VOL 2, ISSUE 38 · OCTOBER 2026

A lot of the conversation around AI right now skips clean past the plumbing. We get handed shiny new tools, watch a few polished demos, and immediately expect software to behave like an omnipotent wizard that sorts our working lives out overnight.

When it inevitably stumbles, the blame usually falls on the model’s raw intelligence rather than our own instructions. But whether you are trying to automate a runaway inbox, teaching an agent how to complete a web form, or deciding what to feed a prompt instead of a flashy job title, the leverage never comes from the machine’s intrinsic cleverness. It comes from the unsexy groundwork: setting hard boundary lines, defining what "done" looks like before you start, and remembering that probabilistic code still needs an explicit set of rules.

Here is what is on the site this week.

The Infinite Sandwich and the Made Bed

I was reminded of a few foundational truths during a catch-up with a colleague earlier this week. We were discussing what happens when teams get handed shiny new AI tooling without the playbook: people find themselves caught between the hype and the fear, skipping clean past the unsexy, essential groundwork—data hygiene, governance, and the basic architecture of how things actually fit together. The default expectation is that AI will be an omnipotent wizard swooping in to fix everything. When it doesn't, frustration sets in.

Continue reading →

The 3,848-Message Sieve

Earlier this week, I let an autonomous agent loose on my primary inbox. The starting tally was 3,848 unread messages, and by the time the script finished, the inbox was sitting at a much more manageable 150. Along the way, it archived thousands of older threads, kept every flagged conversation right where it belonged, and cut off dozens of unwanted mailing lists.

Continue reading →

Also on the site

An Agent Needs a Stopping Point

When I used an agent to clear my inbox earlier this week, the hardest part was not telling it what to touch—it was defining what it was forbidden to decide on its own. Flagged mail stayed put, older threads went into the archive, and unfamiliar senders were shunted into a manual review pile. Leaving an agent with "clean up my email" would have handed probabilistic software a blank cheque.

Continue reading →

Hey, That's Not the Real Batmobile!

If you have spent even five minutes reading prompt advice online, you have seen the recipe:

"Act as an award-winning CMO with 20 years of experience..."

"You are a world-class marketing strategist..."

It is comfortably the most copied piece of prompt engineering advice on the web.

Continue reading →

Gems Are Becoming Skills, but I Can Find My Gems, Not My Skills

I am using Gemini more and more for editorial and creative work. I like it for developing ideas and roughing out illustrations, while I tend to use other tools for purely operational jobs. That has meant spending quite a bit of time playing with Gems.

Continue reading →

When Gemini Runs Claude, What Are You Buying?

I have been leaning on Gemini more and more for editorial and creative work, whilst other tools handle my operational jobs. That routine has put me back inside Gems, saving reusable instructions so I don't have to explain the exact same exercise every time I open a window.

Continue reading →

Jim