AI Bootcamp
Need to catch up? Find all of our bootcamp issues here
Four framings that get a real objection out of an assistant built to agree with you.
Tell a researched answer from a recalled one, name the four things your assistant cannot reach, and check any sourced report in about four minutes.
Tell whether your assistant computed a number or predicted it, and apply one rule to every figure that leaves your desk.
The 6 questions to put to a long document instead of asking for a summary, and the check that proves an answer came out of the page.
Take a prompt that worked, mark the parts that were only true that day, and keep it somewhere you will still find it in month 3.
Why one enormous request buys a thin answer, and the 5-step sequence that fixes it.
The 3 asks that replaced "think step by step", and how to read what comes back for the parts you can actually check.
One finished sample settles the format that two rounds of adjectives could not.
Role, context, task, format and constraints - what each one actually buys you, and which two you are probably leaving out.
The 5 uses that come round every week, a rhythm under an hour, and the rule that keeps it running in a bad week.
Write the four-part standing instruction once, scope the rest to one project, and stop re-explaining yourself at the top of every chat.
Capture your voice once from three things you already wrote, then check any draft in twenty seconds before it goes out with your name on it.
The account you are signed in to decides most of it, and four words tell you what never goes in the box.
Why a confident answer can be false, the 4 shapes the invention takes, and a 30-second check tied to what a mistake would cost.
Paste it or attach it, what each format really gives you, and how to tell what your assistant did not read.
The Think button trades time for care, not intelligence. Four questions that tell you it is worth the wait, and what each assistant calls it.
Three parts turn a vague ask into one an assistant can follow, and four old prompting tricks you can stop typing.
The first reply is a draft, not a verdict. Four lines that fix most of what comes back, and the point where a new chat beats another correction.
One question sorts every task on your list, plus the four kinds of work that pay off in your first week and the four to keep.
Open the account, find the three parts of the screen that matter, and have one real conversation in about ten minutes.
A one-sentence definition of what an AI assistant actually is, and a five-line rule that picks yours in under a minute
Oct 23, 2026
•
3 min read
Plus 4 prompts to get honest feedback from AI
10 min read
Oct 22, 2026
1 min read
5 steps to write 3x faster with your voice
2 min read
Install it, set a hotkey and a tone for each app, add your own words, and send your first email by voice.
Oct 21, 2026
AI got it wrong? Use this prompt to fix it
8 min read
Oct 19, 2026
Plus 9 ChatGPT prompts for business strategy
Oct 18, 2026
Plus this week's recap in 60 seconds
Oct 16, 2026
Plus 3 prompts to copy & paste today
9 min read
Oct 15, 2026
From market research to your first MVP, here's how to use ChatGPT
5 min read
Ten fill-in-the-blank prompts that take an idea from a market scan to a 30-day MVP test.
Oct 14, 2026
Learn how to convert a video into a Claude skill
Oct 12, 2026
Bonus: Copy paste these prompts on real task
Oct 11, 2026
5 ways to get better AI results + this week's recap
Oct 9, 2026
Oct 8, 2026
Step-by-step guide to get Codex to work for you
4 min read
Install Codex, scope its access, switch on Computer Use and save your rules in AGENTS.md, so it starts every task already set up.
Oct 7, 2026
Oct 5, 2026
Oct 2, 2026
Oct 1, 2026
Talk to ChatGPT, Claude or Gemini the way you would brief a colleague, and give it the full picture on the first try.
