St. Pierre AI — Content OS

System Overview

Step 1

Topics Bank

45 topics / 9 sub-pillars

→

Step 2

Weekly Ranker

Auto Sun 6pm

→

Step 3
Slack Brief
Top 10 + enriched

→

Step 4

Pick 5

Akash selects · 1/day

→

Step 5

Generator

GPT-4o carousel

→

Step 6

Post + Distribute

IG → YouTube → Retargeting

ℹ

Zero manual research. Monday brief arrives in Slack automatically. Akash picks topics, runs batch_runner.py, produces the reels. System handles everything else.

Content Pillars

Every carousel and reel maps to one of 3 parent pillars and one of 9 sub-pillars. All pillars tie back to demand gen vs. demand capture.

Better Leads

#	Sub-Pillar	What It Covers	Topics
1	AI Content	Short-form video formats, green screen system, carousel format, reaching the 97%	5
2	AI Inbox	Chatbot setup, qualification logic (project → zip → phone → urgency), filtering tire-kickers	5
3	AI Targeting	FB conversation campaign setup, Super Pixel, retargeting the 97%, $30–$50 CPL	5

Better Systems

#	Sub-Pillar	What It Covers	Topics
4	Speed-to-Lead	Instant response as #1 close-rate lever, >5 min cost, shared lead disadvantage	5
5	Pre-Appointment	Building trust before the rep shows up, confirmation sequences, authority content post-booking	5
6	Post-Appointment	Closing the quote-to-job gap, dead lead reactivation, follow-up automation	5

Better Data

#	Sub-Pillar	What It Covers	Topics
7	Dashboards	Data over gut feel, true cost per booked job (not CPL), one-dashboard ROI view	5
8	Algorithmic Loop	Closed-won sales data → Meta CAPI → trains algorithm on job value not lead volume	5
9	Backend Infra	Postgres/N8N, Super Pixel data moat, proprietary audience across 10K+ appointments	5

ℹ

Each sub-pillar has 5 topics: Tips · Primary Q · Secondary Q · Expectation · Objection. 9 × 5 = 45 carousels total.

Proof Points (rotate across pillars)

Client	Result	Best for
Riley	47x ROI	P2 lead capture stories
Ashley	$717K closed revenue	P1 authority building
Valerie	$676K + 300+ appts / 90 days	P2 volume stories
Thrasher Crawl Space	$360K quarter	P3 data / scale stories
TWF	$45K in 30 days from Messenger alone	P2 speed stories

Topics Bank

Single source of truth for all carousel and reel topics. 45 rows, versioned and scored.

File: Projects/StPierre/carousel-production/topics_bank.csv

Column	Purpose	Values
`id`	Unique topic ID	1–45
`pillar_code`	Parent pillar	BL (Better Leads), BS (Better Systems), BD (Better Data)
`sub_pillar`	Sub-pillar name	AI Content, AI Inbox, Speed-to-Lead, etc.
`bucket`	Topic bucket	Tips, Primary Q, Secondary Q, Expectation, Objection
`topic`	Full topic string fed to generator	—
`hook_angle`	Default hook framing	Pain-first, Contrarian, Proof/result-first
`featured_result`	Proof point to anchor the carousel	Riley 47x ROI, Ashley $717K, etc.
`niche`	Target niche for this topic	foundation repair, waterproofing, both
`status`	Lifecycle stage	pending, done, winner
`score`	Ranker output (max 14 before multiplier)	Float
`ranking_notes`	Score breakdown per dimension	proof=2\|pillar=3\|brain=1\|age=1

⚠

Status = winner applies a ×2 multiplier in the ranker — use it for topics that performed well to resurface them with variation.

Weekly Ranker

Scores all pending topics across 6 dimensions. Writes scores back to CSV. Returns top 10 + reserve 5 with diversity cap.

File: ranker.py · Run: python ranker.py or auto via weekly_brief.py

Scoring Dimensions (max 14 before multiplier)

Dimension	Points	Logic
Proof strength	+2	featured_result contains real $, %, or x figure
Pillar priority	P2=+3, P1/P3=+2	P2 highest — most direct revenue signal
Brain match	>0.75 sim=+3 · >0.5=+1	Semantic search vs video_notes — content you've studied
Winner multiplier	×2	Applied to entire score if status = 'winner'
Age bonus	+1	Pending > 14 days without being ranked
Recency penalty	−2	Same pillar produced in last 7 days

Diversity Cap

Max 2 topics per pillar in the top 10. Prevents the brief from being dominated by a single pillar.

ℹ

Run python ranker.py --dry-run to preview scores without writing to CSV. Brain semantic search is skipped in dry-run (fast mode).

Content Standard — Agent KB

The binding knowledge base for all SP AI content generation. Every piece of content — reel, carousel, YouTube video — must conform to this standard.

The Rule of One

Dimension	Answer
Avatar	Foundation repair + basement/crawl space waterproofing contractors — $1M+/yr
Problem	Inconsistent months — caused by demand capture marketing fighting over the finite 3% already price shopping
Solution	Demand generation — short-form video reaching the other 97% before they start shopping. Pre-qualified appointments. Pay per result.
Funnel	Organic only: IG Reel → YouTube ↔ Call Funnel
Focus	1 year. Dominate organic social (FB/IG + YouTube).

⚡

No lead magnets. No Skool. No paid ads to generate clients. Organic only.

Core Positioning: Demand Gen vs. Demand Capture

This is the intellectual foundation of all content. Every pillar, hook, and case study connects back to this.

Demand Capture — The Villain

Google, Angi, Thumbtack, HomeAdvisor, dealer networks
Everyone fishing in the same pond — the 3% already price shopping
Same lead sold to 4–5 contractors
Finite pool, price wars, race to the bottom
Dealer networks: high % fees, non-competes, can't touch your own site

Demand Generation — The Solution

Short-form video in exact neighborhoods — before homeowners start searching
Goes after the other 97% — effectively infinite pool
Homeowner reaches out first, to you only
Instant response → qualification → pre-qualified appointment
Contractor stops competing and starts being chosen

ℹ

The punchline: "Most contractors are stuck fighting over the same 3% of homeowners already price shopping. We go after the other 97% first."

Brand Voice — The Systems Consultant

What Akash is: A consultant who builds the marketing stack, data stack, tech stack, and sales infrastructure to grow contractor revenue predictably. Not a contractor who ran a foundation repair business. Lane: better leads, better systems, better data — not hiring/managing reps.

Element	Rule
Tone	Casual, slightly profane, self-deprecating but authoritative. Reports findings from 150+ contractors.
Key phrases	"Inconsistent months" · "The 3% trap" · "Demand capture vs. demand generation" · "Quote-to-job gap" · "Pre-qualified appointments"
Address audience as	"Brother" or "Man" — never "Hey guys" or "folks"
Never	Open with "Hey" · Close with a hard CTA or engagement beg · Sound like a LinkedIn post · Over-explain
Angus Sewell formula	[Audience ID: "You might be like me where you..."] + [Credibility: "I manage ads for 150+ foundation repair businesses..."] + [Insight] + [Story] + [Casual close]

The 9-Pillar Framework (3 Parents × 3 Sub-Pillars)

Every piece of content maps to one parent pillar and one sub-pillar. All pillars tie back to demand gen vs. demand capture.

Better Leads

#	Sub-Pillar	What It Covers
1	AI Content	Short-form video formats, conversation campaigns, green screen system, carousel format, creating content that reaches the 97%
2	AI Inbox	Chatbot setup, qualification logic (project → zip → phone → urgency), filtering tire-kickers before the sales team
3	AI Targeting	FB page/campaign setup, Super Pixel, retargeting the 97%, $30–$50 CPL benchmarks, connecting data to Meta

Better Systems

#	Sub-Pillar	What It Covers
4	Speed-to-Lead	Instant response as #1 close-rate lever; what happens at >5 min; shared lead disadvantage
5	Pre-Appointment	Building trust before the rep shows up; confirmation sequences; authority content post-booking
6	Post-Appointment	Closing the quote-to-job gap; dead lead reactivation; follow-up automation

Better Data

#	Sub-Pillar	What It Covers
7	Dashboards	Managing by data not gut feel; true cost per booked job (not CPL); one-dashboard ROI view
8	Algorithmic Loop	Feeding closed-won sales data back to Meta via CAPI; training the algorithm on job value not lead volume
9	Backend Infra	Postgres/N8N as the digital foundation; Super Pixel data moat; proprietary audience across 10K+ appointments

ℹ

CPL benchmark: $30–$50 pre-qualified on conversation campaigns vs. $150–$300 for a shared Angi lead. Use this as an anchor in content.

The Offer

⚡

Guarantee: 5 closed jobs in 6 weeks. Miss = we keep running campaigns at our cost until you hit 5. Not a refund. Not money-back. We don't stop until the engine produces.

Scoreboard: 45 qualified leads → 33 quotes → 5 closed jobs.

Tier	Price	Structure	Guarantee
Primary (PIF)	$9,000	Paid in full at signing · $5.5K fee + $3.5K media	5 closed jobs / 6 weeks
Downsell 1 (weekly)	$12,000	$3K + 6 × $1,500 · $8.5K fee + $3.5K media	5 closed jobs / 6 weeks
Downsell 2 (salvage)	$6,000	$3K + 6 × $500 · lead delivery only · 6 of 9 pillars	30 qualified leads / 6 weeks
Ongoing (after 6w)	$150 / qual lead	~5+/wk ≈ $750/wk · no retainer · cancel anytime	—

Unit Economics — Two Different CACs (always label)

Client-facing (what we sell)	Value
Client spend	$9K (PIF) – $12K (weekly)
Jobs delivered	5
Client CAC (job acquisition)	$1,800 – $2,400 / job
Revenue per 5 jobs ($8K–$15K avg)	$40K – $75K
Gross profit @ 50%	$20K – $37.5K
ROI in 6 weeks	1.7x – 3.1x

SP-internal (do NOT publish)	Value
SP CAC (client acquisition)	$1,500
SP fee per client	$5,500 (PIF) / $8,500 (weekly)
SP LTGP / CAC	3.7x – 5.7x (before delivery cost)

⚠

Naming rule: "Client CAC" = job acquisition cost on contractor's P&L. "SP CAC" = client acquisition cost on SP's P&L. Never use bare "CAC" in client-facing content — it mixes the two and triggers price pushback.

Niche guarantee: Foundation repair / Basement waterproofing / Crawl space = 5 jobs / 6 weeks (canonical).

Exclusivity: One contractor per area. Working with you locks out your competitor.

MRR reconciliation: 25 lifetime closes by Dec 31, 2026 ≠ 25 active recurring. Expected mix: ~11 active ongoing at ~$3.3K/mo (post-6-week retainers) + 14 one-time builds or churn → ~$37K MRR at year-end (per Root Doc WIG).

ℹ

Full offer/pitch doc: eyefly-sp-offer-pitch-docs.pages.dev — sales scripts, downsell language, objection handling, discovery framework.

Case Studies — Always Pair Number with Mechanism

Client	Result	ROI	Mechanism
Riley — Custom Concrete Curb	$650K+ on <$14K spend	47x	Demand gen + quote-to-job gap closed with AI follow-up
Ashley — Vesta Foundation Solutions	$717K / 12 months	15x	AI inbox + one dashboard tracking every channel to booked job
Valerie — Redeemers Group	$676K / 12 months	15x	80% dead leads → 80% qualified via AI inbox reactivation
Thrasher Foundation Repair	$360K / 6 months	—	Authority content + automated lead transfer
TWF Construction (Virginia)	$45K / first 30 days	—	Owner never opened ChatGPT — full system ran without him
Fleet total	$14M+	—	150+ contractors · 10K+ appointments · Same system, different markets

Weekly Brief (Auto-generated)

Every Monday at 9pm ET, weekly_brief.py scores the top 10 topics and posts to Slack #akash-notes with hook angles, contrarian takes, and Slide 1 drafts. Pick 5 topics, run batch_runner.py.

04.5

Angle × Mechanism — Hook Bank

18 pain-point angles + the AI mechanism that solves each. Every row = a slide-1 hook waiting to happen. Pair with topics_bank.csv for weekly ranker rotation. Each angle is the "without" the buyer wants; the mechanism is how the system delivers it.

#	Angle (the "without")	Mechanism
1	Without creating content yourself	AI generates daily carousels + reels + captions. Record one Saturday/month. AI handles ideation, scripts, distribution.
2	Without hiring or managing marketing staff	AI is the marketing manager — content, ads, qualifying, follow-up, attribution. No agency, no in-house hire.
3	Without learning AI yourself	White-glove 6-week install. You don't touch a prompt, pixel, or Meta dashboard.
4	Without buying shared leads (Angi / HomeAdvisor)	AI Messenger delivers exclusive leads. No 5-way bidding. Homeowner reaches out to you, period.
5	Without office manager chasing tire-kickers	AI Inbox qualifies on 4 questions: project · zip · decision-maker · urgency. Only real estimates land on the schedule.
6	Without a bigger ad budget	$500/wk media baked into the build. AI optimizes spend toward cost-per-booked-job. Same dollars, 2–3x more booked work.
7	Without a website	AI Messenger replaces the site. Click ad → DM thread → qualified + booked. No landing page.
8	Without doing sales calls yourself	Bot pre-qualifies before the rep drives out. Reps walk into 60–75% show-rate appointments.
9	Without long contracts or risk	5 jobs in 6 weeks. Miss = we keep paying for ads until you hit 5. Not a refund.
10	Without any tech skills or setup work	6-week build. Meta pixel, Messenger bot, CRM/GHL wiring, dashboards — all done for you.
11	Without spending on Google Ads	Meta + AI Messenger outperform Google. Lower CPC, higher intent, exclusive leads. $30–$50 CPL.
12	Without begging for referrals	Predictable inbound pipeline. 45 → 33 → 5 scoreboard. Calendar doesn't ride on the phone ringing.
13	Without a $7K/mo marketing manager	One $9K PIF replaces the role for a full year.
14	Without BNI, chamber, or networking	System runs while you sleep. No 7am Tuesdays.
15	Without door-knocking or yard signs	Inbound replaces outbound grind. Crews show up to booked work, not chase work.
16	Without renting growth from an agency forever	After 6 weeks, you own the entire engine. Pixel · bot · dashboard · audience yours.
17	Without training Meta on the wrong customer	Closed-won data → Meta CAPI. Algorithm learns what a real $9K job looks like, not what a tire-kicker looks like.
18	Without flying blind on what's working	One dashboard. Cost per booked job (not CPL). Real numbers, not "your ads are doing great" bullshit.

⚠

Avoid "guaranteed" framing in carousels. Meta/IG flag aggressive guarantee copy. Use "system designed to produce" or "we keep paying for ads until you hit 5" instead — reads bold rather than promotional.

Operator-language cheat sheet: "crew days filled" > "marketing automation" · "payroll anxiety" > "lead generation" · "cost per booked job" > "ROI dashboard".

Carousel System

8-slide Instagram carousel. 1080×1350px portrait. Green screen zone lower 35% for talking head. Text/visuals upper 65%.

Generator: generator.py --topic-id N · Batch: batch_runner.py --topic-ids 1 5 12

8-Slide Structure (strict — do not deviate)

HOOK

Scroll-stop headline + sub. Curiosity gap or bold claim.

ENEMY

Name the villain. Shared leads, cold calling, form fills, no AI.

PIVOT

"AI changes this entirely for home service businesses."

PROOF

Client result with specific numbers. Real $, real ROI.

STEP 1

Mechanism step 1. Simple, visual.

STEP 2

Mechanism step 2.

STEP 3

Mechanism step 3.

CTA

Comment KEYWORD to get [thing]. Specify what they'll receive.

Copy Rules

Headline: max 7 words, punchy
Body: max 2 sentences, conversational
Every slide has one visual prompt (Higgsfield / AI image gen)
Every slide has one voiceover cue (spoken tone)
No corporate speak, no hedging, no "just wanted to check in"
No AI-zesty enthusiasm or filler warmth

Generator Output

JSON file in outputs/<id>_<slug>.json — includes slides array, caption, hashtags, production notes. Status auto-updated to done in topics_bank.csv after generation.

Reel Format — @angus.sewell Model

Canonical video style for all St. Pierre AI reels. No exceptions. If it reads like LinkedIn, rewrite it.

Format Spec

Setup

Talking head, selfie cam, home office. No music, no b-roll, no captions.

Length

60–90 seconds max.

Scroll-stop

Bold contrarian text overlay written before the script. This does the heavy lifting.

Hook

"You might be like me where you [exact pain]…" — audience identification first.

Cred frame

"I manage ads for X home service businesses — here's what I'm actually seeing…"

Body

Numbered list. Each point gets a bold title-card text overlay. Feels like a masterclass, costs zero production.

Casual sign-off. No hard CTA. "Good luck, my dudes" energy.

Voice

Casual, contractions, occasional profanity. Direct. Zero polish theater. Short punchy sentences.

Never Do

Start with "Hey guys"
End with "smash that like button" or any engagement beg
Use music or b-roll (pure talking head only)
Over-explain — trust the audience to keep up
Sound scripted — read aloud test mandatory

Infrastructure

generator.py

Single carousel generator. Calls GPT-4o via brain.ask(). Saves JSON to outputs/. Marks topic done in CSV.

Production core

batch_runner.py

Queue processor. Run with --topic-ids 1 5 12 after picking from the brief. Processes in sequence.

Production core

ranker.py

6-dimension scoring engine. Writes scores back to CSV. Brain semantic search for +1/+3 boost. Dry-run skips brain.

Ideation

weekly_brief.py

Enriches top 10 with GPT-4o-mini. Posts to Slack #akash-notes. Saves markdown locally. Monday 9pm ET auto.

Ideation · Scheduled

topics_bank.csv

45 topics. 9 sub-pillars × 5 buckets. All scored weekly. Source of truth for all carousel/reel production.

Data

yt_discovery.py

Auto YouTube search → transcript → brain.video_notes. Currently DISABLED. Manual links only — drop in youtube-summarizer.

Brain input · Disabled

AI Models Used

Task	Model	Why
Carousel copy (8 slides)	GPT-4o	Full context, best instruction-following for structured JSON
Brief enrichment (hook / contrarian / slide 1)	GPT-4o-mini	Fast, cheap — 30–120 token outputs per call
Brain pattern matching	pgvector	Semantic search over brain.video_notes

brain.video_notes — Knowledge Base

Transcripts and summaries from manually-submitted YouTube videos feed the ranker's brain match score. Richer brain = more differentiated topic scoring. Add new videos via youtube-summarizer skill in Claude.

⚠

Current brain state: 71 videos ingested. Most are AI tools / Claude automation — limited crawl space-specific content. Watchlist v2 targets contractor FB ads, Messenger lead gen, appointment funnels, and high-ticket home service content.

Distribution Funnel

Organic only. No lead magnets. No ManyChat. No paid ads to generate clients. Content builds authority → YouTube closes the gap → retargeting handles follow-up automatically.

60s IG Reel or 8-Slide Carousel

Bold contrarian text overlay → audience ID hook → single insight. Drives to profile.

Profile → YouTube

Reel creates curiosity. Profile bio drives to YouTube for depth. One video per sub-pillar, 5–7 min Loom-style.

Retargeting (Autopilot)

50%+ reel viewers → retargeted on IG/FB. 30%+ YouTube viewers → retargeted on YouTube. Pixel handles it.

No manual follow-up required — algorithm does the follow-up

Booking Page

YouTube description link → call booking page. Warm prospect books directly — no DM qualification loop.

Close at $9K PIF (primary)

Primary: $9K paid in full. Downsell 1: $12K weekly ($3K + 6×$1,500). Salvage: $6K lead-only. Ongoing after week 6: $150/qualified lead, no retainer.

Client CAC $1,800–$2,400/job · SP CAC $1,500/client · SP LTGP/CAC 3.7x–5.7x · One contractor per area

⚡

No lead magnets. No Skool. No paid ads to generate clients. Organic only for 12 months. Every piece of content drives to YouTube → booking page. Retargeting handles follow-up automatically.

Content → Revenue Timeline

Phase	Weeks	Focus	Expected closes
Warming	W20–W25	Content streak, brand building, authority establishment	0 — funnel not warm yet
YouTube live	W25–W28	9 sub-pillar deep-dive videos published, retargeting active	1–2 inbound inquiries
First closes	W28+	Warm prospects booking from YouTube → booking page	1–2 closes/mo target
25 clients	By W52	Compound — each client = case study = more proof = more authority	25 by Dec 31, 2026

Weekly Cadence

Day	Content Action	System Action
Mon (data os)	Review Sun brief, pick 5 topics for the week (one per Maker Block)	Weekly brief auto-posts to #akash-notes Sun 6 PM
Tue	Content performance review · analytics deep-dive	Ranker scores written to topics_bank.csv
Daily 5–8 AM	Maker Block — ship 1 topic stack (YT + Reel + Carousel + Static)	batch_runner.py + generator.py
Fri	Kaizen — review what shipped, prep next week's queue	—
Daily	Reply to IG/YouTube comments, engage profile visitors	—
Thu (auto)	Drop YouTube links for transcript ingestion	yt_discovery scheduled (disabled — manual only)

ℹ

Monday is Creative day in the themed-day OS. Brief arrives Sunday 6 PM so Monday's 5 AM Maker Block has the picks ready. Maker Block 5–8 AM = daily topic stack (YT + Reel + Carousel + Static). Planning 8–10 AM. Ops starts 10:30am.

Content KPIs

Streak target

90d

by Aug 1, 2026

Reels / week

1/day Mon–Fri

YouTube videos

1 per topic

Target closes

by Dec 31, 2026

Booked calls

W28+

from YouTube → booking page

Topics banked

5 per sub-pillar

What "Working" Looks Like

Monday brief in Slack every week without fail
5 carousel JSONs generated per week (1/day Mon-Fri)
Every post drives to profile → YouTube
At least 1 new video ingested to brain.video_notes per week
YouTube video published for each topic (45 total)
Adding lead magnets, ManyChat, or Skool to the funnel
Going off-pillar (9 sub-pillars only — no lifestyle, no EyeFly ops content)
Skipping the brief — manual topic selection defeats the ranker system

Content Operating System

System Overview

Content Pillars

Better Leads

Better Systems

Better Data

Proof Points (rotate across pillars)

Topics Bank

Weekly Ranker

Scoring Dimensions (max 14 before multiplier)

Diversity Cap

Content Standard — Agent KB

The Rule of One

Core Positioning: Demand Gen vs. Demand Capture

Brand Voice — The Systems Consultant

The 9-Pillar Framework (3 Parents × 3 Sub-Pillars)

Better Leads

Better Systems

Better Data

The Offer

Unit Economics — Two Different CACs (always label)

Case Studies — Always Pair Number with Mechanism

Weekly Brief (Auto-generated)

Angle × Mechanism — Hook Bank

Carousel System

8-Slide Structure (strict — do not deviate)

Copy Rules

Generator Output

Reel Format — @angus.sewell Model

Format Spec

Never Do

Infrastructure

AI Models Used

brain.video_notes — Knowledge Base

Distribution Funnel

Content → Revenue Timeline

Weekly Cadence

Content KPIs

What "Working" Looks Like