How do agents orchestrate — and what instruments verify the work?
AGENT & INSTRUMENT DIAGRAM: PROMPT DECK
════════════════════════════════════════════════════════════
AGENTS (Yang — who applies force)
─────────────────────────────────────────────────────────
User (Human) ········ Fills grid, reflects, returns weekly, shares, decides priorities
Deck Engine (System) · Persists state, highlights gaps, takes snapshots, serves templates
AI Coach (AI, V3) ··· Suggests questions for gaps, coaches through dimensions
INSTRUMENTS (Yin — what verifies and rewards)
─────────────────────────────────────────────────────────
Gap Highlighter ······ Visualizes empty cells as strategy, not failure
Snapshot Comparator ·· Shows grid evolution over time (this week vs last)
Mode Lens ············ Toggles Pep Talk (inner) / Pitch (outer) perspective
Scale Selector ······· Zooms Personal / Venture / Industry / Portfolio
Kill Date Counter ···· Time pressure on validation milestones
PROTOCOLS (data + value + decision flows)
─────────────────────────────────────────────────────────
┌──────────────────────────────────────────────┐
│ THE FILL LOOP │
│ │
│ FILL ──→ GAPS ──→ QUESTIONS ──→ │
│ │ │ │ │
│ │ Gap User │
│ │ Highlighter reflects │
│ │ │ │ │
│ ──→ RESEARCH ──→ UPDATE ──→ COMPARE │
│ │ │ │ │
│ Domain Deck Snapshot │
│ Content Engine Comparator │
│ │ │ │ │
│ └── FEEDBACK ┘ │ │
│ │ │ │
│ Grid sharpens Evolution visible │
└──────────────────────────────────────────────┘
FEEDBACK LOOPS
─────────────────────────────────────────────────────────
Loop 1: SESSION (per fill)
┌─ Fill cell → Gap Highlighter → See adjacent gap → Fill next → Until complete ┐
└──────────────────────────────────────────────────────────────────────────── ──┘
Loop 2: WEEKLY (return)
┌─ Return → Snapshot → Compare to previous → Update cells → Better grid ─┐
└────────────────────────────────────────────────────────────────────────┘
Loop 3: MODE (per review)
┌─ Pep Talk → Pitch → See inner/outer misalignment → Refine → Pep Talk ─┐
└────────────────────────────────────────────────────────────────────────┘
Loop 4: COMPOUND (monthly)
┌─ Multiple snapshots → Pattern recognition → Deeper insight → New five ─┐
│ Stale grid, no snapshots? → Decision: re-engage or archive │
└────────────────────────────────────────────────────────────────────────┘
HORIZON FLOW
─────────────────────────────────────────────────────────
H1: Prompt Deck (this PRD)
│ what matters, where gaps are, how priorities evolve
▼
H2: Time + Mind
│ closes gap between intention (what grid says) and action (what happened)
▼
H3: AI Coaching
agent helps fill what you can't see alone
════════════════════════════════════════════════════════════
Agent Roster
| Agent | Type | Force Applied | Verification |
|---|---|---|---|
| User | Human | Fill, reflect, return, share, decide priorities | Grid completion rate, D7 return, snapshot count |
| Deck Engine | System | Persist, highlight, snapshot, template, mode switch | Data integrity, load time, session continuity |
| AI Coach | AI (V3) | Suggest questions for gaps, coach through 5P dimensions | User satisfaction, fill rate improvement |
Instrument Registry
| Instrument | Measures | Threshold | Action on Fail | Outcome Map Link |
|---|---|---|---|---|
| Gap Highlighter | Empty cells per grid | Visual at any count | Highlight grows more prominent | Enables O3 (completion > 60%) |
| Snapshot Comparator | Grid delta between snapshots | Change in ≥3 cells per week | Prompt: "Nothing changed — still aligned?" | Enables O2 (D7 return > 35%) |
| Mode Lens | Pep Talk / Pitch alignment gap | Cells that differ between modes | Highlight misalignment for reflection | Enables O3 (completion > 60%) |
| Scale Selector | Active scale level | At least 1 scale used | Default to Personal if unused | Enables O1 (10 users fill) |
| Kill Date Counter | Days to kill date | 0 remaining | Force decision: extend with evidence or stop | Guards all outcomes |
Feedback Loop Quality
| Loop | Frequency | Sensor | Actuator | Latency |
|---|---|---|---|---|
| Session | Per fill | Gap Highlighter | User fills next cell | Instant |
| Weekly | 7 days | Snapshot Comparator | User updates stale cells | Minutes |
| Mode | Per review | Mode Lens | User refines inner/outer alignment | Minutes |
| Compound | Monthly | Multiple snapshots | User recognises patterns, redefines five | Days |
Activation Sequence
From the Dependency Map — when does each agent come online?
| Phase | What Resolves | Agent State | User Experience |
|---|---|---|---|
| Now | Prototype exists | Deck Engine: read-only prototype | User sees the grid, can't persist |
| Sprint 0 (10d) | Auth + persistence + cell editor + mode | Deck Engine: fills persist | User fills, grid survives sessions |
| Sprint 1 (5d) | Card View + Scale + Highlighting | Deck Engine: multi-pattern + lenses | User sees gaps, mobile works |
| Sprint 2 (5d) | Snapshots + templates + share | Deck Engine: memory + distribution | User compares, shares, compounds |
| V3 (future) | AI coaching integration | AI Coach: online | Agent helps fill gaps user can't see |
The instrument doesn't replace the human. Each version adds one capability layer. V1 structures. V2 adds memory. V3 adds voice. The human stays in the loop because the grid is meaningless without their judgment of what matters.
Gate
Before executing:
- Every agent named — YES (3: User, Deck Engine, AI Coach)
- Every instrument named — YES (5 with thresholds and outcome map links)
- Feedback loops explicit — YES (4 loops at different frequencies)
- Horizon data flows declared — YES (H1 → H2 → H3)
- Activation sequence links dependency resolution to capability — YES (5 phases)
Context
- Capability Map — Previous: what can we do
- A&ID Template — The empty pattern
- Spec: Protocols — Feature map, commissioning, build sequence