W
SEO Navigator · WF4 Action Plan
Jake · Founder & Strategist
OWNER #1 · 2–3 weeks
Jake
Founder & Strategist
10
Tasks
6–8h
Estimate
2–3 weeks
Window
At a Glance
YOUR ROLE
You own the strategic decisions and sign-offs. Your tasks are short but gate several downstream workstreams — prioritise the early ones.
DAY 1 PRIORITY
J1 Submit Research Preview application + J2 Approve Anthropic budget. Both are unlock-the-door moves.
IF YOU SLIP
Trung cannot start the IT build without J2 (budget) + J6 (PRD sign-off). SEO team cannot finalise the system prompt without J7 (template sign-off). Rollout gated on J8.
Input → Output Flow
What you receive, what you do, what you produce, who consumes it.
📥 YOU RECEIVE
Research Preview approval from Anthropic · PRD draft from Trung · Templates from Phuong Anh + An Thai · T2 validation from SEO Lead
⚙️ YOU DO
10 tasks — total 6–8h across 2–3 weeks. See task list below.
📤 YOU PRODUCE
Budget approval · Behaviour boundary decisions · Client selection · PRD sign-off · Final go-live green-light · QueryMind MCP decision
👉 CONSUMED BY
Trung (J2, J4, J6 unlock his build) · Phuong Anh (J5 picks test clients she validates) · SEO team (J7 sets template bar)
Tasks — Click any card to expand
Prerequisites chain at top, steps in the middle, done-when at bottom. Checkbox state persists locally.
J1
Submit Research Preview application
⏱ 1h W1
Prerequisites
None — start anytime
Blocks (downstream)
Terminal — nothing waits
📋 Steps
  1. Apply for callable_agents, memory_stores, and outcomes via Anthropic Research Preview form.
  2. Not needed for WF4 MVP — but start Day 1 so access arrives in time for WF2.
  3. Document application ID + submission date in ClickUp.
✅ Done when
Application submitted. Confirmation email received. Logged in ClickUp.
J2
Approve Anthropic API budget ceiling
⏱ 15m W1
Prerequisites
None — start anytime
Blocks (downstream)
T1
📋 Steps
  1. Approve ~$100 ceiling for Sprint 1 testing (safety margin for experimentation).
  2. Approve ~$15/mo production budget (at 8 clients × 1 cycle × ~$0.55–0.70/run).
  3. Confirm payment method on Claude Platform.
✅ Done when
Budget approved + payment method confirmed. Trung can start paid runs.
J3
Audit existing external subscriptions for MCP access
⏱ 30m W1
Prerequisites
None — start anytime
Blocks (downstream)
Terminal — nothing waits
📋 Steps
  1. Verify ClickUp plan tier supports API access + MCP connector.
  2. Verify Slack plan tier supports bot tokens + MCP connector.
  3. Verify Google Workspace service account quota.
  4. Verify GHL API access is enabled on the agency account.
✅ Done when
All 4 subs confirmed at sufficient tier. Any upgrades queued before Trung starts MCP setup.
J4
Define agent behaviour boundaries for WF4
⏱ 45m W1
Prerequisites
None — start anytime
Blocks (downstream)
T6T8T9T10
📋 Steps
  1. Decide: (a) Can the agent post directly to Slack, or only draft for human approval?
  2. Decide: (b) Can the agent update ClickUp task comments?
  3. Decide: (c) Can the agent write files directly to client Drive folders?
  4. Decide: (d) Can the agent auto-embed reports in GHL contact records, or manual only?
  5. Document 4 yes/no decisions in ClickUp — each affects what Trung's orchestration script does vs what humans do.
✅ Done when
Four yes/no decisions documented. Trung can finalise orchestration script scope.
J5
Select 2 test clients (T1 synthetic + T2 real low-risk)
⏱ 1h W2
Prerequisites
None — start anytime
Blocks (downstream)
T12
📋 Steps
  1. Pick the synthetic/sandbox fixture client for T1 (Linh will build fake data — just need a plausible shape).
  2. Pick a real, low-risk client for T2 (established retainer, tolerant of an experiment).
  3. Brief the real client: "Next month's report goes through a new automation — SEO Lead still reviews before you see it." Frame as improvement, not experiment.
✅ Done when
Synthetic + real client chosen. Real client pre-briefed. T2 can proceed.
J6
Review + sign off on the PRD before build kickoff
⏱ 45m W1
Prerequisites
None — start anytime
Blocks (downstream)
T6
📋 Steps
  1. Read Part 4 of the Action Plan doc end-to-end.
  2. Focus on: Definition of Done (§8), scope boundaries (§1), secrets plan (§5).
  3. Flag any scope expansions or risk tolerances you disagree with.
  4. Sign off or send back with edits.
✅ Done when
PRD signed off. Trung starts IT build kickoff (T1 onwards).
J7
Review Phuong Anh's template + An Thai's KPI glossary
⏱ 1h W2
Prerequisites
P1A1
Blocks (downstream)
T6
📋 Steps
  1. Read monthly-report-template.md from Phuong Anh.
  2. Read kpi-glossary.json from An Thai.
  3. Judge: does this represent "a good report looks like THIS"? You have final say.
  4. If yes, approve. If no, specific feedback to the owners before Trung mounts them on the agent.
✅ Done when
Both artifacts approved (or revised and re-approved). Agent system prompt can finalise.
J8
Final sign-off after T2 → green-light production rollout
⏱ 30m W3
Prerequisites
P6T12
Blocks (downstream)
P7L3
📋 Steps
  1. Read Phuong Anh's T2 validation recommendation.
  2. Review the T2 output yourself (the actual report Trung's agent produced).
  3. Green-light or red-light the full production rollout to the remaining 7 clients.
  4. If green: confirm rollout plan + cadence with team.
✅ Done when
Production rollout green-lit. Last gate cleared before all-client cycle.
J9
Decide QueryMind MCP/CLI path (blocks WF2 timeline)
⏱ 1h W3
Prerequisites
None — start anytime
Blocks (downstream)
Terminal — nothing waits
📋 Steps
  1. Read Part 1 "Critical Dependency" callout — 3 options for QueryMind MCP access.
  2. Conversation with Trung: effort estimate for Option A (build thin MCP wrapper, 3–5 days).
  3. Decide: (a) Trung builds wrapper in WF1→WF2 gap, (b) wrap QueryMind CLI if exists, (c) defer WF2.
  4. Commit Trung to the scope — blocks WF2 planning.
✅ Done when
Decision made + logged. Trung has scope for the WF1→WF2 gap work.
J10
Monthly cost review at end of month 1 in production
⏱ 1h Month 1 close
Prerequisites
P7
Blocks (downstream)
Terminal — nothing waits
📋 Steps
  1. Pull Claude Console spend data for month 1.
  2. Compare actual vs projection: ~$5/mo at 8 clients was the projection.
  3. If variance >50%: decide whether to adjust client pricing model, throttle runs, or tune agent for fewer tokens.
  4. Approve or flag next-workflow (WF1) go/no-go based on cost + quality confidence.
✅ Done when
Cost review signed off. WF1 go/no-go decision made.
Handoffs
📤 YOU HAND OFF TO
Trung (J2, J4, J6 unlock his build) · Phuong Anh (J5 picks test clients she validates) · SEO team (J7 sets template bar)
📥 YOU RECEIVE FROM
Trung (J6 PRD, J10 cost data, J9 QueryMind effort estimate) · Phuong Anh (J7 template, J8 T2 recommendation)
← Back to WF4 Hub