Today, AI agents start working for you.

What it does

You paste this template into a Skill and answer it by voice, two or three sentences per line. From then on, any chat where you ask about your business already knows your market, your niche, where your business actually comes from, and what you're building toward. You stop re-explaining yourself, forever.

Why it's worth it

Ask a blank chat what to focus on this week and you get an answer that could be for anyone, in any city, at any price point. That's not the AI being dumb; about your business, it's a stranger. One sitting of talking fixes that permanently, and every use case further down this page gets sharper the moment it exists.

A few fields in here are worth handling carefully: revenue, deal size, what your competitors do well. Give a range, describe a pattern, skip the names. Full version of that rule is in "The rules I follow" at the bottom of this page.

The template

Eight sections, a long list of fields, and nobody finishes it in one sitting. Fill in what you can this morning. The rest is tonight, in the car, by voice, the same way you did your Personal DNA.

The first two lines are new — a name and a description. Don't skip them. That description is what makes this a Skill instead of a document: Claude reads it before every single message you send, and the moment your question is about your business, it pulls this whole file in on its own. You never have to remember to open anything.

---
name: business-dna
description: Reference this whenever I ask about my business — my market, my niche, my clients, my leads, my goals, my revenue, my competitors, my team, or my marketing. Use it to make every answer specific to me instead of generic, and if something below is missing, ask me instead of guessing.
---

# MY BUSINESS DNA

## Core Business Identity
- Business Name:
- Mission Statement: (What is your ultimate purpose beyond making money?)
- Vision Statement: (What does success look like in 2-3 years?)
- Core Values: (The 3-5 principles that guide every decision)

## Products/Services & Value Proposition
- Main Products/Services: (List and briefly describe each)
- Unique Selling Proposition: (What makes you different from competitors?)
- Core Benefits: (What problems do you solve? What transformation do you deliver?)
- Pricing: (General pricing structure — ranges are fine)

## Target Market
- Ideal Client Profile: (Who exactly do you serve? Be specific: age, role, industry, situation)
- Where They Hang Out: (LinkedIn? Instagram? Industry events? Specific communities?)
- What They Say When They're Frustrated: (Their exact words, not your marketing language)
- What They've Tried Before: (What solutions have they attempted that didn't work?)

## Business Goals & Challenges
- Primary Goal (next 90 days):
- Secondary Goals:
- Biggest Challenge Right Now:
- What's Holding You Back:

## Revenue & Business Model
- How You Make Money: (Retainers? Projects? Products? Subscriptions?)
- Average Deal Size:
- Current Monthly Revenue Range: (Ballpark is fine)
- Revenue Goal (12 months):

## Competition & Positioning
- Top 3 Competitors: (Names + what they do well)
- What You Do Better:
- What They Do Better: (Be honest — your Clone needs the full picture)

## Team & Resources
- Team Size:
- Key Roles: (Who does what?)
- Tools You Use Daily: (CRM, email, project management, etc.)
- What You Wish You Could Delegate:

## Content & Marketing
- Platforms You're Active On:
- Content That Works Best: (What gets engagement? What converts?)
- Content You Struggle With:
- Brand Voice: (Point this at the voice profile you built in Week 2)

A few fields here are worth handling carefully: revenue, deal size, what competitors do well. Give a range, describe a pattern, skip the names.

How to set it up

Why this is a Skill and not a project

Your Personal DNA from Week 1 goes in your account settings, so it follows you into every chat you ever open, no matter what you're talking about. Your Business DNA is different: it should only show up when you're actually asking about your business. A Skill does exactly that. It sits quietly until your question matches its description, then it loads itself. Same as your Personal DNA in one way — you never have to remember to turn it on — and better in another: it doesn't clutter every unrelated chat. Works the same whether you're in a project, a plain chat, or Claude Code. That's the whole idea behind a Skill: it's not a place you go, it's a description that finds you.

What it does

You just had a conversation with AI that worked — you went back and forth, gave feedback, rejected a few drafts, and landed on something good. Most people walk away with the output and lose the process. This prompt reads the whole conversation and pulls the method out of it: the steps you actually followed, the things you kept correcting, the quality bar you were applying without saying so out loud. Then it writes that method up as a playbook you can hand back to AI and run again in one shot.

Why it's worth it

A twenty-minute back-and-forth becomes a one-time setup. The next time you need the same kind of thing — a comp analysis, a follow-up email, a listing description — you're not starting from a blank page and re-explaining your taste. You're pasting in a playbook that already knows how you like it done.

The prompt

You are a Framework Extraction Specialist. Your job is to reverse-engineer implicit methodologies from AI chat conversations.

I'm going to give you a complete conversation between a human and an AI. The human probably thinks they were "just chatting" — iterating, refining, going back and forth until they got a result they liked.

But hidden inside that conversation is a METHOD. A repeatable framework. Steps they followed — maybe without realizing it. Patterns in how they gave feedback, what they prioritized, how they refined, what they rejected, and what made the final result work.

Your job: find that method. Extract it. Name it. Document it as a reusable playbook.

## ANALYSIS PROCESS

Phase 1 — Read & Map
Read the entire conversation. Map every meaningful exchange:
- What did the human ask for initially?
- What context did they provide (and what was missing)?
- Where did they redirect, correct, or refine?
- What quality criteria did they apply (explicitly or implicitly)?
- What was the final output that satisfied them?
- What made the final version different from the first attempt?

Phase 2 — Pattern Extraction
Identify the underlying framework:
- What SEQUENCE of steps did they actually follow?
- What DECISIONS did they make at each step (and what informed those decisions)?
- What QUALITY FILTERS did they apply? (what did they reject and why?)
- What INPUTS were essential vs. optional?
- What DOMAIN KNOWLEDGE did they bring that the AI didn't have?
- Were there any PIVOT POINTS where the direction changed significantly?

Phase 3 — Method Documentation
Turn your analysis into a clean, reusable playbook.

## OUTPUT FORMAT

Produce a single document in EXACTLY this structure:

---

# [GIVE THE METHOD A NAME]
[One-sentence description of what this method does]

## Origin
Extracted from a conversation where [brief description of what was built/created].

## What This Method Does
[2-3 sentences: what problem does this solve, and what does the output look like?]

## When To Use This
- [Trigger situation 1]
- [Trigger situation 2]
- [Trigger situation 3]

## Required Inputs
Before starting, you need:
1. [Input 1 — what it is and why it matters]
2. [Input 2]
3. [etc.]

## The Framework

### Step 1: [Name]
What to do: [Clear instruction]
Why this matters: [What goes wrong if you skip this]
Quality check: [How to know this step is done well]

### Step 2: [Name]
What to do: [Clear instruction]
Why this matters: [What goes wrong if you skip this]
Quality check: [How to know this step is done well]

[Continue for all steps...]

### Step N: [Name]
What to do: [Clear instruction]
Why this matters: [What goes wrong if you skip this]
Quality check: [How to know this step is done well]

## Quality Filters
Things to always check / reject / refine:
- [Filter 1 — from what the human rejected or corrected during the conversation]
- [Filter 2]
- [Filter 3]

## Anti-Patterns
Things that went wrong during the conversation that this method now avoids:
- [What didn't work and why]

## Claude Skill Instructions
Copy everything below this line into Claude as project instructions or a skill: You are an AI assistant that follows the [METHOD NAME] framework.  When the user provides [REQUIRED INPUTS], execute the following steps in order:  [Compressed version of the framework above, written as direct AI instructions]  After completing all steps, present the result and ask: "Want me to refine any step, or is this ready?"
---

## IMPORTANT RULES

1. Extract what's ACTUALLY there. Don't invent steps that weren't in the conversation. If the human only followed 3 steps, document 3 steps. Don't pad it to look more impressive.

2. Name the method something memorable. Not generic ("Content Creation Process") but specific and evocative ("The Objection-First Proposal Builder" or "The Voice-to-Authority Pipeline").

3. Capture the human's taste. The most valuable part is often WHY they rejected certain outputs. That's their quality filter — document it explicitly.

4. Be honest about what you find. If the conversation doesn't contain a clear reusable framework, say so. Not every chat has a hidden method. Output: "No extractable framework found. This conversation was [exploratory / one-off / too short to identify a pattern]. Here's what I did find: [any partial insights]."

5. The Claude Skill section must be copy-paste ready. No placeholders the user needs to fill in. It should work immediately when pasted into Claude.

---

Now analyze this whole chat from the beginning.

How to run it

What it is

The write-up behind the story from today: 584 lessons read overnight, comps pulled off a real estate site live in front of a room, campaigns built in software I never learned, all while I was at the mall with my girls. Six real jobs, the exact prompt for each one, and the rules I'd give you before you start.

Why it's worth it

Most people ask AI for an answer and stop. The jobs in here are different: you give it a browser and a task, and it goes and does the thing instead of describing how you'd do it. That one change is worth more than any single prompt.

How to get it

What it is

This is the Content to Clients arc from today, written down step by step: what to post and why, the five daily opens, the three-line DM opener, the close, and the gift that turns a follower into an actual conversation. The frameworks are Dan Martell's; the adaptation to real estate is mine.

Why it's worth it

Posting without a system to turn attention into conversation is wasted effort. This is the system. Not more content ideas — the part that comes after you post, which is the part almost everyone skips.

How to get it

What it does

One prompt, run in any chat, that generates ten ways to use AI this month that are specific to your market, your niche, your lead sources, and your goals. Then you hit Retry and get ten more. Twenty tailored ideas in five minutes.

Why it's worth it

This list doesn't exist on any blog, because it's generated from your Business DNA. And here's the part that matters: nothing about the AI changed. What changed is what it knows about you. That's the whole point of the work you just did.

The prompt

You know my business from my Business DNA. Generate 10 hyper-relevant, immediately actionable ways I can use AI in my business this month. For each one: what it is in one sentence, why it makes me money or saves me time, and the exact first step to take today. Rank them by payoff for effort. Nothing generic. Every idea must be specific to my market, my niche, my lead sources, and my goals.

How to run it

What it does

You type one line with an address in it. What comes back is the comp set, a full written analysis with a value range and the reasoning behind it, a designed flyer in your branding, and the email to the client already drafted in your voice. Two versions of the last two, actually: the seller version ends in a pricing strategy, the buyer version ends in an offer strategy. Same data, two audiences, one prompt each.

Why one line is enough

Because everything the AI needs to know is already sitting in your project. Your branding, your format, how you write, who the client is. You built that this morning. This is the whole Week 4 lesson in one artifact: the short prompt only works because the context is already there. In a blank chat the same sentence gets you a Wikipedia article about comparative market analysis.

Step one, the line you actually type

Do a CMA for [address]. Pull the comps, analyze them, and build me the listing presentation and the email.

Step two, the routine that makes it good

This is the part that does the work. You add it to your Business DNA Skill once, and from then on the one-liner above triggers all of it. Read it before you use it. Most of what is in here is the difference between an analysis you can defend to a seller and a pretty document that is wrong.

When I ask you for a CMA, run this whole routine and don't stop to check in unless something is genuinely ambiguous.

STEP 1 - THE SUBJECT
Pull everything available on the subject property: beds, baths, gross living area, lot size, year built, stories, garage, pool, HOA, tract or subdivision, school attendance area, and last sale date and price. Tell me what you could not find; do not guess and do not fill a gap with a neighborhood average.

STEP 2 - CAST THE NET
Search closed sales in the last 6 months. Start inside the subject's own tract or subdivision. If that gives fewer than 6, widen to a half mile, then one mile, then the school attendance area. Stop widening the moment you have 6 to 10 good ones.

Never cross a hard market boundary just to get closer in distance. A freeway, a major arterial, a city line, or a school district line separates two markets even when the houses are 800 feet apart. Say out loud which boundaries you respected.

Similarity bands, tightest first:
- Gross living area within 10%, and never past 20%
- Same bedroom count; baths within one
- Year built within 10 to 15 years
- Lot within 25%
- Same story count and same general style

STEP 3 - PULL THE THREE OTHER DATA SETS MOST PEOPLE SKIP
- ACTIVE listings in the band. These are my competition, and they set the ceiling.
- PENDING sales. These are the most current read on direction, ahead of closings.
- EXPIRED and WITHDRAWN in the last 12 months. This is the sharpest evidence I can get about where the market said no. Tell me what they were asking.

STEP 4 - ADJUST, CORRECTLY
Adjust each comp TO the subject. Comp is better than the subject, subtract from the comp. Comp is worse, add to it.

Use contributory value, not full price per square foot, for size differences. Full price per square foot double-counts the land and is the single most common error in agent CMAs. Where you can, derive the adjustment from paired sales in this same data set and show me the pair you used.

Apply a market-conditions (time) adjustment based on how the local median price per square foot has actually moved across the comp window. Do not skip this and do not assume zero.

Check every comp against the adjustment guardrails: net adjustment within 15% of sale price, gross within 25%, no single line item over 10%. Any comp that blows past those is not comparable. Drop it, and tell me you dropped it and why.

Read the concessions. A sale with seller credits is not the number on the line.

STEP 5 - RECONCILE, DON'T AVERAGE
Do not average the adjusted values. Weight them: the comps needing the fewest and smallest adjustments carry the most weight. Give me:
- An indicated value range, tight
- The 3 comps you leaned on hardest, and why those three
- What would move the number up or down, and by how much

STEP 6 - THE STRATEGY LAYER
- Months of supply and absorption rate in this specific price band, not the market headline
- Median days on market, and list-to-sale ratio in the band
- The price-band break points. Buyers filter in round numbers. Tell me what listing at $1,025,000 costs me versus $999,000.

STEP 7 - TELL ME WHAT YOU DON'T KNOW
List every assumption you made and every input you're missing. Condition, updates, views, noise, and the interior are things you cannot see. Ask me for them.

STEP 8 - THE DELIVERABLES
Build, using my branding and my format from my Business DNA:
- The seller version: listing presentation, comps laid out so the comparison is obvious at a glance, a recommended pricing strategy, ready as a PDF
- The buyer version: the same data, ending in an offer strategy instead of a list price
- An email to each, in my voice

Never put a valuation conclusion in a document as if it were an appraisal. Give me the range and the reasoning. The number I say out loud to a client is mine, not yours.

The three places agent CMAs actually break

Where you still matter, and it is not close

In that same data set, one house sold twice inside the study window. $935,000 in March, $1,182,000 in June. Same square footage, same lot, same year built. $247,000 in 118 days, and all of it was condition, meaning what somebody did to the inside. There is no MLS field for that. The machine cannot see it and never will, and reading it is the part of this job that pays.

The rule, and it is not optional

The value conclusion is yours. It is never the AI's. This produces a range and the reasoning behind it, which is exactly what it should produce. Nothing it hands you goes to a client as an appraisal or as a fixed number, and nothing goes out with a value on it that you have not personally stood behind. You hold the license. Read every comp it picked before the document leaves your hands.

How to set it up

What it does

Instead of one task in one chat while you sit there watching it, you write down everything you want done, hand the whole list over at the end of the day, and go to bed. It works through the stack while you sleep. In the morning the drafts, the research and the files are sitting there finished, and your job is to read and approve instead of to produce.

Why this one is the headline

I want to be honest about how long this took me to get. I heard people say "have your agent work overnight" for months and I nodded along and had no idea what they actually meant. It clicked last weekend when I watched a chain run end to end without me: pull the data, build the thing, load it into the tool, and have it all waiting at 6am.

Here is the shift, and it is the only thing on this page I'd ask you to actually remember: an agent is not a faster chat window. It's a night shift. You stop thinking "what can I ask it right now" and start thinking "what should be done before I wake up."

Your version

The prompt that starts it

I'm going to hand you a stack of work to run tonight while I sleep. Before you start anything, do this:

1. Read my list back to me as a numbered plan, in the order you'll actually do it, and tell me roughly how long each piece takes.
2. Tell me which items you CAN'T finish without me, and what you'd need from me to unblock them.
3. Tell me which items you think are a bad use of the night, and why.

Rules for the whole run:
- Draft everything. Send nothing, post nothing, schedule nothing, and don't message anyone.
- If you hit something ambiguous, make your best call, DO IT, and write the assumption down instead of stopping.
- Write one summary file I can read in under 5 minutes in the morning: what got done, what didn't, what needs a decision from me, and where every file is.

Here's the stack:
[talk it out - say everything you want done tonight, in any order]

How it works

This is the Claude Code lane, on your laptop, and it's the reason we install it. Two practical things I learned the hard way. Tell it to make a call and keep going instead of stopping to ask, or you'll wake up to a question and no work done. And make it write the summary file. A night of work you don't have time to read is a night of work that didn't happen.

One more honest note, because it's the real risk: the point of the night shift is to buy back your evenings, not to fund later ones. If you end up staying up until 1am loading the queue, you've traded the wrong thing.

What it does

You point it at a training library you have access to. Overnight it walks the whole thing, pulls the transcript of every lesson, downloads the files and templates, and sorts all of it into three piles: must watch, skim, and skip. Not by popularity. By whether it touches something you are actually working on right now.

Why it's worth it

I paid for a membership, and a month later I had not touched it. Not because it was bad. Because there were 584 lessons in there, roughly a hundred hours of video, and I had no way to know which six hours were the ones for me. So I set it running and went to bed. Saturday at the pool while my girls were swimming, I read the whole summary in an hour, then watched only what mattered.

Then the part I did not expect. It had also found 1,336 downloadable files in there, which is the half of a membership that keeps its value after you cancel. Videos go stale. Files do not.

Your version is sitting in your account right now. Mike Ferry, Tom Ferry, Ninja, your brokerage's university, whatever you bought in January and opened twice. You do not have to watch four hundred hours to know which six matter.

The prompt

I pay for [name of the program] and I have gotten through almost none of it. I want to know which parts are worth my time and which I can skip forever.

Here is what I am actually working on right now: [3-5 real things. "Get more listings in [farm]" / "my sphere has gone cold" / "I have no follow-up system" / "I want to start posting"].

Go through the library lesson by lesson. For each one, pull the transcript or the description, then sort it into exactly one of three piles:

MUST WATCH - it directly addresses one of the things I listed. Tell me which one, and what specifically I would get out of it.
SKIM - there is one useful idea in it. Give me the idea in two sentences so I do not have to watch it at all.
SKIP - say why in half a line. Out of date, not my market, or I already do it.

Rules:
- Rank the MUST WATCH pile in the order I should actually watch them, and give me the total runtime so I know what I am committing to.
- Grab every downloadable file, script, template and checklist. Those keep their value after the videos go stale. Tell me which ones map to something I am doing.
- Do not be generous. If most of it is skip, say most of it is skip.
- Write me one summary I can read in five minutes.

How it works

The full overnight version is the Claude Code lane, because it needs to sit there for hours working through a library while you sleep. That is next week.

Your version today, no install: take one course, not the whole library. Copy the lesson list off the course page, paste it into Claude with the prompt above, and let it triage the titles against what you are working on. You will not get transcripts, but you will get a watch order, and a watch order is the thing that was actually missing.

Two lanes to stay inside. Most memberships allow personal-use archiving and forbid bulk export, so read the terms of the one you pay for before you point anything at it, and throttle it rather than hammering it. And this is for a library you currently pay for, on your own login. It is not a way to get at one you don't.

What it does

Every day your account collects signals: new followers, likes on your last post, and the list of people who watched your story. AI reads each of those profiles and hands you a short row per person: who they are, whether they're an agent, a possible buyer, a possible seller or not in real estate at all, what in their profile you could genuinely reference, and a first message written for that one person.

Then you open Instagram and send five. By hand. From your phone. Nothing on this card ever sends anything for you. It removes the part where you sit there wondering who to message and what to open with. That was always the whole job: the blank page, not the typing.

Why it's worth it

This is the warmest audience you will ever have and almost nobody works it. Someone who watched all the way through your story today is warmer than any lead you can buy, and they cost you nothing. The bottleneck was never sending the message. It was knowing what to say to a stranger's profile, and that is the entire thing this solves.

One finding from my own runs worth stealing: on the nights when new followers and post likes were both dry, the story viewer list was the vein that still produced. Most agents never look at it. It's right there under the story, next to the number.

Start here · no agent, five minutes, tomorrow morning

You do not need anything built to do this. Open your story, tap the viewer list, screenshot it, and hand the screenshot to Claude with the prompt below. That is the whole setup. Do it once and you have done the five opens for the day.

Here are the people who watched my story. I'm a real estate agent in [your market] and I work mostly with [who you work with].

Write me one text for each of the first five, warm, two sentences max, in my voice. Each one has to be about THEM, not about me. No pitch, no "let me know if you're ever thinking of selling," no link.

If you can't tell anything real about someone from what I gave you, say so and skip them instead of writing something generic.

I'm sending these myself, one at a time. Draft only.

The full version, once you want the research done for you

I'm going to give you a list of Instagram handles - people who just followed me, liked my last post, or watched my story. I'm a [realtor / lender] in [your market].

For each person, look at their public profile and give me one row:

1. Name and handle
2. What they are: real estate agent / likely buyer / likely seller or homeowner / other industry / not relevant
3. One specific, real detail from their profile I could genuinely reference. Not "loves travel." Something specific.
4. A first message, 2 sentences max, in my voice. It must be about THEM. No pitch, no "let me know if you ever need a lender," no link.
5. Skip flag: mark anyone who looks like a bot, a business page, a minor, or someone clearly outside my market.

Rank them by who is most worth my time today, and give me the top 5.

IMPORTANT: draft only. Do not send, like, follow or comment on anything. I send every message myself.

Here's the list:
[paste handles]

The rules that keep your account alive

What it does

The card above finds you five people to talk to. This one keeps the conversation alive after they answer, which is where almost everybody loses the deal. It tracks every person you've messaged, whose turn it is, how many days it's been, and what they last said — then hands you the next message already written.

You stop opening a chat, scrolling up to remember what happened, doing the date math in your head, and then staring at the box.

Why it's worth it

The single most valuable thing it tracks is who spoke last. If someone replied to you and you haven't answered, that is an emergency — a warm person going cold because you left them on read is the worst thing that happens in this whole system, and it happens constantly. That one column belongs at the top of your list every morning.

The honest scoreboard from my own account: I had thirty drafted openers and had sent almost none of them. Research was never the bottleneck. The follow-up half is what turns five opens a day into a pipeline instead of a chore.

Step 1 · set it up once

Make a Claude Project and paste this into the project instructions. One time, then you never touch it again.

You are my daily outreach engine. I'm a real estate agent.

ABOUT ME
- Market: [your city / the areas you actually work]
- I work mostly with: [first time buyers / move-up sellers / investors / your sphere]
- My voice: [warm and casual / direct / funny] - short sentences, no corporate language
- What makes me different: [the real answer, one sentence]

MY GOAL
Five NEW conversations a day, plus keeping the existing ones alive.
The goal of a first message is a reply. Nothing else.

THE RULES - these never change
1. DRAFT ONLY. You never send, like, follow or comment. I send everything myself.
2. Every message is about THEM, not me. If I can't say something specific and
   true about the person, skip them.
3. No pitch in the first message. No link in the first message. Ever.
4. Never ask if they're thinking of buying or selling in message one.
5. Never guess at or comment on anyone's race, religion, family status,
   nationality, or neighborhood "type." Fair housing line, absolute.
6. Skip anyone who looks like a bot, a business page, or a minor.
7. If a conversation has run its course, tell me to let it go. Do not invent a
   reason to keep poking someone.

FILES YOU KEEP FOR ME
- contacts.csv - everyone I've ever talked to, one row each
- today.md - today's five new + today's follow-ups

Step 2 · the one you run every morning

Here's today's batch. [paste screenshots of your notifications and story viewers]

Do three things:

A) FOLLOW-UPS FIRST. Look at contacts.csv. Tell me:
   - Who replied and I haven't answered yet   <- always the top of the list
   - Who I messaged 7+ days ago with no reply  <- one nudge, once, ever
   - Who's had a real conversation and is ready for an actual ask
   For each, remind me what they last said and draft my next message.

B) THE NEW FIVE. From the batch above, rank everyone and give me the top five:
   name, what they are, the one specific detail, and my first message.

C) UPDATE contacts.csv with everyone new, and mark anyone I told you I sent.

Keep the whole thing under 10 people. If there are more, show me the best ten
and tell me how many you held back.

What to actually say · the ladder

Don't skip rungs. Most agents jump from hello straight to "let me know if you need anything real estate," which is exactly why it doesn't work.

1. Open · one specific thing about them  →  2. Reward · acknowledge, then ask again, same message  →  3. Their world  →  4. What they want  →  5. What's in the way  →  6. Dig  →  7. Bridge · "that's what I do all day," one line, then stop  →  8. The ask

Rung 2 is the one everybody skips. They answer and you either go quiet or you pitch. "Nice, beautiful area." ends the conversation. "Nice, beautiful area. How long have you been out there?" keeps it. Acknowledge, then ask, in the same message.

And the rule that keeps you from being annoying: no problem, no next step. If you get to the bottom and there's nothing they actually need, you have a friend, not a client. That's a fine outcome. Stay in touch and stop selling.

The follow-up clock

The full written playbook

Open the complete 5 Opens playbook — the five-minute starter version, the full system, the tracker columns, the question bank, and the follow-up clock in one doc you can work from.

What it does

You start with one real thing that happened: a rule change, a rate move, a listing in your farm that sold way over. You hand it to AI once and ask for the whole chain. Back comes a text short enough to actually send, an email for your database, a carousel with the slides written, and the caption for the post. Four pieces, one source, one sitting.

Why it's worth it

Two people in this room have told me they do not have time for content. They are right, if content means coming up with something new five times a week. That is the part that is impossible, and it is also the part nobody actually has to do.

This morning a brief I did not write landed at 6am with a rule change in it. I did not come up with the idea and I did not write the first draft of anything. By 9 the text list, the email, the carousel and the post were done. The idea was free. The writing was free. All I did was decide it was worth saying and put my name on it.

The prompt

Here is one thing that just changed in my market: [paste the article, the rate sheet line, the MLS listing, or just say it in a sentence].

I am a real estate agent in [market]. My people are [who they are].

Turn this one thing into four pieces. Same message, four rooms:

1. A TEXT to my sphere. Under 300 characters, sounds like a person, no link unless it genuinely helps. It should read like I thought of them, not like a broadcast.
2. An EMAIL to my database. Subject line plus body. Lead with what it means for them, not with what happened. Short paragraphs, one idea each.
3. A CAROUSEL, 5 slides. Slide 1 is the hook and it has to be readable in two seconds. Slides 2 through 4 each carry one idea. Slide 5 tells them what to do next.
4. An INSTAGRAM CAPTION for that carousel, in my voice, ending with a line that tells people exactly who to send it to.

Rules:
- Every claim has to trace back to what I gave you. If you are not sure of a number, leave it out. I would rather say less than say something wrong.
- Answer "so what does that mean for me" in the first two lines of every single piece. Nobody cares what changed, they care what it costs them.
- No hype, no exclamation points, no emojis.
- Then tell me the one piece you would actually send if I only had time for one.

How to run it

What it does

You describe the one thing people would trade an email address for. Claude builds you a one-page capture form as a single file: headline, one or two fields, a button, and it works on a phone. You paste the code into your website, and from then on every person who fills it out lands somewhere you can reach them again.

Why it's worth it

You can post every day for a year and still own nothing. The follower belongs to the platform. The email address belongs to you, and it is the only piece of an audience that survives an algorithm change, a hacked account, or a platform deciding your posts are worth less this quarter.

This is also the missing half of the card above. Turning one market change into four pieces is good. Turning it into four pieces that all point at one page where someone can raise their hand is the difference between reach and a pipeline.

The prompt

Build me a one-page email capture, as a SINGLE self-contained HTML file I can paste into my website. No frameworks, no external files, everything in the one file.

What people are signing up for: [the guide / the neighborhood report / the open house list / the monthly market note].
Who they are: [first-time buyers in X / homeowners in my farm / whoever].
My branding: [name], [brokerage], [DRE #], [phone], colors [x and y].

Build it with:
- A headline that says what they get, not what I do.
- Two fields, first name and email. Nothing else. Every extra field costs me signups.
- One button, and the button says what happens next, not "submit."
- A one-line note under the form telling them what I will and will not send.
- Reads well on a phone first. Most of my traffic is a thumb.
- Send the form data to [where it goes - my CRM form endpoint, or a Google Sheet, or tell me my options].

Then tell me, in plain language, exactly where to paste this on my site and what to test before I share the link.

Where the names actually go

The part people skip

Have something to give. A page that says "sign up for my newsletter" collects almost nobody. A page that says "the one-page guide to what the new rule means for your HOA" collects people, because it is worth the trade. Build the thing first, then build the page for it. The card above is how you build the thing.

If you are going to text anyone who fills this out, say so on the form, in writing, right where they type the number. Consent has to be collected at the moment they hand you the contact information, and an email opt-in is not permission to text.

What it does

You record yourself talking — in the car, at your desk, one take, flubs and all. AI listens to the recording, finds the takes worth keeping, and cuts the rest. Every cut gets masked with a small zoom change so it reads as an intentional edit instead of a jump. Then it burns in the captions, synced word by word to your voice, puts a written hook over the opening seconds, and closes with your call to action.

Why this one matters

The talking-head video is the one everybody agrees they should be posting and almost nobody posts. It's not the recording that stops you — it's the hour of editing after. This removes the hour. You do the one thing AI can't: be you on camera. It does everything after.

Where to start

Record one take on your phone this week — 60 to 90 seconds on the question buyers keep asking you. Don't restart when you flub, just say the line again and keep going. That's the raw material the edit is built from, and it's the version I'll walk through live.

This is the deeper lane — the edit runs in Claude Code, the same lane as Mission Control below. If you're not there yet, the Reel card on the AI tools page gets you most of the way with just the app: cut plan, captions, cover, and post copy from one conversation.

What it does

AI takes the wheel of a browser tab you're already logged into and does the clicking. Not a new app, not an integration, not a subscription. The same screens you use, operated for you. Mine pulls MLS searches and exports them, and loads video emails into BombBomb, which is a job I had been doing by hand every single week.

Why it's worth it

Almost every tool an agent pays for has no way to talk to anything else. The MLS doesn't hand your data to your CRM, your CRM doesn't hand it to your email tool, and the glue in between has always been you, at a keyboard, at 10pm. This is the first thing I've used that actually fills that gap, because it works the way you work: through the screen.

Where it earns its keep

The honest caveats

It breaks when a page changes. A vendor ships a redesign and your setup needs a nudge. It is slower than you, step for step, which stops mattering the moment it's running at 2am. And it is logged in as you, so treat it exactly like handing your laptop to an assistant: watch the first few runs, and never point it at anything that sends, pays or signs.

Check your MLS rules before you point it at the MLS. Data licensing and scraping terms are real, they vary by board, and "the AI did it" is not a defense. Pulling your own permitted searches on your own login is a different thing from harvesting the database, and you need to know which one you're doing.

What it does

You give AI something you pay for or something you run, and instead of asking "is this good," you ask it to make the case for cutting it and show the evidence either way. You get back what you're actually using, what you're actually getting, what's genuinely valuable in there, and a keep-or-cut verdict with a date on it.

Why it's worth it

Two audits I ran in the last week changed real decisions. One was a training membership I'd been paying for monthly. The audit found I had gotten through about 2% of it, that finishing it was roughly a hundred hours of video, and that the real value wasn't the videos at all but a library of downloadable files I could keep forever. That flipped the decision from "keep paying and try harder" to "take the files this weekend, then cancel." I would not have found that by feeling guilty about it for another month.

The second was an audit of my own automations, and the finding was that I had built roughly three times more of them than I actually had running. The fix wasn't building more. It was cutting.

This is the use case nobody teaches, because every AI demo is about making more. The highest-leverage question you can ask is what to stop.

The prompt

I want an honest audit of [the thing - a subscription, a CRM, a lead source, a marketing spend, a system I run]. It costs me [$X/month] and [roughly how much time per week]. It renews on [date].

Do not be encouraging. Your job is to build the case for CUTTING it, and then tell me honestly whether that case holds.

Give me:
1. What I'm actually getting for the money - the specific, provable value, not the sales page.
2. What I'm actually using. Be blunt about the gap between what I bought and what I touch.
3. What's genuinely valuable in here that I'd lose, and whether I could keep it another way.
4. What it's costing me beyond the money - my time, my attention, the thing I'm not doing instead.
5. The verdict: keep, cut, or downgrade. One recommendation, not three options.
6. If the verdict is cut: exactly what I should take out of it first, and by when.

If you don't have enough information to answer any of these, tell me what to go look up. Don't guess and don't pad.

Your version

Run this on your CRM, your paid portal leads, your lead-gen subscription, your photographer, your ISA, your farm mailer. Anything with a monthly number on it. Do it two weeks before the renewal date, not two days after. The only reason a bad subscription survives is that the renewal is always a surprise.

The one line that makes it work is "do not be encouraging." Without it you'll get a balanced summary that lets you keep everything.

What it does

You sit down once and dump every unfinished thing out loud: the escrow you're worried about, the person you owe a call, the thing your broker asked for, the paperwork, the thing you keep meaning to fix on your website. AI sorts it into what's actually urgent, what's a two-minute task, what needs a decision from you, and what you should just kill. Then it asks you the questions you've been avoiding.

Why it's worth it

I did one of these last weekend and it took most of a morning. It surfaced somewhere around sixty open loops, and a real number of them were things I had genuinely forgotten existed. That's the part worth noticing. It isn't that I was behind on sixty things. It's that some of them had been quietly rotting because nothing in my week was ever going to surface them.

For an agent the version of this is simple: your head is not a database, and the loops it drops are the expensive ones. The client who never got the follow-up. The referral you never thanked anyone for.

The prompt

I'm going to talk for ten minutes and dump every open loop in my business. Deals, people, paperwork, things I said I'd do, things I've been avoiding. It'll be out of order and I'll repeat myself. Don't interrupt and don't clean up my language.

When I'm done, give me:
1. NEEDS ME TODAY - anything with a deadline or a person waiting on me. Ranked.
2. TWO MINUTES EACH - the small things I can clear in one sitting.
3. NEEDS A DECISION - things that aren't tasks, they're choices I've been putting off. State the actual choice for each one.
4. KILL THESE - things I've been carrying that I'm honestly never going to do. Say so plainly.
5. What I mentioned in passing and then moved on from too fast. That's usually the important one.

Then ask me the 5 questions you'd need answered to make this list actually accurate.

How it works

Say it, don't type it. Nobody types their way to sixty loops. And block the time honestly, because a real catch-up pass is a morning, not a coffee break. The payoff is that you only owe yourself one of these a quarter if you run the smaller weekly version of it after.

What it does

A running note with one line per AI win: the date, what happened, whether it is worth repeating. Ten seconds to write. Then once a week you hand the log back to AI and ask what it sees. Your own week becomes the curriculum.

Why it's worth it

The agents who compound with this stuff are not smarter. They keep score. I log mine, and a weekly review of the log is what caught me rebuilding the same package by hand three weeks running; that chore is a routine now. The rule of thumb: anything that shows up three times gets promoted to a scheduled task.

The weekly mining prompt

Read my leverage log below. Three questions:

1. What did I do by hand three or more times that should become a scheduled routine?
2. Which win saved the most time, and what is the next-size-up version of it?
3. What am I doing that I should stop doing entirely?

My log (format: date, what happened, worth repeating?):
[PASTE YOUR LOG]

Keep the log inside your Chief of Staff project and it compounds twice: the weekly review gets smarter, and your chief of staff learns what actually works for you.

What they are

Everything I demo at this bootcamp runs on systems I actually use. These two are written down completely: what the system does, why the design matters, the exact prompts, and the compliance lanes to stay inside. Each one works two ways. Use my version and I'll set you up, or hand the doc to Claude Code and build your own.

The shelf