Understanding AI

The meeting your AI books with you every morning

Fifteen minutes at the start of the day, holding everything you would otherwise have gone looking for.

What you'll walk away with

A prompt that interviews you and builds your own morning brief, then runs it once so you can see it
The five things worth putting in it, and what each one needs to be able to reach
The honest account of what this takes to set up, which is more than one evening

The prompt takes about fifteen minutes to work through. Getting your accounts connected takes longer.

Start Here, Paste This

Here from the video? This is the line. Paste it into Claude, or into Claude Code if that is where you work. It asks which of the two you are in first, because that decides how the thing gets run each morning, then interviews you and runs your brief once against today so you can see tomorrow's before you commit to it.

Paste this into your AI

I want to set up a morning brief. One short document waiting for me at the start of every day, so I do not begin by going through my calendar and my inbox to work out what the day holds. Before you write anything, ask me which setup I am working in. Claude on the web or desktop with my accounts connected, or Claude Code on my computer. That decides how this gets run each morning, so do not guess it. Then interview me one question at a time. Do not write anything until you have asked all five. 1. What I want to know before the day starts. The things I currently go looking for, in the order I go looking for them. 2. What you can actually reach. Which of my accounts are connected to you right now, calendar, email, notes, anything else. Then tell me plainly which of the things I asked for in question one you cannot get to yet. 3. My meetings. What I want to know about the people I am meeting, and how far back you should look through our history with them. 4. What is waiting on me. Whether I want you to draft the replies and chases I owe, or only list them. 5. When I want it. The time it needs to be ready, and whether it lands in my calendar, my inbox, or a document I open. If I give you a vague answer, push back and ask for the version with the specifics in it. If I ask for something you cannot reach, say so at the time rather than writing it into the brief and letting it fail quietly every morning. When you have all five, write me two things. First, the standing instruction that produces the brief. Address it to you, use my words where I gave them, keep the sections in the order I asked for them, and include two rules. Every section gets written every day even when there is nothing in it, so a quiet day and a broken job never look the same. And you draft, you never send. Second, tell me exactly where that instruction goes and how it runs each morning for the setup I named at the start. If I said Claude Code, save it as a skill in my project and set it to run on a schedule, creating the files yourself rather than telling me how, and if any of those files already exist, merge with what is in them rather than replacing them. If I said the Claude app, put it in a Project's instructions and give me the one line I send each morning to set it going. Then run it once, now, against today, so I can see what tomorrow's will look like. Show me the finished brief, and tell me which sections came back empty because you could not reach the source rather than because there was genuinely nothing there.

Why It Works

In a chat, you are the one moving the information. You go and get the thing, you paste it in, you ask the question, you carry the answer somewhere else. Run the same model on a schedule instead and it does the fetching, so what reaches you in the morning is the finished thing and nobody had to ask it anything.

It lands in the calendar for a reason that has nothing to do with being clever. The calendar is the first thing most people open, so the brief goes where you were already going to look. If your day starts in your inbox, send it there instead. A brief in a place you have to remember to visit is a brief you stop reading in a fortnight.

What Goes In It

Five things, and the test for each is the same. Would you have gone looking for this yourself today, and would you have been slightly annoyed about it.

1Today's meetings, and what you need before each one
Have I met them, what did we say last time, and what did I promise them, read out of your own mail.
2The replies you owe, already drafted
The threads sitting on you and the chases you are waiting on, each with a draft in your drafts folder and nothing sent.
3The notes you wrote away from your desk
Whatever you put on paper or a tablet yesterday, picked up and put where it belongs.
4The numbers you would not otherwise look at
Mine is what the running watch recorded overnight. Yours might be the invoices nobody has paid.
5A line that says the whole thing ran
Every job that fed it, named, with the time it ran, so a dead job never reads as a quiet morning.

One Honest Bit

Writing the instruction is the quick part, and it is not the work. The work is everything it assumes, your accounts connected, somewhere for the AI to read about how you operate, and something running it while you are asleep. Mine took weeks.

The failure worth guarding against is not a broken brief, it is a confident one. If it cannot reach your mail it will not say so, it will write a shorter brief that looks perfectly fine. That is why the prompt makes it name what it could not get to.

The Whole Thing

The morning brief is one job out of a set that all run off the same foundation, the context about how you work, the connections into your accounts, and the schedule that sets them going. Build that once and this is the first of many. It is what I teach, live, on your own machine and against your own work rather than a worked example, and it is a waiting list at the moment. Put your email in and the shape of it and what it costs come to you before anyone else.

If you would rather read about it first, the course page is what you build, who it is for, and what you need on your machine before you start.

Where This Goes Next

If your brief came back generic, the missing piece is context, and the context is what your agent actually knows is the background file that fixes it. If it came back short because it could not reach anything, tools are how your AI stops being useless is which accounts to connect first. And the folder structure is where all of this lives, one place your AI works out of rather than a chat you start again each time.

Want to get better at this?

Let's set up your agent ecosystem.

This page is one job. The whole thing is a set of them running off the same foundation, the folder your AI works out of, the brief on how you like things done, the accounts it can reach and the skills that run off all of it, so your admin gets done the way you would do it. It is what I teach one to one, on your own machine and against your own work, and the quickest way to find out what yours would look like is a proper chat about it.

Book a call Or read about the course first

Not ready for a call? Start with the free agent series, what an AI agent actually is, and build up from there.