St. Pierre AI · Internal Reference
Content Operating System
Full stack: ideation → ranking → production → distribution. Every carousel and reel produced by this system. Every lead generated by the funnel below it.
00
System Overview
Step 1
Topics Bank
48 topics / 3 pillars
→
Step 2
Weekly Ranker
Auto Monday 9pm
→
Step 3
Slack Brief
Top 10 + enriched
→
Step 4
Pick 3–5
Akash selects
→
Step 5
Generator
GPT-4o carousel
→
Step 6
Post + ManyChat
Comment → DM
ℹ
Zero manual research. Monday brief arrives in Slack automatically. Akash picks topics, runs
batch_runner.py, produces the reels. System handles everything else.
01
Content Pillars
Every carousel and reel must map to one of three pillars. P2 gets the highest ranking priority — most direct revenue signal.
P1
AI Content Creation
How to generate more leads
Ranker priority: +2
Topics: 16
AI carousels, content systems, hooks, reels, green screen, consistency
P2
AI Lead Capture / Transfer
How to book more quotes
Ranker priority: +3 ★ highest
Topics: 16
AI Messenger, ManyChat, pre-qualification, shared leads, guarantee, booked appointments
P3
AI Data / Analytics
How to dominate your market
Ranker priority: +2
Topics: 16
Super Pixel, $14M data moat, attribution, CPL vs CPQBC, LTV targeting, market intel
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 |
02
Topics Bank
Single source of truth for all carousel and reel topics. 48 rows, versioned and scored.
File: Projects/StPierre/carousel-production/topics_bank.csv
| Column | Purpose | Values |
|---|---|---|
id | Unique topic ID | 1–48 |
pillar_code | Maps to P1/P2/P3 | P1, P2, P3 |
topic | Full topic string fed to generator | — |
hook_angle | Default hook framing | Platform reveal, Data reveal, etc. |
featured_result | Proof point to anchor the carousel | Riley 47x ROI, Ashley $717K, etc. |
keyword | ManyChat comment trigger (ALL CAPS) | AICAROUSEL, MESSENGER, etc. |
niche | Target niche for this topic | crawl space, 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.
03
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).
04
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: We guarantee 5+ new foundation repair and/or basement/crawlspace waterproofing jobs in the next 6 weeks — or you don't pay.
| Tier | Price | What You Get | Guarantee |
|---|---|---|---|
| Main offer | $7,500 upfront | 50 leads / 6 weeks | 5 jobs or money back |
| Downsell | $4,500 upfront | 30 leads / 6 weeks | Lead delivery only |
| Ongoing | $150/lead, week-to-week | Client sets weekly volume | — |
| Metric | Number | How |
|---|---|---|
| Leads delivered | 50 | $7,500 ÷ $150/lead |
| Booked quotes (75%) | 37.5 | 50 × 75% |
| Closed jobs (15%) | 5.6 | 37.5 × 15% — guarantee covered ✓ |
| CAC | $1,500 | $7,500 ÷ 5 jobs |
| Avg job / GP @ 50% | $9,000 / $4,500 | Foundation repair / waterproofing |
| LTGP / CAC | 3x | $4,500 ÷ $1,500 |
Niche guarantees: Crawl space encapsulation / Foundation repair / Basement waterproofing = 10 new jobs in 90 days.
Exclusivity: One contractor per area. Working with you locks out your competitor.
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 3–5 topics, run batch_runner.py.
05
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)
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)
- CTA keyword = ALL CAPS (feeds ManyChat trigger)
- 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.
06
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.
Close
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
07
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
48 topics. 3 pillars × 16 topics. 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.
08
Distribution Funnel
Every carousel and reel feeds this funnel. The CTA on every Slide 8 drives a comment. ManyChat handles the rest.
1
Instagram Reel or Carousel
60–90s reel or 8-slide carousel. Slide 8 / close = "comment KEYWORD"
2
Comment Trigger → ManyChat Auto-DM
Viewer comments the keyword (ALL CAPS). ManyChat fires within seconds.
3
Lead Magnet Delivered
PDF delivered in DM. Rotates by calendar week.
W1: Ad Audit PDF · W2: GHL Client Snapshot · W6: GHL Sales Snapshot
4
DM Conversation → Warm Qualification
ManyChat qualifies niche + revenue. Akash closes warm convos manually.
5
Booked Call
Qualified lead books directly from DM conversation.
6
Close at $6,500
Main offer: $6,500 / 6 weeks / 40 leads / 5-job guarantee. Downsell: $4,500 / 30 leads / 3-job guarantee.
ICP: $1M+/yr revenue · gross margin 55%+ · avg job $7,500+
Content → Revenue Timeline
| Phase | Weeks | Focus | Expected closes |
|---|---|---|---|
| Warming | W20–W25 | Content streak, brand building, warm DM convos | 0 — funnel not warm yet |
| Pipeline seeding | W25–W28 | First qualified leads in DM pipeline | 1–2 prospects |
| First closes | W26+ | Akash closes from warm pipeline | 1–2 closes/mo target |
| 5 clients | By W52 | Compound — each client = case study = more proof | 5 by Dec 1, 2026 |
09
Weekly Cadence
| Day | Content Action | System Action |
|---|---|---|
| Mon (Creative day) | Review brief, pick 3–5 topics, plan week's reels | Weekly brief auto-posts to #akash-notes at 9pm |
| Tue | Run batch_runner, review carousel JSON outputs | Ranker scores written to topics_bank.csv |
| Wed–Thu | Film reels (green screen or selfie cam) | — |
| Fri | Edit + schedule posts. Set ManyChat keywords. | — |
| Daily | Reply to warm DMs, move convos toward call | — |
| 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 night. Deep work 7:20–10:30am = content planning + batch production. Ops starts 10:30am.
10
Content KPIs
Streak target
90d
by Aug 1, 2026
Reels / week
3–5
from batch_runner
Lead magnets
3
W1, W2, W6
Target closes
5
by Dec 1, 2026
Warm convos
W25+
pipeline seeds
Topics banked
48
16 per pillar
What "Working" Looks Like
- Monday brief in Slack every week without fail
- 3–5 carousel JSONs generated per week
- Every post has a keyword CTA → ManyChat wired
- At least 1 new video ingested to brain.video_notes per week
- Warm DM convos increasing week-over-week by W24
- Producing content without a ManyChat keyword wired (no conversion path)
- Going off-pillar (P1/P2/P3 only — no lifestyle, no EyeFly ops content)
- Skipping the brief — manual topic selection defeats the ranker system