CM Content Factory v2.0 — AI Content Machine Platform

Config-driven, self-improving content factory with real-time dashboard, multi-agent independence, and token management. Gets smarter with use through memory + reward system.

Architecture

┌─────────────────────────────────────────────┐
│         🌐 DASHBOARD (localhost:5050)        │
│  Pipeline │ Tasks │ Tokens │ Logs │ Landing  │
└───────────┬─────────────────────────────────┘
            │ SSE / Polling
┌───────────┴─────────────────────────────────┐
│            🏭 PIPELINE ENGINE               │
│  ┌──────────┐ ┌──────────┐ ┌────────────┐  │
│  │  State   │ │  Token   │ │   Agent    │  │
│  │ Manager  │ │ Manager  │ │ Dispatcher │  │
│  └──────────┘ └──────────┘ └────────────┘  │
│                    │                         │
│  EXTRACT → PLAN → WRITE → AUDIT → SEO → PUB│
│                    │         │              │
│              📊 SCOREBOARD (reward/penalty)  │
│                    │                         │
│              🧠 MEMORY (3-layer learning)   │
└─────────────────────────────────────────────┘

Config file:

content-factory.config.json

config.schema.json

🚀 Quick Start

# New project (interactive wizard)
python3 scripts/wizard.py

# Full pipeline WITH dashboard
python3 scripts/pipeline.py --dashboard

# Pipeline with budget limit
python3 scripts/pipeline.py --dashboard --budget 5.0

# Dashboard only (standalone)
python3 scripts/dashboard_server.py

Phase 0: Discovery (MANDATORY)

AI MUST ask 5 question groups in order:

Phase 0.5: Confirm

Display summary table → WAIT for user OK → then proceed.

Operating Modes (12)

extract.py

plan.py

write.py

audit.py

seo.py

publish.py

scoreboard.py

memory.py

research.py

monetize.py

pipeline.py

dashboard_server.py

landing_generator.py

All scripts:

python3 scripts/<script> --config content-factory.config.json

Dashboard (NEW in v2.0)

Real-time web dashboard at

http://localhost:5050

• Pipeline Progress: Visual 6-phase timeline with progress bars
• Task Queue: Active/queued/completed/failed task cards
• Token Tracker: Cost by provider, budget progress bar
• Event Log: Filterable real-time log viewer
• Error Panel: Highlighted error details

# Auto-start with pipeline
python3 scripts/pipeline.py --dashboard --dashboard-port 5050

# Standalone
python3 scripts/dashboard_server.py --port 5050

Multi-Agent Support (NEW in v2.0)

Multiple agents can work independently on the same pipeline via file-based task queue.

from agent_dispatcher import AgentDispatcher
d = AgentDispatcher()

# Enqueue tasks
d.enqueue("write-article-1", "write", {"topic": "SEO Tips"}, priority=3)
d.enqueue_batch([{"id": "w-2", "type": "write"}, {"id": "w-3", "type": "write"}])

# Agent claims next task
task = d.claim_next("gemini-agent-1")
d.heartbeat("gemini-agent-1", task["id"])  # Keep alive

# Complete or fail
d.complete(task["id"], "gemini-agent-1", {"result": "ok"})
d.fail(task["id"], "gemini-agent-1", "API timeout")  # Auto-retry up to 3x

Features: priority ordering, stale lock detection (10min), auto-retry (3x), heartbeat.

Token Management (NEW in v2.0)

Track token usage, costs, rate limits, and budget across all providers.

from token_manager import TokenManager
tm = TokenManager(budget_usd=5.0)

# Record usage
tm.record_usage("gemini", input_tokens=1000, output_tokens=500, task_id="w-1")

# Check budget
if not tm.check_budget():
    print("Budget exceeded!")

# Rate limiting
tm.wait_if_rate_limited("gemini")

# Circuit breaker (auto-stop after 5 consecutive failures)
if tm.is_circuit_open("gemini"):
    print("Provider down, switching...")

python3 scripts/token_manager.py status

Landing Pages (NEW in v2.0)

Generate persona-based landing pages using Content Mastery SB7 framework.

Add

personas

{
  "personas": [{
    "name": "Economic Buyer",
    "headline": "Save 50% on Marketing Costs",
    "subheadline": "AI creates professional content, 10x faster",
    "pain_points": ["High marketing costs", "Lack of content staff"],
    "benefits": [{"title": "Cost Savings", "description": "Reduce costs by 50%"}],
    "social_proof": [{"number": "2,347", "label": "Businesses trust us"}],
    "steps": [{"title": "Configure", "description": "Enter your business information"}],
    "cta_text": "Try It Free"
  }]
}

python3 scripts/landing_generator.py --config content-factory.config.json
python3 scripts/landing_generator.py --config content-factory.config.json --list

Pipeline Execution

1. INIT     → wizard.py + scaffold.py → Astro project + config
2. RESEARCH → pipeline:research → 30+ topics
3. EXPAND   → expand-topics.py → 30 → target (100/200/...)
4. WRITE    → pipeline:write → 3 workers, 8s sleep, ~3 articles/min
5. MILESTONE → audit → build → deploy (at 50%/100%)
6. SHIP     → Final audit → deploy → notify user

🛡️ Golden Rules (Score 95+)

• Performance: Font preload, critical CSS inline, preconnect, img width/height, GTM defer
• Accessibility: WCAG AA contrast (#555+ on white), semantic HTML, h1-h3 hierarchy
• Security: CSP/HSTS/XFO headers via

  public/_headers

  , cache

  immutable

  for

  /_astro/*

• SEO:

  robots.txt

  → sitemap, proper meta tags

Self-Learning System

Memory (3 layers)

memory/semantic/

memory/episodic/

memory/working/

Scoreboard

Scripts Reference

Core Pipeline

pipeline.py

extract.py

plan.py

write.py

audit.py

seo.py

validate.py

publish.py

deploy.py

Platform Layer (NEW v2.0)

state_manager.py

token_manager.py

dashboard_server.py

agent_dispatcher.py

landing_generator.py

Intelligence Layer

memory.py

scoreboard.py

research.py

monetize.py

Setup

wizard.py

scaffold.py

⚠️ Rules

1. ALWAYS ask before doing — Phase 0 Discovery is mandatory
2. ALWAYS confirm — Display summary, wait for user OK
3. ALWAYS notify milestones — At 50%, deploy milestone, completion
4. NEVER deploy without audit — Always audit before deploy
5. NEVER skip questions — If user doesn't provide info, use default + confirm
6. ALWAYS use dashboard — When running pipeline, add

   --dashboard

Content Mastery Framework — High-Conversion Content Writing

Unified content writing system. Synthesized from 8+ frameworks: StoryBrand (SB7), SUCCESs, Cialdini (7 Principles), STEPPS, Hook Model, JTBD, CRO, Grand Slam Offers.

Core Principle: Excellent content is not art — it is systematic science. Every word guides the reader: "unaware" → "interested" → "desire" → "action".

Phase 0: Persona & JTBD

User Persona Canvas (complete BEFORE writing):

Buyer Persona: Economic (ROI) | User (UX) | Technical (specs) | Coach (case studies)

Job Statement (JTBD):

When [situation], I want [outcome], so that [end result]

• 3 dimensions: Functional + Emotional + Social
• 4 forces: Push + Pull > Habit + Anxiety

Phase 1: Hook — 12 Formulas

Rule: 1 hook = 1 message. Test 3-5 hooks for each important piece of content.

Phase 2: SB7 Narrative

1. Hero (Customer) → has ONE desire
2. Problem → Villain + External + Internal + Philosophical
3. Guide (You) → Empathy + Authority
4. Plan → 3 simple steps
5. CTA → Direct + Transitional
6. Failure → consequences of inaction
7. Success → the picture of success

Golden Rule: Customer = HERO. You = GUIDE. Never make the brand the main character.

Phase 3: 7 Cialdini Weapons

FOMO 5 layers: Time Scarcity → Quantity Scarcity → Exclusive Access → Social FOMO → Opportunity Cost

Ethical boundary: FOMO must be BASED ON TRUTH. Fake countdowns = permanent brand destruction.

Phase 4: SUCCESs + STEPPS

SUCCESs (Made to Stick) — ≥4/6: Simple, Unexpected, Concrete, Credible, Emotional, Stories

STEPPS (Viral Check): Social Currency, Triggers, Emotion (high-arousal), Public, Practical Value, Stories

Phase 5: Offer & CTA

Grand Slam Offer:

Perceived Value = (Dream Outcome × Likelihood) / (Time Delay × Effort)

O/CO (Objection/Counter-Objection): Trust → Testimonials. Price → ROI calc. Fit → Case study. Timing → Deadline. Effort → "Done-for-you".

Phase 6: SEO Checklist

• Title Tag ≤ 60 chars + primary keyword
• Meta Description ≤ 155 chars + CTA
• H1 × 1 + keyword. H2-H3 hierarchy + secondary keywords
• First 100 words contain primary keyword
• ≥ 3 internal links + 2-5 external authoritative links
• Schema Markup: FAQ, How-to, Article as appropriate

Phase 7: Cross-Audit 7 Dimensions (each /10)

1. Hook Power — Does the first 3 seconds retain attention?
2. Persona Fit — Correct VoC + pain + dream?
3. Persuasion Depth — ≥3 Cialdini + O/CO?
4. Narrative Flow — SB7 compliant?
5. Stickiness — ≥4/6 SUCCESs?
6. SEO Compliance — Title/Meta/H1/links?
7. CTA Clarity — 1 Direct CTA + repeat?

63-70: Exceptional | 49-62: Strong | 35-48: Average | <35: Fail — rewrite

Content Type Matrix

Ethical Boundaries

1. No fake scarcity (fake timers, fake "sold out")
2. No fabricated testimonials
3. No exploiting vulnerable groups
4. No promising undeliverable results
5. No hidden costs
6. No fear-mongering

Final test: "Would you be willing to apply this technique to your own family?"