◆ THE STANDARD ENGAGEMENT ◆

YOUR IN-HOUSE
AI CREATIVE
SYSTEM.

:: INSTALLED IN 30 DAYS · CALIBRATED FOR 60 MORE ::
» THE SHAPE «

Three months. One sprint, two calibration months. $14,000 total. The same system I run inside my own agency — brand bibles, tagging pipeline, brief agents, prompt assembly, QC loops — installed in your repo and tuned to the way your team works.

3-month engagement 4 weekly calls in month 1 Slack-embedded throughout Kit drops for the life of the engagement
▶ INQUIRE
M1 is the build sprint. The rest runs on light calibration.
CHAPTER I · THE BET

Three reasons this engagement is shaped this way.

▶ THESIS 01

Volume + diversity is the unlock

One perfect ad doesn't move the needle. 14 unique statics a week, with the right spread of personas, angles, and formats, does. The algorithm needs the variance. The system was built around feeding it.

In my own agency, the AI statics now outperform what our editors ship. Not by a little.

▶ THESIS 02

Install over teach

If you bought a course, you'd spend three weeks figuring out the parts I already broke. The work that matters is in the markdown files, the asset templates, and the agent loops — tuned to your way of working without re-litigating every decision.

This engagement skips the teaching and goes straight to building it with you.

▶ THESIS 03

The cookbook compounds

Every brand or client you onboard after install gets the same brand bible flow, the same tagging pipeline, the same QC pattern. Each one teaches the system something the next one benefits from.

One install. Then it pays you back every time you ship a new round.

CHAPTER II · THE STACK

What gets installed inside your repo.

Three tranches. Foundation lands first because nothing downstream works without it. Production and Optimization layer on as the system starts shipping.

M1

Foundation

▸ INSTALLS WEEKS 1-2
  • Meta API tagging pipeline — every ad in the account auto-tagged by persona, angle, emotion, asset type, format
  • Category gap analysis — where you're over- and under-indexing vs. your category
  • Historical winner analysis — surfaces what worked, why, and feeds it downstream
  • Brand bible + spec cards, generated from a brand's site in 30 minutes
  • The 50-universal-personas framework so analysis is comparable across accounts
M1
↓
M2

Production

▸ INSTALLS WEEKS 3-6
  • Brief-generation pipeline — 10 copy agents iterate each brief until it scores 90+
  • Brief-to-prompt converter — turns approved briefs into the structured prompt format GPT-Image and Nano Banana actually want
  • AI static generation — fal.ai integration, variant generation, folder organization, cost tracking, all from inside Claude Code
  • 15 asset-type markdown files (before/after, social proof, founder story, features/benefits, us-vs-them, and more)
  • Visual style cards + brand spec cards in the prompt assembly
M2
↓
M3

Optimization

▸ INSTALLS WEEKS 7-12
  • QC agent loop — reviews each generated static against a 50-point checklist, regenerates until it passes
  • Human-feedback markdown updater — when a strategist flags an issue, the relevant markdown file gets updated so the system stops repeating it
  • Brand-voice agent — trained on each brand's winning ads, makes every future brief sound like them
  • Change-log workflow — read-write log so your team can flag fixes without stepping on each other's edits
  • Handoff doc + "running it without me" checklist at month 3 close
CHAPTER III · HOW WE WORK

Sprint in month 1. Calibration in months 2 and 3.

Higher cadence in the build month. Lower cadence after, when the system is running and just needs nudging.

CHAPTER IV · INVESTMENT

One line item. Three months.

$14,0003 months committed · billed monthly · USD
MONTH 01 · SPRINT
$6,000
MONTH 02 · CALIBRATE
$4,000
MONTH 03 · CALIBRATE
$4,000

Heavier in month 1 because that's where the build happens. Lower after because the system runs itself with light calibration once it's in. 3-month minimum committed up front. No long-term lock-in beyond it.

What happens after month 3?
Optional ongoing collab at $2,500/mo — Slack access, kit drops, and one 60-min call per month. Month-to-month, 30 days notice to cancel. Kit drops and dashboard access end on cancel. You keep every file already on your machines.
FINE PRINT

What's not in the box.

So nobody's surprised in month 2. If any of these become important, we scope them separately.

  • Media buying or ad-account management — your team keeps that
  • Final QC on shipped ads — your humans stay in the loop
  • Copywriting on your behalf — this makes your team faster, it doesn't replace them
  • Work for direct competitors of your active brands — mutual exclusivity clause in the SOW
CHAPTER V · KICKOFF

From signed to first AI statics shipped in 30 days.

The sprint pace. Each item below is what's true at the end of that week.

▶ DAY 0

Signed + Stripe.

SOW countersigned, first invoice paid. Slack channel created. Kickoff call scheduled inside 48 hours.

▶ WEEK 01

Access + first brand bible.

Meta API access + tagging dashboard provisioned. Brand bible and spec cards drafted from your first test brand's site. Repo skeleton committed.

▶ WEEK 02

Foundation workflows installed.

Tagging pipeline, gap analysis, and historical winner analysis live in your repo. First gap-analysis dashboard for the test brand lands in Slack.

▶ WEEK 03

Production pipeline live.

Brief-generation agents, prompt converter, and fal.ai static generation all running. First test briefs go through the 10-agent scoring loop.

▶ WEEK 04 · SPRINT END

First AI statics shipped to a real brand.

14 statics generated, QC'd, and delivered. Sprint cadence ends. We move to bi-weekly + Slack for months 2-3.

▶ MONTHS 02-03

Calibration. Optimization tranche. Handoff.

QC agent loop, human-feedback markdown updater, and per-brand brand-voice agent installed. Kit drops as I ship new asset types and model integrations. Month 3 closes with a "running it without me" checklist.

CHAPTER VI · QUESTIONS

The ones that come up before signing.

Is this a fit for an agency, a brand, or both?
Both. The system was built inside an agency, so the workflows assume multi-brand reuse from day one — but in-house brand teams running heavy paid social get the same install. The shape of the engagement doesn't change.
What does my team need to know going in?
Comfort with Claude Code, GitHub, and a paid Meta account is enough. No prior AI image-gen experience required. If your team has shipped a few apps or built internal tools, you're set. If not, we can do a short pre-engagement onboarding — usually adds a week before the sprint starts.
Can we do this in less than 3 months?
No. The Optimization tranche needs real shipped work to calibrate against — which only happens after Foundation and Production are in. Compressing it would mean shipping a system that hasn't seen real briefs hit it. 3 months is the minimum that produces a system that runs without me.
What about model costs (Claude, fal.ai, etc.)?
Pass-through, on your accounts. Typical run-rate during install is $200–$600/mo across Claude API + fal.ai + GPT-Image, depending on volume. The pipeline is built to track it from inside Claude Code so you see the cost per ad.
Do we own the files?
Yes. Everything installed lives in your repo. You keep it whether you continue past month 3 or not. The only things that end on cancel are the proprietary tagging dashboard access and the kit drops.
What if we want a more bespoke scope?
Email me. The $14k engagement is the standard shape because it's the one that consistently produces a working system — but enterprise scopes (multi-team install, custom integrations, white-label tooling) get scoped separately. Same intake either way.
▶ READY TO START? ◀

Let's get the
first statics shipped.

If this is a go, I send the SOW + Stripe link inside 24 hours. Kickoff call scheduled inside 48. First AI statics in your account inside 30 days.

EMAIL WILL ▶ SCHEDULE KICKOFF
Will Sartorius
— Will