School starts the last week of August. And with it tags along the forms, school supply lists, the class list (why is it always SO thrilling to find out who is in their classes/who their teachers are??). And then the after school activities I have to make sure I sign up for on time. As a Type C parent, it’s exhausting. IYKYK.

A few months ago, I created something called the Sunday Night Reset. But then I realized I don’t actually have Sunday nights, because by end of weekend I am SO TIRED. So instead, I block 30 minutes on Monday morning. I’m going to share that workflow here with you so you can copy it and try it out. If you have a Sunday to give - props to you. Go for it, name it the Sunday morning reset. If not - do what I do, carve out 30 minutes on Monday morning, consistently. Mine is from 9:30am-10:00am.

Claudia, my chief of staff, built in Guide 2, knows me, so what I gather in my Monday morning reset then keeps going all week long. She knows what is going to go on across each lane (Fractional AI/GTM agency, Newsletter world, small business acquisitions, family & personal - all the things).

(New here? This sits on top of the chief of staff from Guide 2. Build that first, it takes about 20 minutes, and this gets twice as good.)

One thing before I start. The second week of September I’m running the live second brain build - the full system these guides come out of, built with you in real time instead of just written up. Reply to this and I’ll put you on the list.

Subscribe now

Sunday night is a lovely idea

Every version of this you read says Sunday evening. Tea, candle, review the week. (YA RIGHT).

I have tried. It rarely works. By Sunday evening I have three kids who need to be in bed and I am not in a “let’s open the calendar” mood. If I planned my week then, I’d plan it badly and resent it the entire time. (I’m sure the candle people are lovely. I am one of them, but not on Sunday night)

So, pick the time that works for you. Here are some options:

Sunday afternoon, during the nap or the quiet hour. Good if I want Monday to start already moving. Requires a nap that happens and you don’t fall asleep during it.

Sunday evening. Great if evenings are yours. Mine are not.

Monday morning, first thing. This is mine. A repeating hold, 30 minutes, at 9:30am. It would be so lovely to have those 30 minutes back on Monday morning, but this is more realistic for me.

One big list puts the newsletter last. Every time.

I had To Dos. Running lists on Notes. Notion notes. Sticky notes. Paper notes. ALL THE NOTES. But it didn’t really work well.

I realized that a running list didn’t catch all the things I missed (duh) and wasn’t that great at helping me prioritize what mattered. It was a long running grocery list.

Lanes fix it. A lane is focused, and has its purpose. Its own top 3 issues. Here are mine. Once you know yours, it will become so much easier to set aside what matters, ignore the rest. And if you build a Claudia chief of staff, she will get to know these SO well.

1. The client work. Fractional AI, GTM and COO work. Real deliverables, real deadlines, people waiting on me.

2. The newsletter. Nobody is waiting on me. But I do have a commitment to weekly Guides and one Newsletter. So I NEED to carve out time to show up.

3. The acquisition search. I’m looking to buy a small business. Long horizon, zero external pressure, and a week of nothing there costs me nothing today and quite a lot in a year. This is THE HARDEST to keep up with.

4. Family and house. I left this out of planning entirely for a long time. And then I kept finding myself thinking of all the million things that I have to do all the time. I needed a place to make that clear.

Three or four lanes is a healthy range. More than that, you’ll probably get overwhelmed. Or not.

I want to run a 30-minute weekly reset with you. My lanes are: [lane 1], [lane 2], [lane 3], plus family and house.

Go one lane at a time and don’t move on until I’m finished talking. For each lane, ask me what’s live, what’s due this week, and who I’m waiting on.

Then make me name ONE priority per lane and no more than two supporting tasks. If I try to name three priorities in one lane, push back on me.

When the lanes are done, do three things. One: look at everything I’ve named and tell me what to cut or push to next week, and be direct about it. Two: ask me where in my week each priority is going to happen. Three: give me the family and house list separately so I can hand it off.

Finish with one page I can look at all week: priorities by lane, my calendar blocks, my cut list, and the family list. Short enough to read on one screen.

The starter version: one prompt, 30 minutes

If you do one thing from this guide, do this. Open a chat, paste it, talk.

Talk it, don’t type it. Typing makes me edit myself into a tidier week than the one I actually have, and then I’ve planned a week I’m not about to live.

What my 30 minutes look like

Okay so I actually keep a stop watch to go through each step. Because if I don’t I will just keep going on and on.

Last week. 3 minutes. What got done, what carries into this week, and what turned out not to matter.

Dump it out. 3 minutes. Everything on my mind. This one is almost like therapy.

Lane by lane. 14 minutes. What’s live, what’s due, who I’m waiting on. Then one priority and up to two supporting tasks. If I can’t name the one thing, that lane doesn’t have a priority this week, it has a pile. Which is also worth knowing on a Monday. Also putting down a blocker for each priority - meaning, is there something that I am waiting on from someone else?

The calendar check. 4 minutes. Monday to Friday, see what’s going on. Where are the committed blocks, where are the open ones, where is each priority going to sit. This is a good check to make sure I know what’s going on, but also see what I need to cancel so that I have time for my priorities.

Who I’m waiting on. 2 minutes. All four lanes, and then I send the follow-ups right there while I’m in it. Claudia drafts, I send. (I still keep everything on draft and send it myself. No rush to leave that rung.)

The cut list. 4 minutes. The good part. Oh HOW FUN it is to say, nah I don’t need to do that.

Asking myself what I don’t need to do is amazing.

Subscribe now

The level-up: make it remember

Same trap as the chief of staff. A reset that lives in a chat is no bueno. Next Monday opens a blank conversation that has no idea what I said mattered seven days ago.

So it writes to a running doc. One file, newest week on top, dated. Mine sits in Notion next to Claudia’s end-of-day dumps.

Before we start, read my weekly reset doc and tell me what I said my priorities were last week. Ask me what got done, what carried over, and what turned out not to matter.

Then run the reset as usual. When we’re finished, add this week’s page to the top of the doc with today’s date, and don’t overwrite what’s already there.

If you notice something I’ve carried for three weeks or more, say so plainly.

It is so cool what it will remember after one week.

The family lane matters. SO MUCH.

This is the part I nearly left out of the guide, and it’s the part that changed my week the most.

There is real burden and stress that can blindly follow you when you have so many to dos. A big part for me with this reset has been listing them out, knowing what really has to get done, and also sharing that list with others so that they can help me get some of it done. So often so much of what we feel we have to do lives in our heads. Getting it on paper is my fastest sure way now to getting people to help me.

So family and house gets a lane, and it comes out as three lists I can hand off instead of three things I’m holding.

Now the house. Three lists, and keep it quick.

One: walk me through the house and pull out what needs attention this week - cleaning, repairs, restocking, organizing - as a list I can hand off Monday morning.

Two: how many dinners do I need to cover this week, what’s already in the fridge, and any constraints. Pick four or five and build the grocery list.

Three: what’s going in the lunchboxes, and what do I need to buy or prep for that.

Give me the groceries as one list sorted by section of the store, and keep the house list separate so I can send it as-is.

I use this for making grocery lists, setting appointments, ordering lunches, making lunches (I have a Notion board where I actually SNAP pictures of the lunch boxes I packed in the past to add to my planning).

One extra sweep, for September only

September is exhausting. Or end of August. Whichever it is for you when school starts. The forms, new schedules, the stress can fill you for days. So here is one that I am going to try to do going into this school year. It will be new for me so TBD how it comes out:

I’m going to dump everything school-related that’s landed in the last two weeks - emails, forms, dates, sign-ups, supply lists. Sort it into: needs a decision from me, needs an action by a date, and just information.

Give me every date so I can put it on the calendar in one pass, and flag anything with a deadline inside the next ten days.

Ten minutes, and said pile stops being a pile.

What comes out the other side

All my week’s priorities written out. The feeling of stress lifted. I have one page, a clear calendar and a few top priorities that need to get done.

Start here

Don’t build all of it this week. Put a 30-minute repeating hold on Monday morning, name your lanes, and run the starter prompt once.

Add the running doc the second week, once you’ve felt what it’s like to show up on Monday with no memory of last Monday. Add the family lists whenever the house is the thing getting you.

Ten minutes of setup. Then 30 minutes a week.

Save this. Share it with a parent who’s three tabs deep in school forms and hasn’t looked at her own week yet.

I’ll see you after carpool.

Danielle

I run three income streams right now. One generates income. One is neutral. One costs me money, on purpose, for now. Each one isn’t a job. It’s part of a portfolio of careers. Sometimes one gets ALL your attention. Sometimes a second quietly pops up next to the first. And sometimes you’re like me, full on doing three.

Why build a portfolio at all? Our parents mostly picked a company and stayed for decades. And it’s not that we’re less loyal. We are loyal. The game changed. Sinead Bovell, the futurist who founded WAYE, has been making this point for years: the way we work is changing faster than the way we plan our careers. Some of us are scared by that. Some of us are excited. I’ve been both, sometimes in the same week. A portfolio is how you get protection either way. More than one thing can carry you.

I wish I had this playbook while I was still in tech. The BEST position to play with what your portfolio could look like is inside a stable job, while the paycheck covers the experiments. If that’s you, this is exactly for you. If you already took the leap like me, also for you.

One more thing before we start. I spent most of last year hiding behind my own throughline instead of promoting it, because I hadn’t internalized it yet. So this audit is for YOU first. Once you can say your sentence out loud to yourself, then you can start saying it to everyone else.

One paste. Three magic words. Under an hour.

Open the AI that already knows you. Mine is Claude (obviously). Paste the block below. From there it runs the whole thing and you just answer questions. If a kid needs you mid-anything, type PAUSE and walk away. It saves your place and picks back up after bedtime. I built this around my life, not around an empty Saturday, because I don’t have one of those either.

Here’s what the hour looks like as a conversation:

This block is the entire setup.

Copy it in. That’s the setup, all of it:

You are running my Portfolio Career Audit. This is for me first, to see my own
throughline clearly before I ever say it out loud to anyone else. Rules:
- Interview me ONE question at a time and wait for my answer.
- Do NOT flatter me. Be specific and quote my actual history back to me.
- If I type PAUSE, summarize where we are so I can come back to this thread later.

STEP 1 - COLLECT. Ask me to paste my resume or LinkedIn, however messy. Then ask
me these five questions, one at a time:
1. Outside of jobs, what have I led or organized? Volunteer roles, boards, clubs,
   co-chair gigs, community or gym things.
2. My education and my gaps: degrees, an MBA, a gap year, time abroad, career
   breaks. For each one, what did it actually teach me? (Cross-culture skills and
   independence count as much as coursework.)
3. Every side project I ever started, including the dead ones.
4. What do people repeatedly ask me for help with?
5. What work makes time disappear for me, and what makes it crawl?

STEP 2 - When I say MAP ME:
(a) List my skills in plain language, pulled from my real history. Think like an
    operator: things like ops, strategy, cross-functional collaboration, systems
    design, deal economics, customer journey. Use MY versions, from MY history.
(b) Write THE THROUGHLINE: one sentence that says what I’m good at, that I could
    say out loud at a dinner. Not a title, not a brand statement. Give me 3 drafts
    and help me sharpen the one I pick.

STEP 3 - When I say OPTIONS: propose 3-4 portfolio careers that fit my skills and
history, drawn from paths like: paid speaking, a digital product, a newsletter,
advisory work, coaching, fractional work, investing in or buying a small business,
launching a business. For each one: why my history fits it (or where it doesn’t),
what starting small looks like, and a rough monthly number it could earn. Rank
them by which I could explore in 30 days.

STEP 4 - When I say SPRINT: ask for my real weekly hours, then design a 30-day
exploration of ONE option. Small real steps, at least one involving another
person, a number attached, and a finish line with a date. End with the one first
step to take today.

Begin with Step 1.

A few notes before you run it:

• Question 1 is where the good stuff hides. The auction you co-chaired, the board seat, the team you manage at the gym. None of it is on the resume. All of it is skills.

• Question 2 turns “gaps” into inventory. An MBA is deal economics. A travel year is cross-culture skills and independence. A career break is usually an operations job nobody named.

• Short answers beat polished ones. It’s a dump. Typos welcome (I’d be a hypocrite otherwise).

What you get back: three things, on one page.

The sentence and skills below are mine, from running this on myself. Of the three drafts it gave me, here’s the one I kept:

The options board is “Sara’s” (made up, but you know her): 11 years in marketing, then 4 years part-time.

30 days on one option. That’s the outcome.

I get my dopamine from action, and the sentence only becomes true once I act on it. The sprint is small on purpose: 30 days of small real steps beats a year of thinking about it.

Still employed and staying? You’re in the BEST position to run this. The paycheck funds the experiments. That’s the version of this I wish I’d run in tech. And if you have zero free hours, your sprint is one conversation. One person, one chat about one option. It fits outside school at pickup.

Park without guilt is a legitimate outcome, by the way. An option that fails a fair sprint just saved me a year of wondering. I parked buying an accounting firm. For now. That can change as I source more deals.

Sara runs the whole thing.

Notice what the sprint did. It wasn’t just the $600. She internalized her own sentence first, then said it out loud. That order matters. The audit is for you before it’s for anyone else.

Skip these four mistakes.

1. Accepting the compliments. If your skills list reads like a greeting card, it failed. Make it quote your actual history, the auction, the MBA, the gap year, or run it again.

2. Stopping at the sentence. The throughline feels so good to finally see that it’s tempting to stop there. The sentence is the map. The sprint is the trip.

3. Sprinting on the option you love instead of the one that’s ready. Rank 1 is rank 1 because it can produce evidence in 30 days. The one you love will still be there in month two.

4. Hiding behind it. I did this for most of last year: I had the throughline and wouldn’t promote it. Internalize it first, yes. But the sentence is meant to be said out loud, and there’s a date by which you should have said it to one real person.

Where to go from here

• This week: the paste, your skills, your sentence. Under an hour, PAUSE allowed.

• This month: the sprint, live, with a finish line on it.

• Day 30: decide. Grow it, keep it small, or park it without guilt.

Save this. Share it with a parent who needs it.

I’ll see you after carpool.

— Danielle

Your company gave you Claude. Then you caught yourself talking like it.

Guide 4: the file that keeps your writing sounding like you, and the loop that keeps it honest.

I write my Notes on Substack the old-fashioned way. I sit down with my pillars in front of me, I don’t open anything else, and I just write. It’s a good exercise and I like doing it.

Which is why it freaked me out a little when I started finding AI-isms in my own writing. “It’s not X, it’s Y,” sitting right at the front of a sentence, unprompted, from ME. Then I caught myself saying it out loud in a real conversation. I’ve been reading so much AI this year that I’ve started to sound like it, and I’m the one who’s supposed to be catching this stuff. (I wish I was making this up.)

Here’s the part I’d rather skip. I’m not the best writer. When I started the newsletter I leaned on AI to get me going, and a big reason I can write more naturally now is all that back and forth - draft it, rework it, look at what I changed. So I’m semi-okay with how I got here (and I’d do it the same way again). What I’m not okay with is sending something out that doesn’t sound like how I’d really write and talk.

I can also tell when someone else hasn’t done it well. I’ll be reading along and get to a story that’s technically right but not personal enough, where the perspective is so general it could be anybody’s, and I get the ick and I skip it. IYKYK. That reader is me, and that reader is also everyone on your list and everyone who opens your business review. And if you’ve started catching it in your own writing, same.

(New here? Guide 1 builds your second brain, and its My Voice page is the file this guide sits on. Start there.)

Nobody is putting spell check back in the box

Everywhere you look right now, someone is telling you to stop writing with AI. I think that’s wrong, and I’d be a hypocrite anyway, because I use it every single day.

Telling people not to write with AI is like telling them to turn off spell check. Of course you’re going to run spell check before you put something out.

And the output is GOOD, which is exactly what makes this tricky. It tightens up the sentence you would have shipped anyway, and it flows better than your third paragraph was going to. What it can’t do is have your judgment, so what comes back is the average of everybody, and the average of everybody is what I scroll right past.

Alex at Tenex changed how I think about this. He built an amazing newsletter and now he runs an AI agency putting this stuff into some of the largest companies in the world, and he walks through exactly how he balances his own voice against the things he cares about when he writes. Watching someone that good at this use AI on purpose was the thing that did it for me. All we see online is AI slop, AI this, AI that, and I get nauseated by it too, but it’s a tool, and the question is how you use it and how much intention you bring. The voice-file idea itself I took from Ruben Hassid (I am just a text file, and it’s not X, it’s Y is the best list of the giveaways I’ve seen - I highly recommend both). I didn’t invent any of this. I just run it.

The only test I trust: would I say this out loud?

Here’s a real example I’m going to share. My last edition, the camp/color war edition. The draft came back with a header that said “The Scarce Thing Isn’t Knowing Anymore.” Like, I would never say that. Not to you, not to a friend standing outside at school pickup.

What I would say, and what the edition ended up being called, is “Everyone’s prepping their kids for AI. I’m sending mine to camp.” That’s how I talk. It also happens to be what the piece was about, and that’s the other thing that goes wrong when a line isn’t yours: the wrong header had moved the entire edition onto a topic I wasn’t even writing about.

Same pass, I cut “future-proof,” “the ground is moving,” “it clicked,” “kept showing up,” and “underneath the doing.” None of them are bad writing. They just sounded finished before they had a thought in them, and every one of them failed the same test - I read it, I heard myself saying it, and it died in the air.

Ruben’s list of the universal tells is worth knowing (the “it’s not X, it’s Y” flip, the tidy group of three, the em dash doing rhythm work nobody asked for, the puffed-up words). But the one that’s the most meaningful for me is the one that’s based off the sentences I have literally cut out of my own editing before, because if I don’t do that, it’s possible they’ll pop right back up. And I don’t want that to happen.

Three steps, and the third one is why I wrote this

Step 1: Upgrade the file you already built

Guide 1 had you make a My Voice page. It’s version one and it’s supposed to be thin, so what we’re going to do here is go back, tighten it, and make it even more meaningful.

Open my My Voice file. Interview me to make it sharper, in small batches, and I’ll answer out loud. Cover the words and phrases I use constantly, the ones I’d never say, my hard NOs, and what I refuse to sound like. Keep it specific and quotable, not a description of a nice person. Where I’m vague, ask me again.

Answer by talking, not typing. The way you talk IS the raw material, and typing cleans it up before it ever gets to the page.

Step 2: Feed it the writing that isn’t smooth

Most people upload their three most polished pieces and then wonder why what comes back doesn’t sound like them. No surprise. Polished writing is where you sound the most like everybody else.

When I looked at my own writing, it was crazy run-on sentences. Some of them are super choppy. I had caps in there from when I was VERY excited. The flow was weird in some paragraphs and honestly horrible in others. And that talks like me. I talk very fast, and it turns out I write fast the same way. All of that is the part that sounds like me, and it’s the first thing a model tidies away if you don’t tell it not to.

So give it the diversity - the range of how you talk and how you write - sorted by what it was for. I use AI hardest on the two places where it matters most for me: getting something complicated across in a business review, and writing the copy for my own website so it still sounds like a person wrote it. Yours might be the update to your manager, the exec summary, the doc where you’re making a hard case. Give it the good version and the tired version of each.

Here’s a batch of my real writing, sorted by what it was for. Read it against my voice file and add what you find: sentence length and rhythm, punctuation habits, how I open and close, my go-to words, where I get uneven, and anything I never do. Show me the additions before you write them in.

If you talk more than you write, feed it voice notes. A transcript of you thinking out loud is the least edited sample of yourself you own.

(Optional, and worth ten minutes: a second file for who’s on the other end. I keep one for my newsletter reader, because writing that sounds like me but lands nowhere is still a miss.)

Step 3: The diff loop

Every time I let AI draft something, I keep the draft. Then I rework it, again and again and again. And my version comes out different in ways I couldn’t have described to you in advance, so I hand both back and ask what changed.

I’m giving you two versions of the same piece: your draft, and my final after I reworked it. Compare them line by line and tell me what I consistently changed - word choices, sentence length, what I cut, what I added, what I softened. Write the patterns as rules in my voice file, and if you see the same pattern twice, mark it confirmed.

The answers become my own rules, the rules go back in the file, and the next draft starts from a version that took into account all of my ways of not talking. That’s what makes sure that every single time I sit down to write something meaningful in long form, it’s really writing how I would naturally write.

Mine is a real file with a date at the top and a log at the bottom (it’s called AAC Voice Edit Tracker, which is not a super cool name, but it works). It’s how I know things about my own writing that nobody ever told me: that I break a long sentence with a spaced hyphen and never an em dash, that I add a caveat in parentheses so I don’t get misread, that after I admit something hard I always turn it forward. I didn’t know any of that about myself until the diff showed me, twice.

What this is protecting

Use the tool, run the spell check, let it tighten your sentences.

But what you’re building underneath all of it is the version of you that’s portable - your judgment, your taste, the way you land a point. That’s what walks out the door with you when the title changes or the org chart moves, and it’s the one thing on your laptop that can’t be regenerated. Protecting it is the same as protecting whether people trust you, because a reader who clocks you as generic doesn’t argue with you. They just skip you, the same way I do.

So go find your My Voice file from Guide 1 and give it fifteen honest minutes out loud (fifteen, that’s it). Then the next time you let AI draft something real, keep both versions and ask it what you changed. That second habit is the one that compounds, and it costs you about two minutes a draft.

Save this. Send it to the person on your team whose messages have started to sound like everybody else’s.

If I made the full version of this, templates and the full system, would you want it? Hit reply and tell me which part.

I’ll see you after carpool.

- Danielle

Your week is already your newsletter. Here’s how to publish it.

Guide 3: the weekly AI system that turns your real life into an edition that sounds like you.

I run an AI and fractional COO agency, and on the side I’m looking at some business investments. This newsletter is just my pastime, the fun thing I do that has nothing to do with either.

Which is kind of funny, because writing was never my thing. I was a math and science kid who dreaded every paper in school, and I still think way faster in numbers than in words.

So when I started AI After Carpool, the writing itself wasn’t the scary part. The scary part was doing it again the next week, and the week after that, when I’m already running a company, looking at deals, raising three kids, and it’s 9pm with nothing left. That’s where most newsletters die, on the week you’re just too fried to write one.

Most people just open a blank chat and ask AI to write the newsletter for them. I get why, but you can always tell. It comes back smooth and fine and sounds like nobody, and nobody forwards that.

So I do it almost backwards. I don’t start with AI, and I don’t end with it either. AI sits in the middle. First I pump in a ton of my own stuff, the real moments from my week, my actual take, the way I’d say it out loud. Then AI takes all of that and writes the first draft. And then the real work starts, where I go back through the whole thing and rewrite it the way I actually would, like an editor with a red pen. The start is me, the middle is AI, and the end is me again.

This is all of it, the real steps, the actual prompts, and one new piece I’m still testing that I stole from someone in the content world. If you’ve been meaning to start a newsletter, or you’ve got one and every week feels like starting over, this is how I’d do it.

(New here? This works on its own, but it runs on the second brain from Guide 1. If Claude already knows your voice and your reader, all of this gets sharper.)

First, the one idea it all runs on

You feed it, and you finish it. AI just drafts the middle.

The stuff that used to stop me from hitting publish, figuring out what to write, staring at a blank page, the endless title tweaking, AI can carry all of that. But the two things that actually make it mine, everything real I put in at the start and the full rewrite at the end, never leave my hands. AI gets the messy middle, and it never gets the first word or the last word.

Every step below protects that. This isn’t about handing your newsletter to a robot. It’s about owning the start and the finish, and letting AI take the slog in between, so you never face a blank page and you’ve still got energy left for the part that makes it yours.

Wait, what’s a “skill”?

I’m going to say the word skill a lot, so here’s the quick version. A skill is a saved job you run with a slash command: you type /, pick it, and Claude does that one task the same way every time, no re-explaining. You set it up once and you’re done.

You don’t code it, you just talk. Tell Claude what you want it to do (run /skill-creator), or when it nails something, say “save this as a skill.” That’s it.

This matters for a newsletter because it’s the same few jobs every week: find the topic, pick the title, sharpen the take, draft it, edit it, publish it. Turn each one into a skill, and your week stops being “write a newsletter from scratch” and starts being “run down the list.” The system gets it out the door, not whether you feel like it on a Tuesday.

The whole setup, on one page

It’s a chain of small skills that hand off to each other, six skills and one habit, and most weeks I’m not even thinking about it, I just run it.

Every step is only as good as what the one before it handed over. Let me walk you through mine.

Step 1: Document the week (a habit, not a skill)

Honestly, everyone skips this step, and it’s exactly why their AI drafts come out flat. I skipped it too at first.

Now I leave myself a trail all week. Not a journal (I’d never keep a journal), just little breadcrumbs I drop the second something happens: a line one of my kids says in the car, a screenshot of something I saw waiting at pickup, two sentences I thumb into my notes app because a work thing suddenly clicked with a parenting thing, a photo of a page in whatever I’m reading.

A draft comes out generic when you didn’t give it anything real to work with, so it grabs the most average version of your topic and runs with it. Specific beats smart every time, and while AI can polish all day, it can’t make up the thing that actually happened to you on Tuesday, because it wasn’t there. You were.

So catch it in the moment, and talk it out instead of typing it, because you talk way faster than you type and the messy stuff you’d never bother writing down is half of what makes it sound like you. Dump it all in one note, wherever you already live, and by the weekend you’re not staring at a blank page, you’ve got a pile of real stuff to pull from.

Step 2: The Trend Scanner (what to write about)

I read a lot, Justin Welsh, Sahil Bloom, James Clear, a bunch of AI newsletters, plus whatever’s blowing up that week. But a pile of stuff I read isn’t a topic, and what I needed was a way to cut through all of it and land on the one thing actually worth writing about, for my reader.

A trend scanner is a skill that works like a little research assistant you send out every week, and it does two things at once. It plays private investigator on the internet, hunting down the news and conversations that are actually trending in your corner of the world. At the same time, it reads back through my own notes from Step 1 and finds the patterns I didn’t realize I kept circling. Then it weaves the two together, what’s moving out there and what’s already on my mind, because spotting patterns and connecting dots is the one thing AI is genuinely great at.

The other half of it is the reader. Mine’s built around one person, Megan, and I’ve got her written down in detail, what she wants and what she’d roll her eyes at. Every trend has to get past her: would she stop for this, could she use it by Friday, does it make her feel more capable instead of more anxious? If it can’t pass Megan it’s out, and that’s what turns “here’s what’s trending” into “here’s what you should write.”

Build a skill called trend-scanner. When I run it, search the web for what’s
happening this week in [your topic], but filter everything through my specific
reader: [a short description of who they are, what they want, what they’d
never care about].

Hand me a short brief, two pages max:
- The top 4 or 5 things worth writing about this week, plain language,
  opportunity-first, never fear-first.
- For each, the specific angle for my reader and the one concrete thing they
  could actually do with it.
- Any expert or named source that makes it credible.
- End with 2 or 3 mapped into a rough direction, plus a few possible titles.

Also read my running notes from this week [point it at your capture doc] and
weave in anything I captured. My real moments beat anything online, lead with
those where they fit.

Then I read the brief and pick a direction, not the final title yet, just what this week’s about.

Step 3: Lock the hook before you write a word

I did this backwards for months. I’d write the whole newsletter and then try to come up with a title at the end, which is a bad idea, because by then the thing’s wandered all over and you’re just slapping a title on whatever came out.

So now the title comes first, and it’s its own skill. I lock the title and subheader before I write a word, and everything after that gets built to pay it off.

The skill spits out about 20 titles across different angles (not 20 versions of the same one), scores them, and gives me the best 5, each with a subheader. The subheader matters more than you’d think, because the title makes you curious and the subheader tells you what you actually get. And one thing I learned the hard way: the title that sounds best isn’t always the one you have the most to say about. So I hold the 5 and lock the real one in the next step, after I’ve heard myself talk.

Build a skill called hook-titles. From this week’s trend brief, generate 20
title options across different angles, not 20 versions of one idea. All in my
voice, nothing that sounds like a guru or a LinkedIn hustler.

Score them and give me the top 5, each with one or two subheaders. The title
opens the curiosity, the subheader makes the promise concrete. Recommend one,
tell me why in two lines. Invent no detail, story, or number that isn’t real,
flag it instead. Hold the 5 as candidates. I’ll lock one after the interview.

Step 4: The Carpool Council (the new step)

This is the piece I’m most excited about, and it’s new, so fair warning, I’m still testing it. I stole the idea from the content world and made it my own.

It’s simple. Before I write, I sit for an interview, not with a person, but with a little panel of voices I put together on purpose, and their whole job is to drag my real take out of me. I call it the Carpool Council, four seats, and it runs right after I’ve got my title options.

When a draft comes out boring, it’s almost never the writing, it’s that nobody pulled your real take out of you first. This gets mine on the table in ten minutes up front, instead of a two-hour rewrite at the end. The one rule is that the panel never writes, it only asks, and if a seat starts writing sentences for me, I stop it and send it back to questions.

Two seats pull the take out of me, two guard the reader. The systems seat pushes for the exact steps someone could copy, which tool, what I did first, what the prompt actually said. The courage seat asks what it cost me or scared me before I did it, which is where the honest part comes from.

Then the guards come in, after I’ve talked. The reality guard asks whether this is even true today, and still true in three months. The evidence guard asks for the proof, and what a skeptic would say.

The best part is in the middle. After the first two seats dig in, the Council tells me which two or three titles I clearly have the most to say about, and I lock one. That’s when the title actually gets decided, because now I’ve heard myself talk.

And it doesn’t hand me a draft, it hands me a brief, and it’s the most useful page of my week:

LOCKED HOOK:      [your final title and subheader]
THE THESIS:       [your take, your words, a sentence or two]
THE PROOF:        [the specific story, example, or number behind it]
THE MECHANICS:    [the replicable how, from the systems seat]
THE EMOTIONAL     [the cost, the stakes, the real moment, from the
CORE:              courage seat]
THE HONEST        [the limit, the caveat, the counter-argument you’re
CAVEAT:            not dodging, from the guards]
THE READER        [what your reader walks away able to do]
PAYOFF:
RAW QUOTES:       [3 to 6 of your own lines, word for word]

That RAW QUOTES section is a week of social posts sitting right there. Don’t mine your finished newsletter for social later, it’s already been smoothed out, so mine the interview instead, because what you said out loud already sounds like you.

Build a skill called carpool-council. Runs after I have my hook candidates and
my notes for the week. Your job is to interview me, not to write. Never draft a
sentence for me. If you catch yourself writing prose, stop and go back to asking.

Four interviewers, one at a time. Two extract, two guard.
- Extract, the system: push for the exact steps, the specific tool, the real
  sequence someone could copy.
- Extract, the courage: push for what it cost me, the honest moment, the stakes.
- Guard, reality: pressure-test whether it’s true today and in a few months.
- Guard, evidence: pressure-test the proof, and what a skeptic would say.

Run the two extract seats first, each one opening question and up to three
follow-ups, digging till satisfied. I answer out loud. Then, mid-session, name
the 2 or 3 hooks I clearly have the sharpest take on and have me lock one. Then
run the two guards against the locked take. Cap it near ten minutes of me talking.

Output only the brief: locked hook, thesis, proof, mechanics, emotional core,
honest caveat, reader payoff, and 3 to 6 of my own verbatim quotes.

Answer these out loud, by voice, so your real way of talking ends up in the transcript, because that’s what keeps the draft sounding like you.

Step 5: The Newsletter Optimizer (the draft)

By the time I get here, I’m not facing a blank page at all, because I’ve got a locked title, a sharp take, the real proof, and a handful of my own quotes. The draft isn’t starting from scratch, everything it needs I already pulled out of myself.

This is where AI actually writes. The optimizer takes everything I’ve fed in and turns it into a full first draft in my voice. But it doesn’t just spit one out and walk away, it runs me through a short set of questions first, the same ones every week.

It asks the stuff a draft can’t guess: the one real moment this is built on, which of my reader’s worries it speaks to, the line I want her to underline, what I want her to feel, the one small thing she can go do this week. Same questions every time, and after a couple months my own answers basically become my style guide, so the drafts get better because I’m getting clearer, not because the AI is. Then it drafts into a shape that works, and signs off the way I always do.

Build a skill called newsletter-optimizer. Runs with my Council brief and trend
brief in hand. First, interview me with a short fixed set of questions, the same
ones every week: the real anchor moment, the reader-need it serves, the line I
want underlined, the feeling they leave with, the one small action this week,
the tone, anything to avoid.

Then write the full draft in my voice [follow my Voice file], 800 to 1,200 words:
a real relatable moment, a simple no-jargon explanation, why it matters as
opportunity, one small doable action, a reassuring close. Bold the underline
line. End on a question my reader can bring to her dinner table, then my sign-off.
Use only what I gave you. Invent nothing.

What comes back is a real draft, a good one even. It’s just not done, and it’s not mine yet.

Step 6: Take the pen back (the live edits)

This is the part I actually care about, and it’s the part nobody wants to hear takes real time. The optimizer hands me a draft, and I go through the whole thing by hand, out loud, rewriting until every line sounds like me instead of some sharp stranger who read my notes and did their best.

I’ll be straight with you, because people always underestimate this: it’s not a quick polish, it’s a full rewrite, line by line, and it’s the single biggest reason my newsletter sounds like a person. Skip it to save twenty minutes and you’ve wasted everything the steps before it set up.

First I hunt down the AI tells and kill them: the em dashes, every one (nothing screams robot to me faster), the puffed-up words, the neat little groups of three. I keep my own list of words I’d never say, and I run every draft against it.

Then comes the part that actually matters. I read the whole thing out loud, and any line I wouldn’t actually say to a friend at pickup, I rewrite until I would. I put my real details back where it went vague, I add the aside I’d really make, the caveat it was too polished to include. I’m not making it perfect, because perfect is what the draft already was, and that was the problem. I’m making it mine.

Start your own list now, even if it’s just three words, and every draft, notice what you keep changing and add it, so that in a month the draft shows up already half-sounding like you.

Step 7: Publish it, live and ahead

Shortest step, and the one that takes the most discipline: you publish, scheduled and ahead of time, done.

The trap at the end is the same one at the start, the almost-finished draft that sits one more day, then another, until it’s stale and nobody ever read it. So I schedule the send and move on, because a newsletter that goes out on a slightly-off Tuesday beats a perfect one that never ships, every time. Then I start catching breadcrumbs for next week.

What mine actually looks like

My real week looks like this. Monday to Sunday I’m just dropping breadcrumbs, not even thinking about the newsletter. When it’s time, I read the brief over coffee, get my title options, and let the Council interview me for ten minutes, which is still the part that feels like magic, because I sit down sure I’ve got nothing and get up with a take I actually believe. The optimizer drafts it, I spend more time than anywhere else editing it into my voice, and then I schedule it and I’m done.

None of that is me staring at a blank page. I don’t start from nothing anymore, I start from a draft that’s most of the way there, and wrong in exactly the ways I already know how to fix.

Start here

Don’t go build all six skills this week, or you’ll end up with six things you kind of use and none you actually rely on.

Start with the basics: this week, just catch breadcrumbs, out loud, into one note. Next week, add the trend scanner so you’re not starting from nothing, and the week after, add the optimizer so you’ve got a draft to edit. Catch the week, scan, draft, edit, and that alone is a real newsletter going out on a schedule, which is most of the value right there. The hook skill and the Carpool Council take it from good to unmistakably you, and you add those once the rest is a habit.

Build the system, so you’ve got the energy left for the writing.

Save this. Send it to the friend who keeps saying they’re going to start a newsletter and has three dead drafts to prove it.

I’ll see you after carpool.

Danielle

You don’t need a bigger team. You need a Chief of Staff.

Guide 2: turn Claude into the chief of staff you can’t afford to hire.

I run an AI agency full time, and I write this newsletter for fun. No team, no assistant, no chief of staff, because who hires a chief of staff for a company of one?

For a while my whole system was a to-do list I kept rewriting. I tried blocking my whole calendar like everyone tells you to, and it didn’t work. The blocks didn’t know that the thing due today was actually the thing on fire, so I’d blow right through them and still miss stuff that had to get done. Then I’d be at school pickup with my kids, half there, suddenly remembering the email I never sent. Busy and behind at the same time. You know the feeling.

Here’s what changed. I stopped trying to be more disciplined and built a chief of staff inside Claude. I’ve been running it a few weeks and it honestly feels like a cloud lifted. I start the day knowing what actually matters and in what order, and the small stuff sits at the bottom where it belongs.

This guide is how I built it. The real setup, the actual prompts, and the spots where it’s still a little duct-taped. It runs on the second brain from Guide 1, so it already knows your company, your role, and how you sound. You’re just teaching it to run your days.

(New here? Build your second brain first, that’s Guide 1. This one assumes you’ve got it.)

First, give it a name

Sounds silly. Do it anyway. Mine is Claudia. A name is the difference between a tool you forget to open and a person you actually check in with, morning and night. You talk to a name. You build a habit around a name. You’ll catch yourself thinking “did I tell Claudia yet,” and that little bit of pretend is what makes it stick.

Pick whatever you want, Claudia, Jack, Otto, your kid’s imaginary friend. I’ll say Claudia. You swap in yours.

It’s really just one loop

Forget the fancy chief-of-staff org chart. It comes down to two moves, every day.

Morning, a brief: here’s your day, ranked, with where to actually spend your time. Evening, a brain dump: you tell Claudia what happened, she sorts it, and she remembers it for tomorrow.

The morning brief is only good because last night’s dump fed it. Skip the dump for a few days and it goes stale. Keep it up and it sharpens every morning, because it knows more about your actual life. Everything else in this guide just serves that loop.

Where she lives

One thing to clear up before we build: Claudia is a Project. That’s it. Doesn’t matter if you work in the browser or the Cowork desktop app, it’s the same thing, a project that exists just for this. Everything below goes inside it.

Step 1: Build the Claudia project (15 min)

Make a new project called “Claudia.” This holds the standing context a good chief of staff keeps in their head. Build it the way you built your brain, by talking.

Help me build the standing context for my chief of staff, Claudia. She sits on top
of my second brain, so don't re-cover my company or role. This is about what I'm
carrying right now.

Interview me with the AskUserQuestion tool, in small batches. I'll answer out loud.

Cover:
- My priorities and goals this quarter.
- The people who matter (boss, team, key clients) and what each needs from me.
- My recurring meetings and what each is really for.
- The live projects I'm driving, and where each one stands.
- What tends to slip through the cracks for me.

Then write a tight standing context I can save as Claudia's instructions, plus a
starter Open Threads list. Keep it lean, I'll update it as we go.

Save it as Claudia’s instructions. This is the one thing you’ll refresh often, usually on a Monday.

Step 2: Give Claudia eyes (the connectors)

A chief of staff who can’t see your calendar is guessing. This is the step people skip, then wonder why the brief feels generic. Turn on the connectors so she works off your real day.

The two you actually need: Calendar for the brief and meeting context, and Email for triaging what comes in and sending the follow-ups.

• Google (Calendar + Gmail) is the simplest, and it’s what I use.

• Outlook works too, through the Microsoft 365 connector. Two honest catches: it’s read-only (Claudia can read and draft but not send), and it needs a work Microsoft account, not a personal @outlook.com. There’s also a Claude for Outlook add-in in beta if you want more.

To turn them on: Settings, Connectors, switch on Calendar and Email, approve the pop-up. On a personal plan that’s two clicks. On Team or Enterprise, some are admin-controlled, so if a toggle is greyed out that’s a policy setting, not you, and a quick note to IT usually fixes it.

Point her at your running agendas too. This is the one that made the biggest difference for me. I keep running agendas for my meetings and projects, and Claudia reads them, so the brief knows what’s actually coming, not just what’s on the calendar. Connect wherever they live (Notion, Google Docs) or drop them in the project.

No connectors at all? You’re not stuck. Paste in your agenda and forward yourself the emails you want handled. Connectors make it automatic, pasting makes it work today.

Step 3: Give her a memory (a running doc)

This is the piece that makes the loop build on itself, and the one most setups skip. Here’s the trap: if you just talk your day into a chat, that chat is a dead end. Tomorrow’s brief opens a fresh conversation that remembers nothing. The dump has to land somewhere it sticks.

So point Claudia at a running notes doc. Each night your brain dump gets added to it, dated. Each morning the brief reads it. That doc is your memory, and it’s the answer to “where does my voice note go.” Straight into the doc.

I keep mine in Notion, a page called “Claudia EOD Brain Dumps.” Could be a Google Doc, a Notion page, whatever you already live in. Set this up now, before the skills, because the skills read and write to it.

Step 4: Build the two loop skills

Same move as Guide 1: tell Claude what you want, let it build the skill, run it with /. These two are the whole loop.

1. Daily Brief · /daily-brief Your whole day, ranked, in 60 seconds.

Build a skill called daily-brief. When it runs in the morning, read my Claudia standing context, my running notes (last night’s brain dump), my running agendas, and today’s calendar. Then give me: a two-line context up top (what I got done yesterday, and what kind of day today is), a “Where to focus today” section with the 2 or 3 things that actually matter and why, a “Today’s to-dos” list matched to my brain dump, most important first, marking anything already handled and flagging anything you couldn’t find in my calendar or email so I know it’s on me to pull up, a “Follow-ups owed” section for who I owe and what, and a callout for any calendar changes like freed-up time or cancellations. Keep it to one screen.

2. Brain Dump · /brain-dump The evening sweep, the one that matters most.

Build a skill called brain-dump. At the end of the day, ask me what happened, and I’ll talk it out. Turn my ramble into what I committed to and to whom, who I’m waiting on, and what’s starting to slip, sorted by area (mine are Numeriq, AI After Carpool, and Personal). Add today’s summary to my running notes doc, dated, and don’t overwrite what’s already there. Then draft the follow-ups I owe in my voice and ask me which to send.

Get the brief without lifting a finger. This is the good part. Ask Claude to schedule it: “Every weekday at 7am, run my daily brief and have it ready for me.” Now it’s just there when you sit down, which is the whole point. You can still run /daily-brief yourself anytime you want a fresh one. (Honest catch: a scheduled run fires while Claude is running for you, so keep that in mind if you close everything down overnight.)

Make the brain dump impossible to forget

The dump is easy, you just talk. Remembering to do it is the hard part. So don’t leave it to willpower, make it a standing appointment.

1. Set a repeating calendar hold. A real recurring event, every weekday, end of day. Mine’s at 5:00pm, called “Brain dump to Claudia.” Set it to repeat and forget about it.

2. When it goes off, don’t type, talk. Open Claudia and talk it out loud, like you’re catching a colleague up on the way to the parking lot: who you met, what you said yes to, what’s nagging you.

3. Run /brain-dump. She sorts it, writes it to your notes doc, and drafts what you owe.

Two minutes, before you close the laptop. (Not at your desk? Talk it into the Claude app on your phone.)

Sending: don’t let it sit in drafts

Everyone’s gripe with AI assistants is that they write the email and leave it in a drafts folder you never open. We’re not doing that. But handing over the send button is where you go slow. So, two rungs.

Rung 1: draft, you glance, you send (start here). Claudia writes it, shows you in the chat, you say “send it,” done. No drafts graveyard, no forgetting. This is the default, and honestly where I still am. I keep everything on draft and send it myself. No rush to move off this rung.

Rung 2: auto-send the routine stuff (once you trust her). After a couple weeks you’ll spot the emails you never edit, the got-it-thanks replies, the standard recap, the FYI forward. Tell her: for plain confirmations and recaps, just send them and tell me what went out, and show me anything sensitive first. Now the boring 80% sends itself.

One caveat so nothing surprises you: hands-off sending needs a send-enabled email connector. Some (like the Microsoft 365 one) are read-and-draft only, so there Rung 1 is your ceiling. Still beats a graveyard of drafts.

A quick word on staying safe

If you’re on a Claude Team or Enterprise account, your work stays out of model training by default, so you can put real work context into Claudia and sleep fine. Still follow your own company’s policy. On a personal plan you can turn training off yourself under Settings, Privacy. Either way, use the same judgment you’d use writing a normal work email, and you’re good.

When you’re ready: two more skills

The loop is the whole game. Once it’s second nature, a chief of staff does two more jobs worth automating. Build them the same way. No rush though. Build all four on day one and you’ll have four things you half-use instead of one loop you actually live by.

Meeting Prep · /meeting-prep

Before a meeting, ask me who it’s with and the topic (or read the invite). Give me who they are and our history, the context I need, the one outcome to push for, and three sharp questions to ask. Short enough to read in the elevator.

Inbox Triage · /inbox-triage

Read my inbox and sort it into four buckets: needs a reply, needs a decision, FYI, and can wait. Draft the quick replies in my voice and let me approve each one to send, don’t leave them sitting in drafts.

What mine actually looks like

Enough talk, here’s my real morning brief. I stripped out the details, so what you’re seeing is the structure Claudia gives me every day: a quick context line up top, where to focus, my to-dos matched to last night’s dump (with the done ones crossed off and the ones she couldn’t find flagged), and follow-ups I owe.

Yours won’t look polished. It’ll look like an assistant who actually remembers what you told her yesterday, which is the whole thing.

Start here

Don’t build all of it. Build the loop. Set up your Claudia, point her at a notes doc and your calendar, and make just /daily-brief and /brain-dump. Run them for a week, brief in the morning, dump at 5:00. That pair alone is 80% of it, and it’s the part that lifts the cloud.

Save this. Send it to the friend who keeps saying they need an assistant and has one sitting unopened on their laptop.

I’ll see you after carpool.

Danielle

Here’s how it usually goes.

Your company rolls out Claude. There’s maybe a training, maybe just a Slack message with a login and a cheerful “go explore.” You open it between two meetings, type “write a follow-up to the client,” and get back something fine. Generic, but fine. You tweak it, you send it, you close the tab. Three weeks later you’re still using a tool that could rewrite your entire job like a slightly fancier search bar.

That’s not on you. Claude showed up knowing nothing about your company, your role, or how you sound, so it wrote for the average person doing the average version of your job. You never told it who it was working for.

Here’s the trade: a little focused time up front, and every task after that comes back in your voice, aimed at your world. People give it fancy names. I’ll call it what it is: your second brain. Here’s exactly how to build one, then how to build Skills that run whole jobs on top of it.

Part 1: Build the brain

What a second brain actually is

It’s a small, reusable set of context about you and your work that Claude reads before it does anything, so it stops guessing and starts sounding like it actually works with you. Build it once. Everything you make after that starts from it.

Same idea my other company, Numeriq Advisors, installs for whole businesses: one “AI Brain” that holds how the best people work and feeds every function. This is the personal version. One person, one afternoon.

Why this is the whole ballgame

Once the brain exists, everything you make gets sharper, because Claude finally has the context it was missing.

The same ten-word request (“draft the board update”) now comes back in your voice, aimed at your board, using your numbers, and you didn’t write a single instruction to get there. The people getting scary-good work out of Claude aren’t writing better prompts. They just did this part first.

Engine vs. storage (the thing that trips everyone up)

One idea saves a lot of confusion. People mix up how Claude works with where your brain lives. Two different things.

The engine is how Claude works. Chat is quick back-and-forth. Cowork is the heavy engine that runs long, multi-step work on your files. It’s optional, and your admin decides whether you have it.

The storage is where your brain lives, and it’s the part that matters:

• A Project holds your real second brain (your company, role, voice, and collateral). It’s yours by default, and it’s the one thing you can share with your team.

• Personal Preferences is a tiny always-on note about how you like to work, riding along in every chat.

The freeing part: your brain lives in a Project plus that short note, not in some special mode. So it works the same on Pro, Team, or Enterprise, with or without Cowork. Cowork is just a stronger engine you can point at the same brain later.

If you’re using Cowork

If your company gave you the Cowork desktop app and that’s where you’re working, everything here still holds — same three files, same brain. The only thing that changes is where the files live.

Cowork works from a folder on your computer, not from a Project’s knowledge base in the browser. So in Cowork, your brain is a real folder (call it “My Work Brain”) with your three files saved inside it as plain documents, plus your collateral (brand, templates, a couple of finished pieces) dropped in as files. Point Cowork at that folder and it reads them the same way the browser reads a Project.

Two things to know so you don’t get tripped up:

• Build the three files once, keep the master copies somewhere you control. Paste them into a browser Project when you’re on the web; keep them in your Cowork folder when you’re on the desktop. They don’t sync on their own — you’re keeping two homes for the same files.

• Your always-on note lives in Settings and rides along in both places, so you only write it once (Step 2).

So when you hit “Make your Project” below, a Cowork-only reader can make a folder instead. The interviews, the files, and the test are identical either way.

Your brain is three files

Don’t overbuild this. The brain is three short pieces of writing, and they all live in your Project:

1. My Company. What your company does, how it wins, who it serves, the brand and tone, the goals this year. True no matter who holds your job.

2. My Role. What you own, your day-to-day, who you answer to, what you’re measured on. Your specific seat.

3. My Voice. How you write and sound, plus the AI clichés you never want going out with your name on them.

You’ll build all three by talking, not typing. Here’s the whole thing, in order.

Step 1: Open Claude and Wispr Flow (5 min)

Claude. The browser works fine for all of this. If your company also gave you the desktop app with a Cowork tab, great, but you don’t need it to build your brain.

Wispr Flow. This is the part most people skip, and it’s the part that makes the whole thing work when you’re busy. Wispr Flow is a dictation tool: hold one key, talk, and your words show up wherever your cursor is. The free tier is plenty.

Why it matters: the setup below works by Claude interviewing you, and good answers are the whole point. You talk at about 150 words a minute. You type at maybe 40 (and if you’re me, half of those are typos). You also think differently out loud. You ramble, you give the real example, you say the thing you’d never bother typing. That mess is what makes your brain sound like you. Install it first, then talk your answers.

Can’t install it, because your work laptop is locked down? No problem. Type your answers instead, and just make them long and specific. Talking is the easy mode here, not a requirement. Don’t let a missing app stop you from building the brain.

Step 2: Set your always-on note (2 min)

Open Settings, go to your Profile, and find the box that asks what Claude should keep in mind about you. This note rides into every chat, so keep it short and lane-neutral. It’s your working style, not your company. Paste something like:

Be concise and direct. Skip the preamble and filler.
If a request is unclear, ask me one or two sharp questions before you start. Don't guess.
Use plain language, no corporate buzzwords.
When you write in my voice, follow the My Voice file in my project.

That last line is the trick: your actual voice lives in the Project (Step 4), and this note just points to it. Keep company-specific detail out of here, because this note also shows up in your personal chats.

Step 3: Make your Project (2 min)

In the left sidebar, click Projects, then New project. Name it something like “My Work Brain.” You’ll see two boxes: instructions (always loaded) and a knowledge base (files it pulls from when relevant). That’s where the three files go next.

No local folder to build or maintain. And because a Project is a normal feature on every paid plan, you can set this up yourself even if IT has locked down everything else.

Step 4: Build the three files (10-15 min each)

Open a normal chat and paste one prompt at a time. Each runs a short interview: Claude asks, you talk, it writes the file. Then you drop the result into your Project. Do them in order. Break between them if you need to.

Prompt 1: My Company

Help me write the "My Company" page of my Claude second brain. It lives in my
Project and loads before every task, so keep it short and useful — under a page.

Don't write anything yet. Interview me first. Ask me three or four plain
questions at a time, then wait for my answers before the next batch. I'll answer
out loud, so I might ramble — pull out what matters and leave the rest.

Ask me things like:
- If you had to explain what we do to a smart twelve-year-old, what would you say?
- What do people actually pay us for?
- Who is our best-fit customer, and what keeps them up at night?
- When someone picks us over the other option, why do they say yes?
- If our company were a person, how would it talk?
- What is the one big thing we're trying to pull off this year?

If an answer comes out fuzzy, ask me for a real example instead of moving on.
Never fill a gap by guessing — ask me.

When you have enough, write the page: plain sentences, a few short lists, no
filler and no buzzwords. Then give me two versions — a four-to-five-line summary
to paste into my Project instructions, and the full page to save as a knowledge
file.

Tip: paste your company website link into the chat so Claude can pull from it while it interviews you.

Prompt 2: My Role

Now help me write the "My Role" page of the same second brain. The company page
already covers the company — don't repeat any of it. This one is only about my job.

Same as before: interview me first. Ask three or four simple questions at a time
and wait for my answers. I'll talk it through, so listen for what matters.

Ask me things like:
- What's your job title, and what does that actually mean day to day?
- What lands on your desk that really only you can handle?
- Who do you work with most, and who do you report to?
- How does your boss decide whether you had a good month?
- What do you end up making again and again — the same reports, emails, or docs?
- When you hand something off, how do you know it's actually good?

If an answer is vague, ask me for the specific real example. Ask, don't assume.

Then write the page: tight, mostly short lists, under a page. Give me the
four-to-five-line summary for my Project instructions and the full page to save.

Prompt 3: My Voice (spend the most time here)

This is the file that stops Claude sounding like a stranger who skimmed your LinkedIn once. It has Claude study your actual writing, not just ask about it.

Now the most important page: "My Voice." This is what makes Claude write like me
instead of like a robot. Take your time here.

First, learn how I write. Ask me to paste in three things I wrote and liked — an
email, a text, a note, a post, anything real. Read them and tell me what you
notice, with proof from the samples: how long my sentences run, how formal or
loose I am, the words I reach for, how I start, how I sign off, how I handle bad
news. Don't flatter me. Just tell me what's actually there.

Then ask me a few simple questions, a few at a time:
- Who am I usually writing to, and how do I want them to feel?
- Am I more buttoned-up or more casual? Does it change with who I'm writing to?
- Any words or phrases that feel like me?
- Any words or phrases that make me cringe?
- If a coworker read something with no name on it, what would tell them it's mine?

Then write the page in three parts:

1. How I sound — a real description in my own style, pulled from my samples and
answers. Include the three-to-five moves I make every time, and a plain do / don't
list. Be specific, not generic.

2. Words to never use — the AI giveaways to keep out of my writing. Start with
these and let me add my own:
- the "it's not X, it's Y" flip, in all its forms
- puffed-up words: leverage, delve, unlock, tapestry, robust, seamless, elevate,
  game-changer, and their cousins
- the tidy group-of-three ("faster, smarter, better")
- tired openers: "In today's world...", "It's worth noting that..."
- long dashes stacked in one sentence, and every line the same length

3. Before and after — two quick rewrites that take a stiff, generic line and turn
it into how I'd actually say it, so future-me and Claude can see the difference.

Keep it to about a page and a half. Give me the short version for my Project
instructions and the full version to save as a knowledge file.

Step 5: Feed it your real work (5 min)

The three files describe your world. Your collateral shows it. Upload the real material into your Project’s knowledge base, and your output stops being about your company and starts looking like it came from it: your brand (logos, exact colors, style guide), your templates (a board deck, a proposal, the monthly report), and two or three finished pieces you were proud of, so Claude knows the bar.

Then point Claude at them: “Draft the Q3 board deck. Match the template and colors in this project’s knowledge.”

Step 6: Test it (2 min)

Open a fresh chat inside your Project and ask for something real, with no instructions: “Draft my weekly update to my manager.” If the brain’s working, it comes back in your voice, aimed at the right person, using your priorities. If something’s off, open the one file that got it wrong and fix that file. That’s the whole maintenance loop.

When the test comes back wrong

The first try usually isn’t perfect, and that’s fine. Almost every miss traces back to one file. Match the symptom to the fix:

• Still sounds generic or stiff → your My Voice file is too thin. Add real writing samples and specific do’s and don’ts, not adjectives.

• It made up a number, name, or quote → it’s missing your real material. Upload the actual document into your knowledge and tell it to use only what’s there.

• Too long, or too formal → say so in My Voice, add a “keep it short” line, and give it one before-and-after example.

• Describes your company but doesn’t feel like it came from you → that’s a My Role gap. Spell out what you own and who you’re writing for.

• Ignored your template or brand colors → point it straight at the file: “match the template and colors in this project’s knowledge.”

Fix the one file, run the same test again, and move on. You’re not chasing perfect — you’re chasing “sounds like me, mostly.” That’s the file doing its job.

Skip these four mistakes

1. Dumping confidential data. Keep it to what you’d already put in a normal email. No client data, no secrets, unless your company’s policy clearly allows it.

2. Ten-page files. If a file gets bloated, Claude skims it instead of reading it. Lean or it stops working.

3. Company voice in the always-on note. Personal Preferences applies everywhere, including your personal chats. Keep the company and role stuff in the Project.

4. Giving short answers. Short answers make a generic brain. However you answer, go long and give the real example — that’s what makes it sound like you, not whether you typed or talked.

Don’t overload it

More context isn’t always better. A tight brain makes Claude sharp. A bloated one makes it repetitive, because it leans on the same loaded material for every answer. Fine when you want the same board deck every quarter. A problem when you want it to think with you on something new.

Keep the always-on layers lean, and pull in heavy collateral only when the task calls for it.

The corporate stuff (30 seconds)

Greyed-out buttons? If Cowork, a connector, or a setting is missing, that’s your admin, not you. The Project path here needs none of it.

Your data? On Team or Enterprise, your company’s setup generally keeps your work out of model training, so you can add your work context with reasonable confidence (still follow your own policy). On a personal Pro account, you can turn training off yourself under Settings → Privacy.

Keep it fresh

Your job changes, your goals move, new AI clichés start driving you up the wall. Once a quarter, spend ten minutes rereading your three files. Cut what’s stale, update this year’s goals, add new phrases to the banned list, swap in a fresher writing sample. A brain you never update ages like milk.

Reuse it across Projects

The moment you spin up a second Project (a client, a launch, a new team), you’ll want the same you inside it. Here’s the rule that trips people up: a Project’s files stay in that Project. They don’t sync.

So keep your three About Me files saved somewhere central, and re-drop them into each new Project’s knowledge base, with the short summary pasted into its instructions. Then add only what’s specific to that project on top. Your Personal Preferences already ride along everywhere, so the light layer is automatic. Build the About Me once, and stamp it into every new workspace.

Part 2: Turn your brain into Skills

You built the brain. Now stop re-explaining the same tasks.

A Skill is a saved capability you trigger with a slash command, for the work you do again and again. Your brain tells Claude who you are. A Skill tells it how to do a specific job the way you like it, every time, without re-explaining. And because the Skill runs on top of your second brain, it already knows your voice, your brand, and your numbers.

Where Skills live

Two places. You fire a Skill by typing / in any chat and picking it from the menu. You manage them (create, edit, turn on and off) under Customize → Skills. If you don’t see Customize, your company may have it switched off. You can still keep a Skill’s instructions in a note and paste them when you need them.

How to make one

You don’t write code. You describe what you want, out loud, and Claude builds it.

Two ways in:

1. Run /skill-creator and talk it through (Wispr Flow again). Tell it what the skill should do, what to ask you for, and what “good” looks like.

2. Save a win. Any time Claude nails a task, say “save this as a skill.” It turns that chat into a reusable command.

The whole trick is the description. You’re not programming. You’re briefing a sharp assistant on a job you want done the same way every time.

Four skills worth building first

Here’s what each one does, and the plain-language brief you’d hand /skill-creator to build it. Swap in your own details.

1. Friday Recap Email · /friday-recap Turns your week into a polished recap email to your boss.

Build a skill called friday-recap. When I run it, ask me what I worked on this week: wins, what moved forward, anything that slipped, and what’s next. Then write a tight recap email to my manager in my voice (follow my Voice file): a one-line summary up top, then wins, in-progress, and next week, with any blockers flagged. Keep it skimmable. Only use what I actually gave you, don’t inflate.

2. Friday End-of-Day Recap · /eod-recap A quick, informal end-of-week wrap-up for you or your team.

Build a skill called eod-recap. When I run it, ask how the week went and what I got done. Then give me a short, casual end-of-day recap I can drop in Slack or keep for myself: what shipped, what’s still open, and where I’m picking up Monday. Loose and human, not a formal report. Same facts as my boss recap, lighter tone.

3. Content Creation Engine · /content-engine Drafts posts in your voice, and a first-draft press release when you need one.

Build a skill called content-engine. When I run it, ask what I want to make (a social post, or a PR / press release draft), what happened, and who it’s for. For a post: draft it in my voice (follow my Voice file), lead with a real hook, keep it tight, give me two versions. For a PR draft: use my company’s tone from my project, with a headline, a strong first paragraph, a quote slot, and a boilerplate at the end. Only the facts I gave you, don’t invent numbers or quotes.

4. Recurring Meeting Agenda · /meeting-agenda Builds the agenda for your recurring meeting, in your format, every time.

Build a skill called meeting-agenda. When I run it, ask which meeting it’s for, who’s attending, and what’s on my plate this week. Then build the agenda in my usual format: carry over open items from last time, group by topic, and leave space for notes and action items. Keep it tight enough to actually get through. Match how I run that meeting.

The rest of the menu (build these the same way when you need them): /meeting-prep, /board-update, /exec-summary, /competitor-onepager, /email-reply. Same move every time: describe what you want, let Claude build it, trigger it with /.

One rule: start with one. Pick the task you do most, build that skill, use it for a week. Then add the next.

Your next moves

Take one sitting this week and build the brain: Steps 1 through 4 (through your first file) together, My Role and My Voice on two more short breaks, then feed it your collateral and test it. A working second brain by Friday. Then build one Skill, the task you do most, and watch a week of that job get shorter.

That’s the system: a brain that knows you, and Skills that run your repeat work on top of it. Next time I’ll show you how to stack Skills into full workflows, and how a team can share one brain instead of everyone building their own.

Save this. Send it to the colleague whose company just gave them Claude and who still hasn’t opened it.

I’ll see you after carpool.

AI After Carpool · Build your second brain