SEO NavigatorDeployment Playbook

Phase 2 — SYSTEMATIZE

A 30-day deployment of Layer 2 — the Technical Architecture. Phase 1 proved the manual model; Phase 2 makes it autonomous. Stand up the reusable orchestration harness, ship the 6-agent Managed-Agent swarm, wire the Unified Command Center, then productize it all as the Hybrid OS retainer.

30Days
8Sprints
4Gates
6Agents
~165hRecovered / wk
~22hJake
Phase 2 progress
0%  0 / 0
Governing Principle — Hormozi Scaling Roadmap, Stage 5 (Productize) → Stage 6 (Optimize)
"Better beats more. Don't hire bodies to scale delivery — deploy the system that does the delivery, then sell the system as a product. The agent swarm is the second premium product to the same client base."
Layer 2 (Technical · WHAT) ships on top of the proven Layer 3+4 base. The Hybrid OS retainer that the fleet enables is the LTV:CAC multiplier — gated to the end of Phase 2 on purpose. Maps to the 90-Day Transformation, Sprint 2 (Days 31–60).
Week
Owner
00

Pre-Deploy Readiness

Four things must be true before a single agent runs. Confirm these in the Day-0 kickoff so Week 1 isn't spent chasing access.

Check 1 · Platform access

Managed Agents beta enabled

Anthropic Managed Agents beta access confirmed, beta header set, and the $0.08/session-hour pricing model understood. Sprint 1 test budget ~$50–100 approved.

Check 2 · Integrations

MCP + triggers wired

SEO Utils MCP reachable; external API keys ready (Apify, Firecrawl, Google Maps, OpenAI, Gemini, Perplexity); ClickUp status trigger + Slack slash-command path scoped.

Check 3 · Ownership

Roles assigned

Hung owns AI automation (harness, agents, n8n). Trung (IT) owns infrastructure + website/Astro. Phanh owns Sentinel's system prompt + rubric. Jake approves spend + the architecture map. PM owns the ClickUp Agent Registry.

Check 4 · Phase 1 closed

Gate 3 passed

Phase 1 must be green: CRM live, repeatable onboarding, monthly reporting working. Layer 2 automates these proven manual processes — don't automate what isn't yet proven.

Hormozi — sequence beats speed

Building the agent fleet before the manual model is proven is the classic premature-optimization trap. Phase 1 earned the right to automate; Phase 2 cashes it in. Readiness checks keep the order honest.

W1

Harness + First Agent Days 1–8

Build the reusable orchestration harness once, then deploy SEO Sentinel v1 as the proof agent. This is the hard week — the abstraction built here is what makes agents 2–6 trivial.

S-1A Reusable Orchestration Harness Days 1–5 Hung-led
Goal: A generic harness that triggers Managed-Agent sessions, streams their events, and routes their outputs — with a per-agent config-file pattern so every future agent plugs in with zero code changes.
TaskOwnerHrsSource
Build the dispatcher + config-file pattern (./agents/<name>.json: agent_id, kickoff prompt, ClickUp fields, delivery channels) Hung 6h Reuse PRD — Orchestration
Implement session lifecycle state machine + SSE event handling with reconnect logic Hung 5h Reuse PRD → lifecycle
Add idempotency, logging, and the HITL gate handler (stubbed for v1 — goes live with PM Pulse in Week 3) Hung 4h Reuse PRD → HITL
Deploy to VPS and pass the 7-test integration suite Hung 3h Reuse PRD → tests
Approve Anthropic API spend budget (~$50–100 Sprint 1) + sign off on the harness architecture Jake 1h PRD Local Automation
Hormozi — build the asset once

The harness is the leverage. Built properly once for Sentinel, it carries Catalyst, Revenue Relay, Ad Arbitrage, Build Bot, and PM Pulse for free. The abstraction pays for itself on the second agent — classic “better beats more.”

S-1B SEO Sentinel v1 — Proof Agent Days 5–8 Phanh + Hung
Goal: One Managed Agent — SEO Sentinel — runs the 5 Local SEO Automation modules against a real client on demand at ~$1.75/run, ~20–30 min, replacing ~3 hours of analyst work. Read-only: it audits, it never publishes.
TaskOwnerHrsSource
Create the SEO Sentinel agent + environment config; wire 5 modules (GBP, On-Page, Geographic grid, Citations, AI Visibility) via bash + SEO Utils MCP Hung 5h PRD Local Automation → §7
Phanh writes the v1 system prompt + scoring rubric (coverage, accuracy, structure) Phanh 3h SEO Lead Handoff
Wire triggers: ClickUp status → “Ready” and Slack slash-command; output posts to Slack + updates the ClickUp task Hung 3h PRD → triggers
Run T1 + T2 dry runs on a synthetic client; iterate the system prompt with the Phanh Phanh 2h PRD → testing
Hormozi — proof over promise

Sentinel is read-only on purpose: the riskiest thing an agent can do is publish. Prove accuracy on audits first, earn trust, then graduate to client-facing actions behind HITL gates. ~$1.75/run vs. ~3 analyst hours is the unit win that funds the whole fleet.

A Gate A — First Agent Validated 0%
  • Orchestration harness deployed to VPS; 7-test integration suite green
  • SEO Sentinel agent exists; agent_id recorded in ClickUp + version control
  • All 5 modules run end-to-end against a real client at ~$1.75/run
  • T1 validation passed — Sentinel's audit matches the reference on coverage / accuracy / structure (Phanh sign-off, ~Day 18 of the PRD roadmap)
Pass → proceed to Week 2 and start cloning agents. Fail → hold the fleet — a broken harness or inaccurate Sentinel poisons every agent built on top of it.
W2

Graduate the Fleet Days 9–15

Cash in the harness abstraction: plug in Content Catalyst and Revenue Relay via config files, no new orchestration code. In parallel, stand up the n8n playbook as the no-Managed-Agent fallback path.

S-2A Agents #2 & #3 via Config Days 9–12 Hung + pillar leads
Goal: Content Catalyst and Revenue Relay run on real client data — each added by dropping in an agents/<name>.json with zero changes to the dispatcher. This is the test of whether the harness abstraction actually holds.
TaskOwnerHrsSource
Drop in catalyst.json — wire Content Catalyst to QueryMind MCP (brief gen, meta optimization, AEO scoring) Hung 3h Reuse PRD → config pattern
Content Lead writes Catalyst's system prompt + rubric; validate brief output vs. a reference brief Nhu 3h QueryMind pipelines
Drop in revenue-relay.json — wire Revenue Relay to GoHighLevel MCP (follow-up sequences, lead scoring) Hung 3h SNMS CRM + Reuse PRD
Confirm the zero-code claim: log the diff — only config files added, dispatcher untouched Jake 1h Reuse PRD → acceptance
Hormozi — leverage compounds

Agent #1 took a week. Agents #2 and #3 take a config file each. That curve is the entire thesis of Layer 2 — build the system, then the marginal cost of capacity collapses toward zero.

S-2B n8n Playbook — Fallback Path Days 12–15 Hung + Phanh
Goal: The 4-module n8n Local SEO Automation playbook runs hands-free from a single form — a no-Managed-Agent path that saves 30+ hours/client/month and de-risks platform dependency.
TaskOwnerHrsSource
Build the 4 n8n modules: GBP Intelligence (44-point), On-Page Engine, Geographic grid (9/25-pt via Apify), Citation/NAP Hung 6h Local SEO Automation Playbook
Wire the pipeline: web form → n8n parallel APIs → Code scoring → OpenAI HTML report → SendGrid → Airtable Hung 4h n8n Playbook → flow
Phanh validates n8n report output parity against a Sentinel run on the same client Phanh 2h n8n Playbook
Hormozi — never one channel deep

Two paths to the same outcome (Managed Agent + n8n) is risk reversal at the infrastructure level. If Anthropic pricing or features shift, delivery doesn't stop — the n8n path keeps the SEO audits flowing.

B Gate B — Fleet Scales by Config 0%
  • Content Catalyst + Revenue Relay both running on real client data
  • Zero-code claim verified — agents added by config file only, dispatcher unchanged
  • n8n 4-module playbook runs hands-free from a single form submission
  • n8n output reaches parity with the Managed-Agent audit on the same client
Pass → proceed to Week 3 — the remaining agents + coordinator. Fail → if adding an agent needed code changes, fix the harness abstraction before going further.
W3

Coordinate & Command Days 16–22

Complete the fleet (Ad Arbitrage, Build Bot), then deploy PM Pulse — the coordinator that delegates to specialists and activates the HITL gates for client-facing output. Wire it all into the Unified Command Center.

S-3A Agents #4 & #5 + PM Pulse Coordinator Days 16–19 Hung + leads
Goal: Ad Arbitrage and Build Bot deployed by config; PM Pulse coordinator delegates to all 5 specialists, synthesizes outputs, posts to Slack — with the HITL gate now live for anything client-facing.
TaskOwnerHrsSource
Deploy Ad Arbitrage (ad-arbitrage.json) — Google + Meta reporting, copy variants, audit reports; Sang/Tung write its rubric Sang + Tung 3h Manage Agent SEO swarm
Deploy Build Bot (build-bot.json) — migrations, schema audits, Lighthouse + Playwright UAT Hung 3h Manage Agent SEO
Deploy PM Pulse coordinator — multi-agent delegation, output synthesis, Slack posting Hung 4h AI Orchestration diagram
Activate + test the HITL Slack gate on a client-facing deliverable (email draft / GBP post) — nothing ships without approval Jake 2h Reuse PRD → HITL
Hormozi — the human keeps the reins

PM Pulse is where agents start producing client-facing work, so the HITL gate goes live here. The centaur model holds: AI throughput, human approval before anything reaches a client. Speed without a quality gate is just faster mistakes.

S-3B Unified Command Center + Agent Registry Days 19–22 Hung + PM
Goal: One ClickUp + Slack control surface where every agent's runs, costs, and outputs are visible, and an Agent Registry that makes the fleet auditable and governable.
TaskOwnerHrsSource
Stand up the Unified Command Center (ClickUp + Slack) across the 7 workstreams Hung 4h Automating Agency Workflows
Build the ClickUp Agent Registry v1 — agent_id, owner, scope, cost/run, last run, status per agent PM 3h SN Workstream PM
Define governance: spend caps per agent, escalation paths, and the weekly agent-fleet review cadence PM 2h SN Workstream PM → governance
Hormozi — what gets measured gets managed

The Command Center turns six invisible cloud agents into a dashboard a human can run. Cost-per-run, accuracy, and hours saved are visible per agent — the basis for the Phase 2 graduation metrics and every optimization that follows.

C Gate C — Full Swarm Coordinated 0%
  • All 6 agents deployed (PM Pulse + 5 specialists) — the 8-day deploy target met
  • PM Pulse delegates to specialists and synthesizes outputs end-to-end
  • HITL Slack gate tested — no client-facing output ships without human approval
  • Unified Command Center + Agent Registry live; per-agent cost and status visible
Pass → proceed to Week 4 — productize. Fail → if coordination or HITL is shaky, keep specialists running solo and delay PM Pulse rather than shipping ungated output.
W4

Productize the Hybrid OS Days 23–30

Turn the working swarm into a sellable product, enroll the first 2 beta clients, and prove the graduation metrics: SOP accuracy ≥90%, fleet accuracy ≥85%, and ≥30% hour reduction.

S-4A Hybrid OS Package + 2 Beta Clients Days 23–26 Jake + PM
Goal: The Hybrid OS retainer is packaged as a real offer (~$1,500–$2,000/mo), the GHL snapshot is built, and 2 existing clients are enrolled as betas. Enrollment is a phone call, not a project.
TaskOwnerHrsSource
Package the Hybrid OS offer — scope, deliverables, price anchor vs. Detailers Roadmap, guarantee Jake 3h AI driven agency → Hybrid OS
Build the Hybrid OS GHL snapshot (the productized delivery container) Trung Le 5h 90-D Transfo → G4 Hybrid OS
Enroll 2 beta clients — one call each, grandfather pricing in exchange for feedback Jake 2h 90-D Transfo → beta
Hormozi — Productize (Scaling Roadmap Stage 5)

A second premium product to the same client base is the highest-leverage LTV:CAC move there is. The swarm already runs delivery, so gross margin on the Hybrid OS is structurally higher — that's the “triple the margin” claim made real.

S-4B Prove the Metrics — Full UAT Days 26–30 Jake + all leads
Goal: Run the full 12-agent UAT (334 checks, ~$9.65/run) on the beta clients and measure the swarm against the graduation bar. Document a Phase 2 retrospective with Phase 3 input.
TaskOwnerHrsSource
Run the 12-agent parallel UAT (239 of 334 checks automated, ~40 min, ~$9.65/run) on both beta clients Trung Le 3h AI driven agency → UAT
Measure the bar: SOP accuracy ≥90%, fleet accuracy ≥85%, ≥30% hour reduction vs. manual Jake 2h 90-D Transfo → criteria
Compile the Phase 2 retrospective — what to optimize (Stage 6) and Phase 3 (Layer 1) input Jake 2h Master Index → Layer 2 review
D Gate D — Phase 2 Complete: SYSTEMATIZE Proven 0%
  • 6-agent swarm live and coordinated through PM Pulse with HITL gates
  • Fleet accuracy ≥85% and SOP accuracy ≥90% on beta-client UAT
  • ≥30% hour reduction vs. the pre-agent manual process, measured
  • Hybrid OS packaged and 2 beta clients enrolled and live
  • Retrospective documented with an explicit Phase 3 (Layer 1) input list
Pass → graduate to Phase 3: AMPLIFY (Layer 1 strategic positioning, outbound flywheel, hiring plan; 90-Day Sprint 3). Fail → hold beta enrollment, fix the failing metric, and re-run UAT before scaling.

The Agent Fleet

Six Managed Agents on Anthropic infrastructure — one coordinator and five specialists — deployed in 8 days versus four weeks of DIY. Hours saved are weekly capacity recovered across the client book. Pricing is standard tokens + $0.08/session-hour, no idle charges.

PM Pulse
Coordinator

Delegates to specialists, synthesizes their outputs, posts to Slack. Owns the HITL gate for client-facing deliverables.

coordination layerWeek 3
🛰
SEO Sentinel
Specialist

Reports, audits, rank monitoring, AEO. Runs the 5 Local SEO modules at ~$1.75/run, replacing ~3h of analyst work.

~37h/wkWeek 1
Content Catalyst
Specialist

Brief generation, meta optimization, AEO scoring — wired to QueryMind MCP.

~30h/wkWeek 2
🔁
Revenue Relay
Specialist

GHL automation, follow-up sequences, lead scoring — wired to the GoHighLevel MCP.

~28h/wkWeek 2
📊
Ad Arbitrage
Specialist

Google + Meta reporting, ad-copy variants, audit reports across both ad platforms.

~25h/wkWeek 3
🔧
Build Bot
Specialist

Site migrations, schema audits, Lighthouse + Playwright UAT runs.

~18h/wkWeek 3
~165h recoverable per week across the fleet once all six are live — the capacity that funds the Hybrid OS margin and removes the “hire to scale” tax.

SEO Sentinel Deployment Pipeline

The end-to-end chain for Agent #1, straight from the Master Index's Layer 2 pipeline. Each link is a real document — WHAT the agent does, HOW it's triggered, WHO owns the deliverables, and the n8n alternative path.

PRD
What it does

PRD Local Automation — 19-section spec, 5 modules

Harness
How it triggers

Reuse PRD — config pattern, SSE, HITL

Handoff
Who owns it

SEO Lead Handoff — prompt + rubric

n8n
Fallback path

Local SEO Automation Playbook — 4 modules

Why this order matters: the harness is built generic so agents 2–6 inherit the trigger + streaming + HITL plumbing for free. The n8n path is deliberately parallel — it delivers the same SEO audit without depending on the Managed Agents platform, which is the single biggest tracked risk (R-01 below).

Agent ROI Calculator

Live payback and return for the fleet. Defaults are grounded in the source docs — SEO Sentinel replaces ~3 analyst hours at ~$1.75/run. Toggle to the fleet view to see total weekly capacity recovered in dollars.

Inputs

3.0 h
$25
32
$1.75

Outputs

Labor value created / mo$2,400
Agent cost / mo$56
Net savings / mo$2,344
Return on agent spend43×
Deploy — the agent returns far more than it costs. Every run is almost pure margin.
Hormozi — the real ROI is the freed human

The dollar return is large, but the point isn't token savings — it's that ~165 hours/week of human capacity move from execution to judgment, relationships, and selling the Hybrid OS. That reallocation is what triples margin, not the $1.75 line item.

RACI Ownership Matrix

Phase 2 is the AI-automation buildout — Hung is Responsible for the technical spine (agents, harness, n8n); Trung (IT) owns infrastructure, deployment, and website/Astro builds. Jake stays Accountable and owns the two judgment calls that can't be delegated: spend approval and the HITL gate on client-facing output.

WorkstreamJakeHung (AI)PhanhContent (Nhu)Ads (Sang/Tung)PM
Orchestration harnessARIIIC
SEO Sentinel v1ARRIII
Fleet graduation (agents 2–5)ARCCRI
PM Pulse + HITL gatesRRCCCA
Command Center + RegistryIRIIIA
Hybrid OS productizationRCIIIC
R Responsible — does the work A Accountable — owns the outcome C Consulted — input before I Informed — told after

Risk Register

Phase 2's risk profile is higher than Phase 1's — you're now dependent on a beta platform and shipping AI-produced work toward clients. Each risk has a mitigation already wired into the plan.

R-01Anthropic platform dependencyLikelihood: MedImpact: High

The fleet runs on Managed Agents (public beta). A pricing change, feature deprecation, or outage would hit delivery directly — this is the top risk named in the strategic vision.

Mitigation: The n8n playbook (Week 2) delivers the same SEO audits without Managed Agents. Skill definitions are portable to other frontier models; all client data lives in GHL / WordPress / ClickUp, never on Anthropic infrastructure.

R-02Agent ships a bad client-facing outputLikelihood: MedImpact: High

Once PM Pulse produces email drafts or GBP posts, an unreviewed error reaches a client and damages trust.

Mitigation: HITL Slack gate is mandatory for any client-facing action (Week 3). Sentinel and the early agents are read-only by design — trust is earned on audits before agents touch published output.

R-03Harness becomes a single point of failureLikelihood: LowImpact: High

Every agent plugs into one orchestration layer. A harness bug or VPS outage takes the whole fleet down at once.

Mitigation: 7-test integration suite gates the harness before any agent rides on it (Gate A). Idempotency + reconnect logic built in; the n8n path is an independent fallback for the highest-volume workflow.

R-04Fleet accuracy misses the 85% barLikelihood: MedImpact: Med

Agents run, but outputs aren't reliable enough to graduate — the Phase 2 metric fails and beta clients get sub-par work.

Mitigation: Per-agent rubrics + side-by-side validation against reference outputs at each gate. Gate D blocks scaling until ≥85% fleet accuracy and ≥30% hour reduction are measured, not assumed.

R-05Cost / token overrunLikelihood: LowImpact: Low

Runaway runs or verbose prompts inflate spend beyond the ~$1.75/run economics.

Mitigation: $0.08/session-hour with no idle charges keeps the floor low. The Agent Registry sets per-agent spend caps and the Command Center surfaces cost-per-run weekly. Sprint 1 budget is a contained ~$50–100.

Source Document Cross-Reference

Every sprint traces to specific Layer 2 documents in the 1st Batch. Links resolve to the real files in this folder.

SprintPrimary source documentsTheme
S-1AReuse PRD — Agent Orchestration, PRD Local AutomationManaged Agent Arch
S-1BPRD Local Automation, SEO Lead HandoffSentinel Pipeline
S-2AReuse PRD (config pattern), QueryMind, SNMS CRMManaged Agent Arch
S-2BLocal SEO Automation Playbook (n8n)Workflow Automation
S-3AManage Agent SEO (swarm), AI Orchestration, Reuse PRD (HITL)Managed Agent Arch
S-3BAutomating Agency Workflows, SN Workstream PMWorkflow Automation
S-4AAI driven agency (Hybrid OS), 90-D Transfo (G4)Productization
S-4BAI driven agency (UAT), Managed Agent — Monthly ReportProductization

What Comes Next — Phase 3: AMPLIFY

With delivery automated and the Hybrid OS proven on betas, Phase 3 deploys Layer 1 (Strategic North Star): positioning, the outbound → content flywheel, and the hiring plan — then scales beta clients to paying.

Phase 3 Preview — 90-Day Transformation Sprint 3 (Days 61–90)
Layer 1 turns a working machine into a growing business: sharpen the “first AI-native detailing agency” positioning, build the outbound + case-study flywheel (every won deal feeds the content engine), and hire against the workforce plan — train Agent Managers, don't add operators.
Closes the remaining gaps: G7 Outbound + Brand, plus HR & workforce strategy. Hormozi Scaling Roadmap Stage 6 (Optimize) → Stage 7 (Categorize). Better beats more — optimize the fleet before expanding it.