop. You don’t need an AI detector. You don’t need fancy software. You don’t need to burn more tokens or waste more resources. Whether you’re a supervisor, a parent, a teacher, or…
Summary In today's episode, I walk through how to run an objective AI search visibility audit without letting personal search histories and custom profiles skew the results. Here's what this means for you. You get a practical, low-cost playbook for figuring out what AI models actually know about your brand and what they see when…
Summary In today's episode, I walk through how to build a version-controlled prompt management system using Git repositories, agentic plugins, and behavioral change tactics to keep your AI prompts consistent across teams. Here's what this means for you. You'll create a single source of truth for prompts that prevents drift and lost work without forcing…
“when everyone’s super… no one will be!” – Syndrome, the Incredibles When everyone has access to state of the art models, your AI is no longer any kind of advantage, and depending on you or your team’s level of skill, might even be a disadvantage. So, if AI isn’t an advantage any more, then what…
