← ALL PLAYBOOKS
── PLAYBOOK · MARKETING
✓ APPROVED

Run the content engine on a real cadence

Content that talks to nobody ranks for nothing, and one great post that never repeats is a fluke, not an engine. Build from real buyer language, publish on a rhythm, and grow the list that actually opens it.

[ BUILT GTM ]

Run the content engine on a real cadence

Solvethe problem worth solving
Problem · 01Marketing

Content that talks to nobody ranks for nothing, and one great post that never repeats is a fluke, not an engine.

Build from real buyer language, publish on a rhythm, and grow the list that actually opens it.

Stackthe workflow, box by box
Claude01
Design a customer-interview study and turn transcripts into messaging.
Get the exact words buyers use.
Connect to analyze
AI
Claude02
Hand a writer a brief they can start from without a meeting.
Hand writers a brief they can start from, on a repeatable weekly rhythm.
Connect to analyze
AI
Marketo03
Build a list worth having, not just a big one.
Build a list worth having, not just a big one.
Powers up with
AI
Claude04
Strip the AI tells and make it sound like you.
Strip the AI tells and rewrite the published piece in your voice before it goes out, so the cadence never costs you authenticity.
Connect to analyze
AI
Splithow control passes: agents branch left, humans right
HUMAN + AI, IN THE LOOP
How control passes.
AgentsHuman
Agent01
Design a customer-interview study and turn transcripts into messaging.
Claude runs it.
Agent02
Hand a writer a brief they can start from without a meeting.
Claude runs it.
Agent03
Build a list worth having, not just a big one.
Marketo runs it.
Agent04
Strip the AI tells and make it sound like you.
Claude runs it.
The skills run the work. You stay in the loop on the calls that need judgment.
Outputwhat the workflow produces
OUTPUT · 01

The real language

OUTPUT · 02

Writer-ready briefs

OUTPUT · 03

A growing audience that opens what you send

OUTPUT · 04

Every piece rewritten in your voice before it ships

Outcomethe result it drives
OUTCOME · 01

$2M+ influenced

The same content system that earned that number: buyer language turned into briefs, then a publishing cadence that keeps shipping and growing the list.

Built GTM
── 01 / WHY RUN IT
RUN THIS AND YOU CAN
The real language
Writer-ready briefs
A growing audience that opens what you send
Every piece rewritten in your voice before it ships
── 02 / THE RUN, STEP BY STEP

The workflow that solves it, one step at a time.

Each step is the plain question you are already asking. The skills answer them in order, one handing its receipt to the next.

1✓ TESTED
Design a customer-interview study and turn transcripts into messaging.

Who to talk to, a non-leading interview guide, and how to turn transcripts into positioning and messaging inputs.

YOU GETThe interview slate, the non-leading guide, and transcripts-to-positioning.
OPEN THE SKILL →
2✓ TESTED
Hand a writer a brief they can start from without a meeting.

Turns a keyword or topic plus an audience into a writer-ready brief that kills the back-and-forth.

YOU GETSearch intent, the angle, the outline, must-cover questions, internal links, and one CTA.
OPEN THE SKILL →
3✓ TESTED
Build a list worth having, not just a big one.

The subscribe offer, the growth loops, the content rhythm, and the metrics that matter beyond list size.

YOU GETThe subscribe offer, the growth loops, and engagement-first metrics.
OPEN THE SKILL →
4✓ TESTED
Strip the AI tells and make it sound like you.

Removes the hedging, the rule-of-three, and the sycophantic openers, then rewrites the draft in your voice.

YOU GETThe AI-tell checklist and the voice-rewrite pass.
OPEN THE SKILL →
WHERE YOU LAND

The real language, writer-ready briefs, a growing audience that opens what you send, and every piece rewritten in your voice before it ships.

EVERY STEP, TESTED AND PASSED
EVAL RESULTPASS4/4 dimensions
HOW WE EVAL →
Skills resolve
Structure + proof
Example chat
Quality judge
  • All 4 chained skills resolve to real, scored skills.
  • Has a problem, an outcome, 2+ steps, and proof from a real build.
  • Ships an example chat showing the play run in Claude.
  • Reads in plain operator voice, grounded in a real build.
Last eval run 2026-08-05
DEEP EVAL · PASS
THE STANDARD →

We did not just check the structure. A judge read this play against the full text of every skill it chains (composition), then ran it on a real scenario end to end (simulated). It passed both. Test scenario: Sam, Content Marketing Manager: blog gets traffic that doesn't convert, wants to fix it at the root and build a real publishing cadence.

── 03 / SEE IT RUN

Watch the skills answer in order.

Describe your situation in plain language. The right skill fires on its own and hands its receipt to the next.

EXAMPLE CHATSam, Content Marketing Manager, running the loop in one sitting
S
Our blog gets traffic but none of it converts. I think we're writing about things buyers don't actually care about. How do I fix that at the root?
S
Step 1· Customer Research
Let's start from the buyer's own words instead of guessing. I built an interview slate of customers to talk to, a non-leading guide so you don't put words in their mouth, and a way to turn the transcripts into the exact phrases they use into positioning inputs.
Receipt
Research plan: 12 customers to interview, a non-leading guide, and a transcript-to-messaging method that surfaces the real phrases buyers use.
S
Ran five of those calls. Buyers keep saying 'I can't tell which leads are worth my time.' I want a post on exactly that. Can you brief it out?
S
Step 2· Content Brief
I turned that phrase into a writer-ready brief: the search intent behind it, the angle, an outline, the must-cover questions, internal links, and one CTA. A writer can start without a kickoff meeting.
Receipt
Brief built on 'which leads are worth my time,' with a 6-section outline, 5 must-cover questions, and one CTA.
S
We publish but the list barely grows and half of it never opens anything. How do I build an audience that's actually worth having?
S
Step 3· Newsletter Growth
I set a subscribe offer tied to that same buyer pain, mapped a couple of growth loops off your existing content, and set a content rhythm. The metrics I picked are engagement-first, so you're not just chasing a bigger number that never opens.
Receipt
Growth plan with a lead-magnet subscribe offer and 2 growth loops, targeting engaged-subscriber growth over raw list size.
S
One more. When people ask AI tools about our space, we never come up. Can you audit our pages for that?
S
Step 4· Humanize Draft
Before each piece ships, I strip the AI tells and rewrite it in your voice: the hedging, the rule-of-three, the sycophantic opener, all gone. The cadence never costs you sounding like a person.
passvoice
tells cut9
Receipt
The published draft rewritten in your voice: 9 AI tells removed, opener and close rebuilt to read like you wrote it.
── 04 / SEE IT IN PRODUCTION

Before you run it, I ran it for real.

This workflow is genericized from a real build. Here is the number it moved, and what I actually did.

THE BUILD · AEO + GEO STRATEGY
Getting Found in the AI World
$2M+
churned win-back the same backward read surfaced
25% to 100%
share of the prompt budget working the positioning, was 25%
108 to 0
undifferentiated utility prompts, eliminated
2 to 56
Define prompts, the category ground nobody owned
WHAT I DID
01
Start with the customer, not the keyword. The same inputs that build a real ICP, customer interviews, G2 reviews, call transcripts, and closed-won patterns, are what tell you the language buyers actually use. AEO is downstream of understanding the customer; you cannot be quoted on words your buyer does not say.
02
Read attribution backward. I ran the research on how customers actually find us, why they buy, and why they stay, reading the demo and attribution data from the win back to the origin instead of crediting the last click.
03
Rewrite positioning to be quoted, not ranked. I rewrote the positioning for how buyers search now, so the answer engine repeats it. Written for the answer, not just the page, in the customer's language rather than the category's.

AEO and GEO are not SEO with a new coat of paint. The machine answering your buyer only quotes what it can source, in the buyer's own words, so start by understanding the customer, rewrite the positioning to be quoted rather than ranked, reallocate your prompt budget to Defend, Intercept, and Define, name the AI only where it earns the line, and lock the story to one versioned source. Get found where the buyer actually looks now.

Dig into the full build
05 / INSTALL THE WHOLE PLAYBOOK

One plugin. 4 skills, bundled.

The whole playbook installs as a single plugin in Claude Code, no copy-pasting 4 times. Or grab any single step above. It runs on what you paste; connect your stack to go live.

OR KICK IT OFF IN CHAT
Here is my situation: [describe your workflow or account in a sentence or two]. Walk me through Run the content engine on a real cadence step by step, and run each skill as we go.
── GET THE NEXT PLAYBOOK

One runnable workflow a week. Free.