Follow-up walk-through · 2026-05-14 · post-discovery v2 — full corpus translation

The Compounding Content Engine — a three-week bet for Helen + Karina

Build one durable brand-voice Skill — anchored to Notion, surfaced through Slack — that compounds week over week until the same content output takes fewer hours. Amplify, don't replace. Start with one workflow, one metric, three weeks.

"It's not about having hours of free time… It's about micro-moments." — Helen Leland
ForHelen Leland · Karina
Engagementhelenleland.com creator hub · Sessions by Helen
WithJonathan · aiChemist
NextEight decisions to confirm via the input form

Frame one · the architectural shift

1The vending machine vs. the system

The convergent practitioner diagnosis is the same across every rig at this scale: most teams misuse AI as a text generator instead of a persistent system. In your vocabulary — don't ask for output. Build the place output comes from.

Vending machine · today

Ask · paste · copy back

Each ask starts from zero. Each caption has to be re-explained — voice, brand, the wellness-claim line, the Sessions emotional anchor, the Lane story, the founding-member tier. Yesterday's output didn't teach today's draft anything.

Symptom: the team approximates your voice; you catch the drift on read-through; the next caption starts from zero again.

System that compounds · after week 12

A durable brand-voice Skill, surfaced in Slack

One Skill carries your voice across both businesses. Karina governs it. Faith vets the wellness-claim guardrails. Every brand-deal draft, every Sessions caption, every ShopMy curation inherits it. Every Friday it gets sharper.

Outcome: the same brand-deal pitch takes Briana a fraction of the hours; the caption sounds like you on the first draft; the team's energy goes to community building and storytelling.
"Posture impacts how your lymph flows, how your muscles engage, and even how much energy you have." — Helen Leland (the same principle: the foundation determines what flows from it)

Frame two · the three creative modes

2Analyze → Curate → Generate

The established practitioner pattern separates three creative jobs that most teams collapse into one. A mature workflow chains all three in order: understand the audience first, refine what already works, then create. The order matters — out of order is where brand drift comes from.

Mode one

Analyze

Read what is already happening. Meta Ad Library on category-adjacent wellness advertisers becomes a competitive positioning brief. Sessions refund-survey responses become a pain-point taxonomy. Broadcast Channel comments surface participant-language vocabulary. AI as analyst, not generator.

Surface: Ad-library pull on the wellness/postpartum lane → positioning brief for next Sessions launch cohort.

Mode two

Curate

Refine and select from what already works. Algorithmic outlier-spotting surfaces posts performing 3–5× above baseline. Treat them as raw material — rewritten in your voice, not copied. Curation is the safer compass than generation.

Surface: Outlier-spotter pull → 5 candidates → Karina picks one → rewritten in Helen's voice for Reel.

Mode three

Generate

Draft new — only after analyze + curate have grounded the system. Six-hook-pattern Skill generates six opening hooks per topic. The draft inherits voice + audience signal + prior approve/reject patterns. First draft is closer to your voice because everything upstream is in the room.

Surface: 6-hook variant set for a single Sessions video → Karina + SMC pick the best → ships in one approval cycle.

Section three · where "compounds" stops being abstract

3The source-leverage inventory

Nothing new needs to be filmed for the engine to start producing. Helen's existing inventory is the input. Each row of this table is a single asset that already exists; each derivative is what the engine can pull from it. This is the visual proof of "compounds" — and the inventory Karina sees on Day 1.

Existing asset Derivative outputs the engine can produce
Sessions 12-video curriculum
~150 min of existing footage · highest single-source ROI
IG Reel caption × 12 TikTok hook variant × 12 IG Broadcast daily snippet × 10 Kajabi Day-by-Day email × 10 Long-form blog post × 3 (Posture · Nervous System · Cycle-Synced) Founding-member testimonial extraction prompt
Founding Member Zoom recordings
First cohort live calls · testimonial-rich
Q&A → FAQ doc Participant testimonial extraction Pain-point taxonomy for ad copy Top-5 friction list for Karina Objection-handler content briefs
IG Broadcast Channel archive
Cohort accountability surface · ongoing
Pillar identification (4–5 categories) Participant-language vocabulary file (Skill input) Evergreen cadence calendar from past month's performance
Brand-deal raw video footage
Cuts that already exist, never fully repurposed
IG Reel + TikTok dual-post draft IG Story sequence Carousel post (3–5 slides) ShopMy-link caption Founder-approval-ready brief
Sessions checkout reviews / refund-survey responses
Audience-voice substrate · already written by your people
Audience-voice persona deck Objection-handler library Onboarding email rewrite brief Day-6 drop-off intervention copy
IG Live recordings
Spontaneous content · evergreen-eligible
Topical Reels × 3–5 per Live Email-list announcement IG Broadcast follow-up draft Evergreen blog post

The Sessions 12-video curriculum is softly highlighted because it carries the highest single-source ROI — and is the recommended starting input on Decision 7 of the form. Nothing precludes the others.

Diagram one · the keystone

4The content-engine flywheel

Five stages, one loop. Mine outliers + audience signal. Transcribe an existing source. Rewrite in Helen's voice. Approve via Slack with one emoji. Distribute to six platforms. Refine the Skill on Friday. The system mutates weekly — each refinement raises tomorrow's baseline. This is why effort compounds instead of plateaus.

The compounding content engine — five stages, one loop

Karina governs. Notion holds state. Slack is the action surface. Claude is the bridge. The brand-voice Skill is the foundation underneath — built once via the 95% interview, refined every Friday.

"Wellness isn't about extremes, it's about building momentum with realistic habits." — Helen Leland (the same principle as the flywheel: build momentum, not breakthroughs)

Diagram two · what compounds actually looks like

5One source · ten outputs

The 10× promise made concrete. One Sessions video — a single asset that already exists — runs through the transcription pipeline, the voice Skill, and emerges as six distinct platform outputs. No new filming. No new copy from scratch. One approval cycle, not six. This is what the source-leverage table looks like in motion.

One source · ten outputs — the multi-platform compound distribution pattern

The transcription Skill turns audio into searchable text. The voice Skill rewrites for each platform's register and length. Karina ships in one cycle, not six. Hope's video edits land in the same Notion record as the captions.

Section six · the wedge stack

6Seven wedges, one Day-1 bet

Ranked by leverage across both in-scope businesses. The Day-1 wedge has the densest workflow surface — it touches every member of the team in sequence. The brand-voice Skill is the foundation that lives underneath all seven. Every wedge implements specific tactics from the convergent practitioner pattern — listed in plain language below.

# Wedge Surfaces What it implements Phase
1
Brand-deal triage classifier
Touches all 8 team members in sequence — Karina, Briana / Pia, Helen, Faith, Hope, John, Kamille.
Slack #brand-deals + Notion brand-deal DB + Claude classifier anchored to the voice Skill. Implements the Build-or-Skip filter, the founder-approval Slack agent, the classifier-by-prior-pattern approach, multi-platform brief generation. Day 1 · 3-week prototype
2
Sessions curriculum repurposing engine
Highest single-source ROI · the 12-video curriculum becomes the substrate.
Whisper transcription pipeline + Notion content library + Slack draft channel. Implements Whisper-based transcription, the 4-stage Find/Spot/Transcribe/Rewrite pipeline, multi-platform compound distribution (6 outputs from 1 source). Phase 2
3
Viral outlier mining
Wellness · postpartum · 10-Day Reset niches.
Outlier-spotter Skill + Notion outlier DB + Slack #content-source. Implements viral outlier spotting (3–5× baseline), curation-over-generation, the six-hook-pattern Skill applied per outlier. Phase 2 alt
4
Wellness-claim fact-check pipeline
Faith's leverage — frees her for genuine edge cases.
Fact-check tool (Perplexity-class) + Slack #fact-check channel + Faith's escalation. Implements automated claim verification, human-only-sees-flagged-subset routing, trust-by-default with audit trail. Phase 2
5
Audience-voice inference
Sessions reviews + IG Broadcast comments → personas.
Persona-research Skill + Notion persona DB. Implements audience-voice inference (the participant's voice, not the creator's), ad-library strategic analysis, persona-research automation. Phase 3
6
Notion knowledge-base priming
Eliminates copy-paste · full team context every conversation.
Notion connector + each team Claude Project (Helen · Karina · each SMC). Implements the durable knowledge-base priming pattern — Notion becomes the knowledge base Claude reads on every turn. Cross-cutting foundation
7
Founder approval Slack agent
Directly amplifies Helen's stated delegation philosophy.
Notion approval DB + Slack #approvals + one-emoji approve. Implements the founder-approval Slack agent · classifier-routes-by-prior-approve/reject-patterns · state mutates from emoji reaction. Phase 2 / 3

W1 is softly highlighted because that is the hypothesis we'd like to test with you on Decision 1 — not a prescription. The brand-voice Skill is the foundation under all seven; built once during P1, refined weekly, inherited by every downstream Skill.

Diagram three · founder approval, surfaced where Helen already lives

7The founder-approval Slack agent

The approval queue lives in Notion. The classifier scores against Helen's prior approve/reject patterns. The card lands in Slack #approvals on Helen's phone — where she already is. One emoji mutates the state. Approved content triggers distribution; revisions route back to the SMC with a templated note. Goal: one approval cycle per piece, not three.

Founder approval, surfaced where Helen already lives

This is the direct amplification of Helen's stated delegation philosophy: she stays on community building and storytelling; the agent handles the queue mechanics; Karina governs.

"I delegated operations to hire someone to handle the day to day so I could focus on community building and the marketing and sharing the story and helping with the branding." — Helen Leland, Kara Goldin Show (Jan 2024). The founder-approval agent is the amplification of this — not a correction of it.

Diagram four · how the Skill is born

8The 95% confidence interview

The convergent prompt pattern across the practitioner pattern: "Ask me clarifying questions, one at a time, until you are 95% confident you can complete the task successfully." This is what stops generic pastiche. We use it to bootstrap the durable Skill — once, ~45 minutes with Helen, then Karina governs.

How the foundation Skill is born — the 95% confidence interview

Karina runs the interview with Claude on Desktop. Helen contributes voice corpus + delegation philosophy + wellness-claim guardrails (Faith vets that section). The output is one file: helen-voice.skill.md.

Diagram five · the phased rollout

9Three weeks to prototype · twelve weeks to handoff

A short, named, measurable Day-1 bet — followed by the weekly compounding cadence — followed by full ownership handoff to Karina at week 12. Jonathan retains an advisor role beyond. No surprise scopes. No twelve-month commitments. Each phase has one owner and one metric.

P0 baseline · P1 the foundation Skill + Notion-Claude connector (W6) · P2 the Day-1 wedge prototype · P3 the weekly refinement loop · P4 Phase-2 wedge selection · P5 Karina owns the system.

The Build-or-Skip filterRecurring + Structured + Delegatable → build a Skill. Anything else → don't automate, just do it. This is the established practitioner discipline that prevents over-engineering: most teams ship one durable Skill per quarter, not seven half-built ones.

Section ten · the compounding mechanism

10How it gets sharper without more hours

Fifteen minutes a week. Karina walks Claude through what shipped. Flags the drift. Helen contributes one-emoji confirmations in the month-one cadence, then attends quarterly. The Skill mutates. The convergent industry pattern: review weekly, refine the system, tomorrow's baseline is strictly higher than today's. This is the only honest answer to "how does this get better without more hours?"

The mechanism is structural, not aspirational. Every approve/reject in Slack #approvals writes to Notion. Every Friday review reads that log, identifies the drift patterns, and mutates helen-voice.skill.md. The next week's drafts inherit the correction automatically — the team doesn't have to remember.

Section eleven · what we are saying out loud

11Four disclosures the proposal owes you

These are not footnotes. They are the load-bearing honesty of the proposal. If we cannot say them at the front, we cannot deliver against them at the back.

The desktop / CLI prerequisite gate

The pattern only runs on Claude Desktop or Claude Code — on an operator's machine. Web Claude alone cannot install Skills or connect to Notion. We confirm Karina's device baseline before any prototype begins. This is Decision 3 on the input form.

Pluggable tooling architecture

The convergent corpus over-concentrates on a single scheduling/distribution vendor (founder-overlap risk in the source material). We keep the scheduling layer pluggable — Karina chooses. We recommend specifying the interface, not the vendor. Decision 5 surfaces this.

The hidden human gate

Every "autonomous" demo in the practitioner pattern has a human checkpoint that the demo elides. The convergent verbatim: "I still check every single piece of content that goes out." We design for the gate — your one-emoji approve, Karina's triage, Faith's wellness-claim review — we don't pretend it isn't there.

Amplify, don't replace

The established practitioner pattern's most defensible position: AI absorbs production-heavy work — drafting, formatting, scraping, repurposing, transcribing, scheduling. It does not absorb strategy, editorial judgment, brand governance, narrative pacing, crisis response. Teams become smaller and strategy-heavier — they do not vanish. We promise amplification of your stated delegation philosophy, not substitution for the people who hold the voice.

Section twelve · next step

12Eight decisions to confirm

Each decision has a hypothesis we'd like to test with you — softly highlighted on the form, not prescribed. Free-text "other" available on every one. ~12 minutes if you skim · ~18 if you add notes · auto-saved every keystroke.

  1. Day-1 wedge confirmation — which of the seven wedges is the right 3-week Day-1 prototype?
  2. Brand-voice anchor — single voice across both businesses, Sessions sub-voice, or three voices?
  3. Tooling baseline — Claude Teams seats, Karina Desktop, Notion connector, Slack channel discipline?
  4. Two-SMC split logic — Briana ↔ Pia split by content type, platform, cohort cycle?
  5. Scheduling / distribution layer — native platform, third-party, or manual?
  6. Success metric for the 3-week prototype — hours saved, engagement rate, approval cycles, or other?
  7. Highest-leverage existing asset — which Sessions / creator-hub asset is the priority input for the engine?
  8. Wellness-claim fact-check posture — how does the fact-check pipeline interact with Faith's role?

The next step is the input form. Eight decisions, recommended hypothesis on each, free-text "other" everywhere. Walk through it with Jonathan live — or fill it independently. Returns are auto-saved locally; submission posts a structured summary back to the team.

Open the input form →