In partnership with
👋 Welcome to AI Central,
Happy Sunday!
We’ve now spent a full week getting better at prompting and hopefully you’ve already tried some of these ideas with your own work.
We started with the five parts of a prompt and why context matters. Then we looked at how one good example can help AI understand the format you want. And on Friday, we tried a simple way to see what AI is assuming before it gives you an answer.
These are small changes but together they can make your prompts much easier to reuse and improve.
Which one did you actually try this week: adding more context, giving AI an example, or asking it to show its assumptions? Hit reply and let me know. I read every response.
Below, check out a bonus guide on how to write great prompts.
Plus you’ll find this week in 60 seconds and what’s coming next week.
Big hug and love you ❤️
Kris & The AI Central Team
P.S. We're building this with you - so if you're loving it (or have any suggestions) leave us a review here
🎙️ What's one thing you've done this week?
We’d love to hear your story. How the bootcamp is going, what you wish we’d cover or something you’ve built and want to show the community.
📊 You need your AI score
Take five minutes of your busy day to yourself - find out where you stand with AI.
You'll get a score, the one thing worth working on next, and a card for LinkedIn if you fancy showing it off.
📚 Want even more resources?
Most AI content online is noise - too basic or too niche to help with the job you're actually paid to do.
If you’re looking for bonus content to the bootcamp, our AI Library is the rest of the syllabus: 3,000 hours of AI research, filtered into one place - searchable by topic, use case, and author, so you find exactly what you need in minutes.
There's a preview video on our homepage - watch it, then start a 1-month trial for $4.99 (less than a coffee).
👇 Get ahead before next week's guides
📋 How to write great prompts
A practical guide to getting better results from AI by giving it the right role, context, instructions, format and constraints. It includes real examples of how to improve prompts for LinkedIn posts, newsletters, SEO strategies, market research and business planning.
If your AI outputs often feel generic or miss the mark, this guide will help you turn vague requests into clear prompts that deliver more useful, actionable results.
Tried one and it worked? Tell us which and we'll build the next pack around what people actually use.
📚 This week's recap
Chapter 13 - The 5 parts of a prompt that works
Role, context, task, format, constraints. Which two do nearly all the work, which one everyone overrates, and why the sentence you spend on "you are a world-class expert" is wasted.
Chapter 14 - How to show AI what good looks like
You can't describe your way to the right format, because "concise" means something different to you than it does to the machine. One finished example settles length, order and tone at once. Plus the 4 tests an example has to pass first.
Chapter 15 - Make AI think before it answers
"Think step by step" is finished, and the vendors say so themselves. The 3 asks that replaced it: show me your assumptions, give me options before you pick, and name the one step this rests on.
Missed one? No problem. They're written to be read in order but any of them stands on its own. Pick the one that sounds most useful and read it with a coffee.
📆 Where we're headed
This week was about getting one instruction right. Next week is about the jobs one instruction can't do.
Monday. What to do when a job is simply too big for a single answer.
Wednesday. Turning the instructions you keep retyping into ones you can reuse.
Friday. Reading a long document properly, the way an analyst would.
