|
Hey there,
Week 2 of the AI, Eh? Summer Boot Camp. Last week was Prompt Better, the foundation everything else builds on. This week we point that exact skill at something that eats up real time every single week of your life, whether you are on vacation or not: dinner.
Quick reminder of the shape, same every week. A detailed prompt you copy and paste. An iteration showing you how to fix it. Something personal you apply it to. And a Prompt Card you save to your toolkit.
If you built My AI Toolkit last week, grab that doc now. We are adding Card 2. Let's go.
Six things every good prompt needs
Same checklist as last week. Watch for all six in the prompt below.
|
1. Give it context. Who you are and what is actually going on, anything AI could not otherwise know. |
|
2. Be specific about the task. Not "help me plan dinner," exactly what you want it to produce. |
|
3. Set your real constraints. Time, budget, allergies, preferences, whatever actually limits your options. |
|
4. Tell it the format you want back. A list, a table, short sections, a word limit. Do not let it guess. |
|
5. Ask it to flag uncertainty. Anything it is not fully sure about, so you know what to double check yourself. |
|
6. Protect your privacy. Skip anything that could identify you personally, like your full name or address. |
Step 1: Run this prompt exactly as written
Open ChatGPT, Claude, or whatever AI tool you already have. Paste the whole thing below in exactly as written, and hit enter.
| "I'm planning weeknight dinners for a busy household this summer, and nobody has much energy to cook after 6pm. One person in the house has a tree nut allergy, so nothing can contain nuts or carry an obvious cross-contamination risk. Give me five weeknight dinner ideas, each takeable in 30 minutes or less, and keep them kid-friendly. Present each one as its own short section with the main ingredients listed, then give me one consolidated shopping list at the bottom, organized by grocery aisle. Flag anything you're not fully certain about, like whether a specific product is genuinely nut-free, so I know what to double check myself." |
Step 2: Here is how you fix it when it is not quite right
You will probably get five solid sounding dinners back, plus a shopping list at the bottom. Look closely at that list, because it is where this kind of thing tends to hide. Somewhere on it, there is a good chance of a packaged or pre-made item, a jarred sauce, a dip, a granola bar, something like that. Packaged products are exactly where cross-contamination risk lives, since plenty of them are made in facilities that also process tree nuts even when the product itself does not contain any. AI cannot see a label, so it cannot know that for certain.
This is exactly the moment to speak up, in one line, in the same conversation.
| "Before I shop, can you go through this list and flag anything that is likely to be packaged or pre-made rather than fresh, so I know exactly what to double check for cross-contamination given the tree nut allergy in the house." |
One sentence, pointed at the actual risk. This is a good habit any time AI hands you a shopping list, not just this week. AI did not do this on purpose, it simply cannot read a package label from here. Catching that is on you, and now you know exactly where to look.
Step 3: Build your own, then save it as a Prompt Card
Now think of something real going on in your own life this week, something ongoing, not a one-time event. In your head, walk through it. What is actually going on. What you actually want back. Your real limits, whatever is actually boxing you in. How you want it formatted. What you want it to double check before you trust it. And keep it anonymous, real details, no names or addresses.
Now say all of that out loud as one real paragraph, the way you would actually explain it to a friend. That is your prompt. Paste it in and run it.
Once you have a result, ask yourself two quick things. Did anything come back not quite right? If so, what one line did you send to fix it?
Now open your toolkit doc, add a heading called Prompt Card 2, and write out these four things yourself, based on what you just did.
|
What this is for. One line, plain language, describing your real situation. |
|
The prompt. The real paragraph you wrote and ran. |
|
The fix that got it there. The one line you sent to correct it, if you needed one. |
|
When to use it again. One line reminding future you when this applies. |
That is Prompt Card 2, done. Two real, working prompts in your toolkit now, both proven on your own life.
Coming up next week
Week 3 is AI for Work, without the jargon. Same four steps, pointed at something you actually deal with on the job. Bring your toolkit doc, Prompt Card 3 is next.
|
AI assisted, Human led.
Whatever AI produces for you, always read it, verify it, and make it sound like you. AI is an incredible first draft machine. Your judgment, your voice, and your values are always the final layer.
|
Hit reply and tell me what your Prompt Card 2 turned out to be. I read every single one.
Know someone who keeps saying they want to "get into AI" but does not know where to start? Forward this to them. Boot Camp starts wherever they join in.
Talk soon,
Chris
Founder, AI, Eh?
theaieh.ca π
|
