VOL 2, ISSUE 42 · NOVEMBER 2026
Frameworks are all around, and they've been in use for ages. Some of my favourites are the five whys, where you ask “why?” until you reach the cause of a problem, and the Eisenhower matrix, which sorts your tasks by how urgent and how important they are. There's no reason why you can't use these in your daily workflows to help you keep organised or to troubleshoot problems.
If you don't know one for your job, ask your AI what established methods exist for it, and pick one that's widely used in business and whose foundations haven't changed.
Here's how you do it. You turn the method into a skill, a set of instructions your AI keeps and follows, so you don't have to explain the method again. These screenshots are from ChatGPT, using the Eisenhower matrix.
1. Find the method's Wikipedia page, start a new chat, and paste in the link with: “I need a skill for this. Ask me questions one at a time before you write it.”
2. Answer each question as it comes, so the AI doesn't make a decision on your behalf.
3. When it has asked its questions, ask it to write the skill as instructions you can paste into a ChatGPT project, a workspace that keeps its own instructions and chats together. To make one, open Projects from the sidebar menu and click Create. Then open the project's settings and paste the instructions into the Instructions box. If ChatGPT says they're over its 8,000-character limit, ask it to shorten them to fit.
4. Start a chat in that project and give it next week's list.
You likely won't get it right first time; it's going to need a little bit of tweaking here and there.
Also in this week's issue: what to ask the companies whose software you rely on, now that OpenAI's new security model has found 81 serious flaws in Firefox, and how to keep your website out of Google's AI summaries.
Your questions are coming in
Some good use cases and questions have been coming in, and I'll be featuring them in an upcoming newsletter. If you haven't filled in the reader survey yet, it asks how you use AI at work and what you're stuck on.
Working with AI
Revisit this week's topic in the full post, with step-by-step frames and a click-through comparing one question at a time with all at once.
An AI's fix can work on the examples it was checked on and yet still fail on new ones. A new study shows one reason it happens, and how to test a fix yourself before you rely on it.
Security and Risk
Your business relies on software that other companies have to patch. OpenAI says GPT-6 Cyber, its new security model, found 81 high-severity flaws in Firefox. Two weeks earlier, attackers were using flaws in PHP, the language a lot of websites run on, within days of the fixes coming out. Part 2 of my series “AI Finds the Flaws. Who Fixes Them?” covers what to ask your suppliers while a fix is on its way.
Guides
When a long chat stops following an instruction you gave it at the start, one possible cause is the context window: how much a single chat can hold. The guide shows the sizes in Claude, ChatGPT and Gemini, what fills them, and what to do when a chat drops an instruction.
 |
Book a discovery session |
Just starting out with AI, or trying to find a way into AI enablement inside your organisation? Book a 60-minute AI discovery session at jimchristian.net/discovery and let's have a chat about what you can make possible.
|
The Industry
Google can both summarise your website in its AI Overviews and use it to train AI. Your site is in both until you change a setting in Google Search Console and add rules to your robots.txt file.
Schools that give students Google accounts can't switch off Google's AI Overviews for them without switching off Search. Students still need to learn to check sources: so who teaches them? Plus three questions parents can ask their schools.
Also this week
For Claude Code users: what a hook is, which of your rules need one, and how to set one up. Read it →
For companies on Claude Enterprise: what the new security check on each prompt catches, and what it misses. Read it →
For paid Claude, Codex and Cursor plans: what to hand over while you have allowance left, and what to do when you run short. Read it →
Reader challenge: do you know what lateral reading is?
|
A
Lateral reading is checking an unfamiliar website by leaving it: you open a new tab and search the open web before spending time on the page.
|
|
B
Lateral reading is skimming a long document by reading only the first sentence of each paragraph, to get the gist quickly.
|
That's it for this week. If your team is working out what to do with AI, hit reply and tell me where you're stuck.
Jim