Add agent identity & check-in protocol to all 5 sessions
Each session now has:
- Agent self-identification system (S1-H01 through S5-H10)
- Check-in protocol (agents announce identity at start)
- Task reference system (agents find instructions by number)
- Dependency tracking (parallel vs sequential execution)
Note: Prestige yachts sell for €1.5M (not €480K) - needs price correction in Session 1
🤖 Generated with Claude Code
This commit is contained in:
Danny Stocker
parent
317c01e871
commit
a5ffcb5769
8 changed files with 310 additions and 2 deletions
|
|
@ -44,9 +44,30 @@ Gather comprehensive market intelligence for Riviera Plaisance Euro Voiles, focu
|
|||
|
||||
---
|
||||
|
||||
## Your Tasks (Spawn 10 Haiku Agents in Parallel)
|
||||
## Agent Identity & Check-In Protocol
|
||||
|
||||
### Agent 1: Recreational Boat Market (Jeanneau Prestige Focus)
|
||||
**YOU ARE:** Sonnet coordinator for Session 1 (Market Research)
|
||||
|
||||
**YOUR HAIKU SWARM:** You have 10 Haiku agents available. Use as many as needed (not required to use all 10).
|
||||
|
||||
**AGENT IDENTITY SYSTEM:**
|
||||
When spawning a Haiku agent, assign it an identity: `S1-H01` through `S1-H10`
|
||||
Each agent MUST:
|
||||
1. **Check in** at start: "I am S1-H03, assigned to [task name]"
|
||||
2. **Reference their task** by searching this document for "Agent 3:" (matching their number)
|
||||
3. **Retain identity** throughout execution
|
||||
4. **Report completion** with identity: "S1-H03 complete: [deliverable summary]"
|
||||
|
||||
**TASK DEPENDENCIES:**
|
||||
- Agents 1-9 can run in parallel (no dependencies)
|
||||
- Agent 10 (Evidence Synthesis) MUST wait for Agents 1-9 to complete
|
||||
|
||||
---
|
||||
|
||||
## Your Tasks (Use Haiku Agents S1-H01 through S1-H10 as Needed)
|
||||
|
||||
### Agent 1:
|
||||
**AGENT ID:** S1-H01
|
||||
**Research:**
|
||||
- Jeanneau Prestige 40-50ft market (units sold annually, price range €250K-€480K)
|
||||
- Riviera Plaisance Euro Voiles volume (150+ boats/year validated)
|
||||
|
|
@ -56,6 +77,8 @@ Gather comprehensive market intelligence for Riviera Plaisance Euro Voiles, focu
|
|||
**Deliverable:** Market sizing report for recreational boat segment with citations
|
||||
|
||||
### Agent 2: Competitor Analysis (Boat Management Apps)
|
||||
**AGENT ID:** S1-H02
|
||||
**
|
||||
**Research:**
|
||||
- Boat management apps (Savvy Navvy, Dockwa, Boat Buddy, BoatVault, DeckDocs)
|
||||
- Daily engagement features (cameras, maintenance logs, inventory tracking)
|
||||
|
|
@ -66,6 +89,8 @@ Gather comprehensive market intelligence for Riviera Plaisance Euro Voiles, focu
|
|||
**Deliverable:** Competitive matrix showing NaviDocs differentiation (daily engagement + perfect docs)
|
||||
|
||||
### Agent 3: Owner Pain Points (Daily Boat Management)
|
||||
**AGENT ID:** S1-H03
|
||||
**
|
||||
**Research:**
|
||||
- What frustrates recreational boat owners? (maintenance tracking, expense tracking, remote monitoring)
|
||||
- "Forgot to sell the tender" problem - how common is inventory loss at resale?
|
||||
|
|
@ -76,6 +101,8 @@ Gather comprehensive market intelligence for Riviera Plaisance Euro Voiles, focu
|
|||
**Deliverable:** Owner pain point analysis ranked by frequency and financial impact
|
||||
|
||||
### Agent 4: Inventory Tracking & Resale Value Protection
|
||||
**AGENT ID:** S1-H04
|
||||
**
|
||||
**Research:**
|
||||
- Boat equipment upgrade market (tenders, electronics, deck refinishing, automatic systems)
|
||||
- Average upgrade spend per boat per year (Jeanneau Prestige 40-50ft owners)
|
||||
|
|
@ -86,6 +113,8 @@ Gather comprehensive market intelligence for Riviera Plaisance Euro Voiles, focu
|
|||
**Deliverable:** ROI calculator for inventory tracking (€X forgotten value prevented)
|
||||
|
||||
### Agent 5: Sticky Engagement Feature Research
|
||||
**AGENT ID:** S1-H05
|
||||
**
|
||||
**Research:**
|
||||
- Boat camera/monitoring systems (Siren Marine, GOST, Nautic Alert)
|
||||
- Maintenance reminder apps (what makes them sticky vs ignored?)
|
||||
|
|
@ -96,6 +125,8 @@ Gather comprehensive market intelligence for Riviera Plaisance Euro Voiles, focu
|
|||
**Deliverable:** Feature prioritization - which sticky features drive daily/weekly engagement?
|
||||
|
||||
### Agent 6: Search UX Best Practices (Critical for Inventory)
|
||||
**AGENT ID:** S1-H06
|
||||
**
|
||||
**Research:**
|
||||
- Search UX for inventory/asset management (how to avoid long lists?)
|
||||
- Structured search results (Pinterest, Amazon, Airbnb approaches)
|
||||
|
|
@ -106,6 +137,8 @@ Gather comprehensive market intelligence for Riviera Plaisance Euro Voiles, focu
|
|||
**Deliverable:** Search UX recommendations - impeccable structured results, zero long lists
|
||||
|
||||
### Agent 7: Pricing Strategy Research (Broker-Included Model)
|
||||
**AGENT ID:** S1-H07
|
||||
**
|
||||
**Research:**
|
||||
- "Included with purchase" software models (Tesla app, luxury car apps)
|
||||
- Broker/dealer software bundling strategies
|
||||
|
|
@ -116,6 +149,8 @@ Gather comprehensive market intelligence for Riviera Plaisance Euro Voiles, focu
|
|||
**Deliverable:** Pricing recommendation for "included with every Riviera boat" model
|
||||
|
||||
### Agent 8: Home Assistant & Camera Integration Research
|
||||
**AGENT ID:** S1-H08
|
||||
**
|
||||
**Research:**
|
||||
- Home Assistant boat monitoring setups (camera feeds, bilge sensors, battery monitoring)
|
||||
- Marine camera systems compatible with HA (Hikvision, Reolink, marine-rated cameras)
|
||||
|
|
@ -126,6 +161,8 @@ Gather comprehensive market intelligence for Riviera Plaisance Euro Voiles, focu
|
|||
**Deliverable:** Technical feasibility report for Home Assistant/camera integration
|
||||
|
||||
### Agent 9: Broker Sales Objection Research
|
||||
**AGENT ID:** S1-H09
|
||||
**
|
||||
**Research:**
|
||||
- Why brokers resist including software with boat sales (complexity, support burden)
|
||||
- Owner adoption challenges (will they actually use it after purchase?)
|
||||
|
|
@ -136,6 +173,8 @@ Gather comprehensive market intelligence for Riviera Plaisance Euro Voiles, focu
|
|||
**Deliverable:** Objection handling playbook for Sylvain meeting
|
||||
|
||||
### Agent 10: Evidence Synthesis
|
||||
**AGENT ID:** S1-H10
|
||||
**
|
||||
**Research:**
|
||||
- Compile all findings from Agents 1-9
|
||||
- Cross-reference data for consistency
|
||||
|
|
|
|||
|
|
@ -40,9 +40,32 @@ Design technical architecture for **sticky daily-use features** (inventory track
|
|||
|
||||
---
|
||||
|
||||
|
||||
## Agent Identity & Check-In Protocol
|
||||
|
||||
**YOU ARE:** Sonnet coordinator for Session 2 (Technical Architecture)
|
||||
|
||||
**YOUR HAIKU SWARM:** You have 10 Haiku agents available. Use as many as needed (not required to use all 10).
|
||||
|
||||
**AGENT IDENTITY SYSTEM:**
|
||||
When spawning a Haiku agent, assign it an identity: `S2-H01` through `S2-H10`
|
||||
Each agent MUST:
|
||||
1. **Check in** at start: "I am S2-H03, assigned to [task name]"
|
||||
2. **Reference their task** by searching this document for "Agent 3:" (matching their number)
|
||||
3. **Retain identity** throughout execution
|
||||
4. **Report completion** with identity: "S2-H03 complete: [deliverable summary]"
|
||||
|
||||
**TASK DEPENDENCIES:**
|
||||
- Most agents can run in parallel
|
||||
- Agent 10 typically synthesizes results from Agents 1-9 (must wait for completion)
|
||||
|
||||
---
|
||||
|
||||
## Your Tasks (Spawn 10 Haiku Agents in Parallel)
|
||||
|
||||
### Agent 1: NaviDocs Codebase Analysis
|
||||
**AGENT ID:** S2-H01
|
||||
**
|
||||
**Read Files:**
|
||||
- `server/db/schema.sql` - Database structure
|
||||
- `server/routes/*.js` - API endpoints
|
||||
|
|
@ -52,6 +75,8 @@ Design technical architecture for **sticky daily-use features** (inventory track
|
|||
**Deliverable:** Architecture map with integration points
|
||||
|
||||
### Agent 2: Inventory Tracking System Design (CRITICAL)
|
||||
**AGENT ID:** S2-H02
|
||||
**
|
||||
**Design:**
|
||||
- Database schema: `boat_inventory` (item_name, category, zone, purchase_date, purchase_price, receipt_url, warranty_expiration, current_value)
|
||||
- Categories: tender/zodiac, electronics, engine, deck, interior, safety
|
||||
|
|
@ -63,6 +88,8 @@ Design technical architecture for **sticky daily-use features** (inventory track
|
|||
**Deliverable:** Inventory tracking spec with impeccable search UX
|
||||
|
||||
### Agent 3: Maintenance Log & Reminder System
|
||||
**AGENT ID:** S2-H03
|
||||
**
|
||||
**Design:**
|
||||
- Database schema: `maintenance_log` (service_type, date, cost, provider, next_due_date, engine_hours)
|
||||
- Service types: engine, electronics, hull, deck, safety equipment
|
||||
|
|
@ -73,6 +100,8 @@ Design technical architecture for **sticky daily-use features** (inventory track
|
|||
**Deliverable:** Maintenance tracking spec with smart reminders
|
||||
|
||||
### Agent 4: Camera & Remote Monitoring Integration (STICKY!)
|
||||
**AGENT ID:** S2-H04
|
||||
**
|
||||
**Research + Design:**
|
||||
- Home Assistant camera feed integration (Hikvision, Reolink, marine cameras)
|
||||
- Webhook architecture (NaviDocs ← HA events: motion detected, battery low, bilge alert)
|
||||
|
|
@ -83,6 +112,8 @@ Design technical architecture for **sticky daily-use features** (inventory track
|
|||
**Deliverable:** Camera/HA integration architecture with peace-of-mind UX
|
||||
|
||||
### Agent 5: Contact Management System
|
||||
**AGENT ID:** S2-H05
|
||||
**
|
||||
**Design:**
|
||||
- Database schema: `boat_contacts` (name, role, phone, email, notes, last_used)
|
||||
- Roles: marina, mechanic, cleaner, charter crew, electrician, surveyor
|
||||
|
|
@ -93,6 +124,8 @@ Design technical architecture for **sticky daily-use features** (inventory track
|
|||
**Deliverable:** Contact management spec with mobile-first UX
|
||||
|
||||
### Agent 6: Expense Tracking & Accounting
|
||||
**AGENT ID:** S2-H06
|
||||
**
|
||||
**Design:**
|
||||
- Database schema: expense tracking across inventory, maintenance, marina fees
|
||||
- Expense categories (maintenance, upgrades, insurance, marina, fuel, crew)
|
||||
|
|
@ -103,6 +136,8 @@ Design technical architecture for **sticky daily-use features** (inventory track
|
|||
**Deliverable:** Expense tracking spec with budget management
|
||||
|
||||
### Agent 7: Impeccable Search UX Design (CRITICAL)
|
||||
**AGENT ID:** S2-H07
|
||||
**
|
||||
**Design:**
|
||||
- Search architecture (Meilisearch faceted search)
|
||||
- Structured results (NO long lists - Pinterest/Airbnb grid layout)
|
||||
|
|
@ -114,6 +149,8 @@ Design technical architecture for **sticky daily-use features** (inventory track
|
|||
**Deliverable:** Search UX spec with visual mockups (avoid long lists!)
|
||||
|
||||
### Agent 8: Notification System Design
|
||||
**AGENT ID:** S2-H08
|
||||
**
|
||||
**Design:**
|
||||
- Email notification service
|
||||
- SMS alerts (warranty expiration, document missing)
|
||||
|
|
@ -123,6 +160,8 @@ Design technical architecture for **sticky daily-use features** (inventory track
|
|||
**Deliverable:** Notification architecture with templates
|
||||
|
||||
### Agent 9: Database Migration Plan
|
||||
**AGENT ID:** S2-H09
|
||||
**
|
||||
**Create:**
|
||||
- Migration scripts for warranty tracking
|
||||
- Charter mode fields (flag, crew, safety)
|
||||
|
|
@ -132,6 +171,8 @@ Design technical architecture for **sticky daily-use features** (inventory track
|
|||
**Deliverable:** SQL migrations + rollback scripts
|
||||
|
||||
### Agent 10: Sprint Planning
|
||||
**AGENT ID:** S2-H10
|
||||
**
|
||||
**Compile:**
|
||||
- Week 1-4 task breakdown
|
||||
- Dependencies mapped (e.g., DB migrations before API work)
|
||||
|
|
|
|||
|
|
@ -37,9 +37,32 @@ Create sales pitch demonstrating **NaviDocs as sticky daily-use app** (not passi
|
|||
|
||||
---
|
||||
|
||||
|
||||
## Agent Identity & Check-In Protocol
|
||||
|
||||
**YOU ARE:** Sonnet coordinator for Session 3 (UX/Sales)
|
||||
|
||||
**YOUR HAIKU SWARM:** You have 10 Haiku agents available. Use as many as needed (not required to use all 10).
|
||||
|
||||
**AGENT IDENTITY SYSTEM:**
|
||||
When spawning a Haiku agent, assign it an identity: `S3-H01` through `S3-H10`
|
||||
Each agent MUST:
|
||||
1. **Check in** at start: "I am S3-H03, assigned to [task name]"
|
||||
2. **Reference their task** by searching this document for "Agent 3:" (matching their number)
|
||||
3. **Retain identity** throughout execution
|
||||
4. **Report completion** with identity: "S3-H03 complete: [deliverable summary]"
|
||||
|
||||
**TASK DEPENDENCIES:**
|
||||
- Most agents can run in parallel
|
||||
- Agent 10 typically synthesizes results from Agents 1-9 (must wait for completion)
|
||||
|
||||
---
|
||||
|
||||
## Your Tasks (Spawn 10 Haiku Agents in Parallel)
|
||||
|
||||
### Agent 1: Pitch Deck Structure (Sticky Engagement Focus)
|
||||
**AGENT ID:** S3-H01
|
||||
**
|
||||
**Design:**
|
||||
- Slide 1: Problem - "Owners ignore passive doc vaults" (show app abandonment stats)
|
||||
- Slide 2: Solution - "Daily-use app they actually open" (camera, maintenance, inventory)
|
||||
|
|
@ -52,6 +75,8 @@ Create sales pitch demonstrating **NaviDocs as sticky daily-use app** (not passi
|
|||
**Deliverable:** Pitch deck emphasizing daily engagement, NOT passive documentation
|
||||
|
||||
### Agent 2: Demo Script Writer (Daily Use Scenarios)
|
||||
**AGENT ID:** S3-H02
|
||||
**
|
||||
**Create:**
|
||||
- 5-minute demo showing DAILY engagement (not just sale-time docs)
|
||||
- Screen 1: Camera check - "Is my boat OK?" (2 mins)
|
||||
|
|
@ -63,6 +88,8 @@ Create sales pitch demonstrating **NaviDocs as sticky daily-use app** (not passi
|
|||
**Deliverable:** Demo script showing sticky engagement, NOT passive vault
|
||||
|
||||
### Agent 3: ROI Calculator Designer (Inventory Focus)
|
||||
**AGENT ID:** S3-H03
|
||||
**
|
||||
**Build:**
|
||||
- Input fields: boat purchase price, annual upgrades (€5K-€20K typical)
|
||||
- Inventory forgotten at resale: tender €15K, electronics €8K, blinds €3K
|
||||
|
|
@ -74,6 +101,8 @@ Create sales pitch demonstrating **NaviDocs as sticky daily-use app** (not passi
|
|||
**Deliverable:** ROI calculator showing inventory tracking value (primary) + maintenance reminders (secondary)
|
||||
|
||||
### Agent 4: Objection Handling Playbook
|
||||
**AGENT ID:** S3-H04
|
||||
**
|
||||
**Research:**
|
||||
- Common broker objections (from Session 1 research)
|
||||
- Responses with data backing
|
||||
|
|
@ -83,6 +112,8 @@ Create sales pitch demonstrating **NaviDocs as sticky daily-use app** (not passi
|
|||
**Deliverable:** Objection handling guide (Q&A format)
|
||||
|
||||
### Agent 5: Pricing Strategy Presentation
|
||||
**AGENT ID:** S3-H05
|
||||
**
|
||||
**Design:**
|
||||
- Per-yacht pricing model (€50-€200/yacht)
|
||||
- Brokerage bulk pricing (10+ yachts)
|
||||
|
|
@ -92,6 +123,8 @@ Create sales pitch demonstrating **NaviDocs as sticky daily-use app** (not passi
|
|||
**Deliverable:** Pricing slide with 3 tiers
|
||||
|
||||
### Agent 6: Competitive Differentiation
|
||||
**AGENT ID:** S3-H06
|
||||
**
|
||||
**Compile:**
|
||||
- NaviDocs vs 5 top competitors (from Session 1)
|
||||
- Feature comparison table
|
||||
|
|
@ -101,6 +134,8 @@ Create sales pitch demonstrating **NaviDocs as sticky daily-use app** (not passi
|
|||
**Deliverable:** Competitive matrix slide
|
||||
|
||||
### Agent 7: Technical Architecture Visualization
|
||||
**AGENT ID:** S3-H07
|
||||
**
|
||||
**Create:**
|
||||
- System architecture diagram (non-technical)
|
||||
- Integration points (Home Assistant, cameras, offline)
|
||||
|
|
@ -110,6 +145,8 @@ Create sales pitch demonstrating **NaviDocs as sticky daily-use app** (not passi
|
|||
**Deliverable:** Architecture diagram (Mermaid or visual)
|
||||
|
||||
### Agent 8: Case Study Writer
|
||||
**AGENT ID:** S3-H08
|
||||
**
|
||||
**Draft:**
|
||||
- Hypothetical yacht sale scenario
|
||||
- Before NaviDocs: 6 hours documentation prep, €8K warranty miss
|
||||
|
|
@ -119,6 +156,8 @@ Create sales pitch demonstrating **NaviDocs as sticky daily-use app** (not passi
|
|||
**Deliverable:** One-page case study
|
||||
|
||||
### Agent 9: Visual Design System
|
||||
**AGENT ID:** S3-H09
|
||||
**
|
||||
**Define:**
|
||||
- Color palette (nautical theme: blues, whites)
|
||||
- Typography (readable, professional)
|
||||
|
|
@ -128,6 +167,8 @@ Create sales pitch demonstrating **NaviDocs as sticky daily-use app** (not passi
|
|||
**Deliverable:** Design system guide
|
||||
|
||||
### Agent 10: Sales Collateral Package
|
||||
**AGENT ID:** S3-H10
|
||||
**
|
||||
**Compile:**
|
||||
- One-pager (leave-behind document)
|
||||
- Email follow-up template
|
||||
|
|
|
|||
|
|
@ -35,9 +35,32 @@ Create detailed 4-week implementation plan with task breakdown, dependencies, ac
|
|||
|
||||
---
|
||||
|
||||
|
||||
## Agent Identity & Check-In Protocol
|
||||
|
||||
**YOU ARE:** Sonnet coordinator for Session 4 (Implementation Planning)
|
||||
|
||||
**YOUR HAIKU SWARM:** You have 10 Haiku agents available. Use as many as needed (not required to use all 10).
|
||||
|
||||
**AGENT IDENTITY SYSTEM:**
|
||||
When spawning a Haiku agent, assign it an identity: `S4-H01` through `S4-H10`
|
||||
Each agent MUST:
|
||||
1. **Check in** at start: "I am S4-H03, assigned to [task name]"
|
||||
2. **Reference their task** by searching this document for "Agent 3:" (matching their number)
|
||||
3. **Retain identity** throughout execution
|
||||
4. **Report completion** with identity: "S4-H03 complete: [deliverable summary]"
|
||||
|
||||
**TASK DEPENDENCIES:**
|
||||
- Most agents can run in parallel
|
||||
- Agent 10 typically synthesizes results from Agents 1-9 (must wait for completion)
|
||||
|
||||
---
|
||||
|
||||
## Your Tasks (Spawn 10 Haiku Agents in Parallel)
|
||||
|
||||
### Agent 1: Week 1 Task Breakdown
|
||||
**AGENT ID:** S4-H01
|
||||
**
|
||||
**Create:**
|
||||
- Day-by-day tasks for foundation week
|
||||
- Database migrations (warranty tracking, webhooks, notifications)
|
||||
|
|
@ -48,6 +71,8 @@ Create detailed 4-week implementation plan with task breakdown, dependencies, ac
|
|||
**Deliverable:** Week 1 detailed schedule with dependencies
|
||||
|
||||
### Agent 2: Week 2 Task Breakdown
|
||||
**AGENT ID:** S4-H02
|
||||
**
|
||||
**Create:**
|
||||
- Day-by-day tasks for core integrations
|
||||
- Warranty tracking APIs (CRUD + expiration alerts)
|
||||
|
|
@ -58,6 +83,8 @@ Create detailed 4-week implementation plan with task breakdown, dependencies, ac
|
|||
**Deliverable:** Week 2 detailed schedule
|
||||
|
||||
### Agent 3: Week 3 Task Breakdown
|
||||
**AGENT ID:** S4-H03
|
||||
**
|
||||
**Create:**
|
||||
- Day-by-day tasks for automation features
|
||||
- Sale workflow (as-built package generator)
|
||||
|
|
@ -68,6 +95,8 @@ Create detailed 4-week implementation plan with task breakdown, dependencies, ac
|
|||
**Deliverable:** Week 3 detailed schedule
|
||||
|
||||
### Agent 4: Week 4 Task Breakdown
|
||||
**AGENT ID:** S4-H04
|
||||
**
|
||||
**Create:**
|
||||
- Day-by-day tasks for polish & deployment
|
||||
- MLS integration (YachtWorld, Boat Trader APIs)
|
||||
|
|
@ -78,6 +107,8 @@ Create detailed 4-week implementation plan with task breakdown, dependencies, ac
|
|||
**Deliverable:** Week 4 detailed schedule
|
||||
|
||||
### Agent 5: Acceptance Criteria Writer
|
||||
**AGENT ID:** S4-H05
|
||||
**
|
||||
**Define:**
|
||||
- Feature-level acceptance criteria (Given/When/Then format)
|
||||
- API endpoint acceptance tests
|
||||
|
|
@ -87,6 +118,8 @@ Create detailed 4-week implementation plan with task breakdown, dependencies, ac
|
|||
**Deliverable:** Acceptance criteria document (all features)
|
||||
|
||||
### Agent 6: Testing Strategy Designer
|
||||
**AGENT ID:** S4-H06
|
||||
**
|
||||
**Create:**
|
||||
- Unit test plan (service layer, utilities)
|
||||
- Integration test plan (API endpoints, database)
|
||||
|
|
@ -96,6 +129,8 @@ Create detailed 4-week implementation plan with task breakdown, dependencies, ac
|
|||
**Deliverable:** Testing strategy document with tooling recommendations
|
||||
|
||||
### Agent 7: Dependency Mapper
|
||||
**AGENT ID:** S4-H07
|
||||
**
|
||||
**Analyze:**
|
||||
- Task dependencies (Gantt chart format)
|
||||
- Critical path identification
|
||||
|
|
@ -105,6 +140,8 @@ Create detailed 4-week implementation plan with task breakdown, dependencies, ac
|
|||
**Deliverable:** Dependency graph (Mermaid Gantt or visual)
|
||||
|
||||
### Agent 8: API Specification Writer
|
||||
**AGENT ID:** S4-H08
|
||||
**
|
||||
**Document:**
|
||||
- All new API endpoints (OpenAPI 3.0 format)
|
||||
- Request/response schemas
|
||||
|
|
@ -114,6 +151,8 @@ Create detailed 4-week implementation plan with task breakdown, dependencies, ac
|
|||
**Deliverable:** OpenAPI spec file (`api-spec.yaml`)
|
||||
|
||||
### Agent 9: Database Migration Planner
|
||||
**AGENT ID:** S4-H09
|
||||
**
|
||||
**Create:**
|
||||
- Migration scripts (up/down for each change)
|
||||
- Data backups strategy
|
||||
|
|
@ -123,6 +162,8 @@ Create detailed 4-week implementation plan with task breakdown, dependencies, ac
|
|||
**Deliverable:** Migration scripts + rollback guide
|
||||
|
||||
### Agent 10: Deployment Checklist Creator
|
||||
**AGENT ID:** S4-H10
|
||||
**
|
||||
**Compile:**
|
||||
- Pre-deployment checklist (backups, tests, env vars)
|
||||
- Deployment steps (zero-downtime strategy)
|
||||
|
|
|
|||
|
|
@ -45,9 +45,32 @@ Synthesize all intelligence from Sessions 1-4 into comprehensive dossier, valida
|
|||
|
||||
---
|
||||
|
||||
|
||||
## Agent Identity & Check-In Protocol
|
||||
|
||||
**YOU ARE:** Sonnet coordinator for Session 5 (Evidence Synthesis)
|
||||
|
||||
**YOUR HAIKU SWARM:** You have 10 Haiku agents available. Use as many as needed (not required to use all 10).
|
||||
|
||||
**AGENT IDENTITY SYSTEM:**
|
||||
When spawning a Haiku agent, assign it an identity: `S5-H01` through `S5-H10`
|
||||
Each agent MUST:
|
||||
1. **Check in** at start: "I am S5-H03, assigned to [task name]"
|
||||
2. **Reference their task** by searching this document for "Agent 3:" (matching their number)
|
||||
3. **Retain identity** throughout execution
|
||||
4. **Report completion** with identity: "S5-H03 complete: [deliverable summary]"
|
||||
|
||||
**TASK DEPENDENCIES:**
|
||||
- Most agents can run in parallel
|
||||
- Agent 10 typically synthesizes results from Agents 1-9 (must wait for completion)
|
||||
|
||||
---
|
||||
|
||||
## Your Tasks (Spawn 10 Haiku Agents in Parallel)
|
||||
|
||||
### Agent 1: Session 1 Evidence Extraction
|
||||
**AGENT ID:** S5-H01
|
||||
**
|
||||
**Read:**
|
||||
- `intelligence/session-1/session-1-market-analysis.md`
|
||||
- `intelligence/session-1/session-1-citations.json`
|
||||
|
|
@ -61,6 +84,8 @@ Synthesize all intelligence from Sessions 1-4 into comprehensive dossier, valida
|
|||
**Deliverable:** Evidence inventory with citation links
|
||||
|
||||
### Agent 2: Session 2 Technical Claims Validation
|
||||
**AGENT ID:** S5-H02
|
||||
**
|
||||
**Read:**
|
||||
- `intelligence/session-2/session-2-architecture.md`
|
||||
- NaviDocs codebase (`server/db/schema.sql`, `server/routes/*.js`)
|
||||
|
|
@ -74,6 +99,8 @@ Synthesize all intelligence from Sessions 1-4 into comprehensive dossier, valida
|
|||
**Deliverable:** Technical validation report (verified vs unverified claims)
|
||||
|
||||
### Agent 3: Session 3 Sales Material Review
|
||||
**AGENT ID:** S5-H03
|
||||
**
|
||||
**Read:**
|
||||
- `intelligence/session-3/session-3-pitch-deck.md`
|
||||
- `intelligence/session-3/session-3-demo-script.md`
|
||||
|
|
@ -88,6 +115,8 @@ Synthesize all intelligence from Sessions 1-4 into comprehensive dossier, valida
|
|||
**Deliverable:** Sales material validation report
|
||||
|
||||
### Agent 4: Session 4 Implementation Feasibility
|
||||
**AGENT ID:** S5-H04
|
||||
**
|
||||
**Read:**
|
||||
- `intelligence/session-4/session-4-sprint-plan.md`
|
||||
- NaviDocs codebase (all relevant files)
|
||||
|
|
@ -101,6 +130,8 @@ Synthesize all intelligence from Sessions 1-4 into comprehensive dossier, valida
|
|||
**Deliverable:** Feasibility assessment report
|
||||
|
||||
### Agent 5: Citation Database Compilation
|
||||
**AGENT ID:** S5-H05
|
||||
**
|
||||
**Gather:**
|
||||
- All citations from Sessions 1-4
|
||||
- Web sources (with SHA-256 hashes)
|
||||
|
|
@ -115,6 +146,8 @@ Synthesize all intelligence from Sessions 1-4 into comprehensive dossier, valida
|
|||
**Deliverable:** `session-5-citations-master.json`
|
||||
|
||||
### Agent 6: Cross-Session Consistency Check
|
||||
**AGENT ID:** S5-H06
|
||||
**
|
||||
**Analyze:**
|
||||
- Market size claims (Session 1 vs Session 3 pitch deck)
|
||||
- Technical architecture (Session 2 vs Session 4 implementation)
|
||||
|
|
@ -129,6 +162,8 @@ Synthesize all intelligence from Sessions 1-4 into comprehensive dossier, valida
|
|||
**Deliverable:** Consistency audit report
|
||||
|
||||
### Agent 7: Guardian Council Vote Preparation
|
||||
**AGENT ID:** S5-H07
|
||||
**
|
||||
**Prepare:**
|
||||
- Dossier summary for each guardian (tailored to philosophy)
|
||||
- Empiricism: Focus on market research data, evidence quality
|
||||
|
|
@ -144,6 +179,8 @@ Synthesize all intelligence from Sessions 1-4 into comprehensive dossier, valida
|
|||
**Deliverable:** Guardian briefing package
|
||||
|
||||
### Agent 8: Evidence Quality Scoring
|
||||
**AGENT ID:** S5-H08
|
||||
**
|
||||
**Score Each Claim:**
|
||||
- **Primary Source (3 points):** Direct research, codebase analysis
|
||||
- **Secondary Source (2 points):** Industry reports, competitor websites
|
||||
|
|
@ -158,6 +195,8 @@ Synthesize all intelligence from Sessions 1-4 into comprehensive dossier, valida
|
|||
**Deliverable:** Evidence quality scorecard
|
||||
|
||||
### Agent 9: Final Dossier Compiler
|
||||
**AGENT ID:** S5-H09
|
||||
**
|
||||
**Synthesize:**
|
||||
- Executive summary (2 pages max)
|
||||
- Market analysis (Session 1 findings)
|
||||
|
|
@ -174,6 +213,8 @@ Synthesize all intelligence from Sessions 1-4 into comprehensive dossier, valida
|
|||
**Deliverable:** `NAVIDOCS_INTELLIGENCE_DOSSIER.md`
|
||||
|
||||
### Agent 10: Guardian Council Vote Coordinator
|
||||
**AGENT ID:** S5-H10
|
||||
**
|
||||
**Execute:**
|
||||
- Submit dossier to Guardian Council
|
||||
- Collect votes from all 20 guardians
|
||||
|
|
|
|||
26
add_agent_ids.py
Normal file
26
add_agent_ids.py
Normal file
|
|
@ -0,0 +1,26 @@
|
|||
import re
|
||||
|
||||
files = [
|
||||
('CLOUD_SESSION_1_MARKET_RESEARCH.md', 'S1'),
|
||||
('CLOUD_SESSION_2_TECHNICAL_INTEGRATION.md', 'S2'),
|
||||
('CLOUD_SESSION_3_UX_SALES_ENABLEMENT.md', 'S3'),
|
||||
('CLOUD_SESSION_4_IMPLEMENTATION_PLANNING.md', 'S4'),
|
||||
('CLOUD_SESSION_5_SYNTHESIS_VALIDATION.md', 'S5'),
|
||||
]
|
||||
|
||||
for filename, session_id in files:
|
||||
with open(filename, 'r') as f:
|
||||
content = f.read()
|
||||
|
||||
# Add agent IDs to each "### Agent X:" section
|
||||
for i in range(1, 11):
|
||||
pattern = f'### Agent {i}:'
|
||||
replacement = f'### Agent {i}:\n**AGENT ID:** {session_id}-H{i:02d}'
|
||||
content = re.sub(pattern, replacement, content)
|
||||
|
||||
with open(filename, 'w') as f:
|
||||
f.write(content)
|
||||
|
||||
print(f"Updated {filename} with {session_id} agent IDs")
|
||||
|
||||
print("\nAll files updated!")
|
||||
48
add_identity_protocol.py
Normal file
48
add_identity_protocol.py
Normal file
|
|
@ -0,0 +1,48 @@
|
|||
protocol = '''
|
||||
## Agent Identity & Check-In Protocol
|
||||
|
||||
**YOU ARE:** Sonnet coordinator for Session {session_num} ({session_name})
|
||||
|
||||
**YOUR HAIKU SWARM:** You have 10 Haiku agents available. Use as many as needed (not required to use all 10).
|
||||
|
||||
**AGENT IDENTITY SYSTEM:**
|
||||
When spawning a Haiku agent, assign it an identity: `{session_id}-H01` through `{session_id}-H10`
|
||||
Each agent MUST:
|
||||
1. **Check in** at start: "I am {session_id}-H03, assigned to [task name]"
|
||||
2. **Reference their task** by searching this document for "Agent 3:" (matching their number)
|
||||
3. **Retain identity** throughout execution
|
||||
4. **Report completion** with identity: "{session_id}-H03 complete: [deliverable summary]"
|
||||
|
||||
**TASK DEPENDENCIES:**
|
||||
- Most agents can run in parallel
|
||||
- Agent 10 typically synthesizes results from Agents 1-9 (must wait for completion)
|
||||
|
||||
---
|
||||
|
||||
'''
|
||||
|
||||
sessions = [
|
||||
('CLOUD_SESSION_2_TECHNICAL_INTEGRATION.md', 2, 'Technical Architecture', 'S2'),
|
||||
('CLOUD_SESSION_3_UX_SALES_ENABLEMENT.md', 3, 'UX/Sales', 'S3'),
|
||||
('CLOUD_SESSION_4_IMPLEMENTATION_PLANNING.md', 4, 'Implementation Planning', 'S4'),
|
||||
('CLOUD_SESSION_5_SYNTHESIS_VALIDATION.md', 5, 'Evidence Synthesis', 'S5'),
|
||||
]
|
||||
|
||||
for filename, num, name, sid in sessions:
|
||||
with open(filename, 'r') as f:
|
||||
content = f.read()
|
||||
|
||||
# Find where to insert (before "## Your Tasks")
|
||||
marker = '## Your Tasks'
|
||||
if marker in content:
|
||||
parts = content.split(marker, 1)
|
||||
formatted_protocol = protocol.format(session_num=num, session_name=name, session_id=sid)
|
||||
new_content = parts[0] + formatted_protocol + marker + parts[1]
|
||||
|
||||
with open(filename, 'w') as f:
|
||||
f.write(new_content)
|
||||
print(f"Added protocol to {filename}")
|
||||
else:
|
||||
print(f"WARNING: Could not find marker in {filename}")
|
||||
|
||||
print("Identity protocols added!")
|
||||
31
fix_agent_format.py
Normal file
31
fix_agent_format.py
Normal file
|
|
@ -0,0 +1,31 @@
|
|||
import re
|
||||
|
||||
files = [
|
||||
'CLOUD_SESSION_1_MARKET_RESEARCH.md',
|
||||
'CLOUD_SESSION_2_TECHNICAL_INTEGRATION.md',
|
||||
'CLOUD_SESSION_3_UX_SALES_ENABLEMENT.md',
|
||||
'CLOUD_SESSION_4_IMPLEMENTATION_PLANNING.md',
|
||||
'CLOUD_SESSION_5_SYNTHESIS_VALIDATION.md',
|
||||
]
|
||||
|
||||
for filename in files:
|
||||
with open(filename, 'r') as f:
|
||||
content = f.read()
|
||||
|
||||
# Fix duplicate AGENT ID lines (keep only first occurrence)
|
||||
content = re.sub(r'(\*\*AGENT ID:\*\* \S+-H\d+)[^\n]*\n\*\*AGENT ID:\*\* (\S+-H\d+)', r'\1', content)
|
||||
|
||||
# Fix broken headers like "### Agent 1:\n**AGENT ID:** S1-H01 Recreational Boat..."
|
||||
# Should be "### Agent 1: Recreational Boat...\n**AGENT ID:** S1-H01"
|
||||
content = re.sub(
|
||||
r'### Agent (\d+):\s*\n\*\*AGENT ID:\*\* (\S+-H\d+)\s+(.+?)(?=\n\*\*)',
|
||||
r'### Agent \1: \3\n**AGENT ID:** \2\n**',
|
||||
content
|
||||
)
|
||||
|
||||
with open(filename, 'w') as f:
|
||||
f.write(content)
|
||||
|
||||
print(f"Fixed {filename}")
|
||||
|
||||
print("All formatting fixed!")
|
||||
Loading…
Add table
Reference in a new issue