Agent & Instrument Diagram
Template: A&ID | Tight Five: Performance
How do human and AI orchestrate to run the Dreamineering loop?
Agents
| Agent | Type | Fuel | Strength | Limitation |
|---|---|---|---|---|
| Wik | Human | Intention, experience, taste | Judgment, voice, relationships, final gate | Time, energy, one person |
| Claude | Phygital | Prompts, context, skills | Speed, consistency, cross-linking, validation | No memory across sessions, no measurement |
| The Site | Infrastructure | Content, architecture | Compounds — each page makes others more valuable | Can't measure itself, can't reach people |
Instruments
| Instrument | Function | A&ID Role |
|---|---|---|
| CLAUDE.md | Encodes system context, rules, routes | Controller setpoint |
Rules (.claude/rules/) | Always-loaded constraints | Gauge thresholds |
Hooks (.claude/hooks/) | Automated enforcement on file edit | Feedback actuator |
Skills (.claude/skills/) | On-demand capability modules | Process recipes |
Templates (/docs/pictures/templates/) | Standardized thinking patterns | Instrument calibration |
| Git + CI/CD | Version control, build validation | Quality valve |
| Analytics (not built) | Engagement, traversal, return rate | The missing gauge |
Feedback Loops
Content Loop (primary)
Current state: The loop runs from Wik through Claude to the Site, but the return path (Analytics → Reflection) is broken. Force is applied. Results are not compared to expectations. The dashed node is the gap.
Full A&ID visual language is being built in a separate project — proper P&ID symbols for agents, instruments, and control loops.
Skill Loop (meta)
Current state: Running. Three lessons encoded (content flow, skill execution, design verification). The system learns from its own failures.
Evidence Loop (not running)
Current state: Defined in META-POSTS.md Part D. Zero entries. 17 articles shipped with no recorded learnings. Entire loop is dashed — none of it is running.
Orchestration Table
Who does what at each VVFL station:
| VVFL Station | Human | AI | Instrument |
|---|---|---|---|
| Capture | Notices friction, selects ideas | Generates variations, researches | Hopper (idea backlog) |
| Priorities | Judges what matters | Scores against criteria | Skills (quality gates) |
| Attention | Directs focus, sets intention | Executes at speed | Rules (constraints) |
| Value | Selects voice, calibrates tone | Writes drafts from each lens | Templates (structure) |
| Systems | Designs architecture | Cross-links, validates | Hooks (enforcement) |
| Standards | Defines thresholds | Checks mechanically | Git + CI/CD (validation) |
| Distribute | Owns relationships, channels | Generates distribution assets | Site + LinkedIn (reach) |
| Reflect | Asks better questions | Identifies patterns | Analytics (the gauge) |
| Evolve | Changes the game | Adapts skills and rules | Memory (learning) |
The Gap
The system has agents and instruments for every VVFL station except one: Reflect has no instrument. Analytics is the missing gauge. Without it, the controller (Wik's reflection) has nothing to read.
Apply force ──→ Compare results to expectations ──→ Amplify or retreat
✓ ✗ (no gauge) ✗ (no signal)
The five maps are now filled in. The next hard dependency is the gauge.
Gate: All five maps complete. The pattern is clear. The missing piece is measurement.
| Map | Status | Key Finding |
|---|---|---|
| Outcome | Filled | Success = each page makes others more valuable |
| Value Stream | Filled | Meta pipeline at 5-10% efficiency; docs at 80% |
| Dependencies | Filled | Analytics and evidence loop are the two hard blockers |
| Capabilities | Filled | Core at 3.0, supporting at 1.0 — analytics is P1 gap |
| Agent & Instrument | Filled | Every VVFL station has instruments except Reflect |
Five maps. One answer: build the gauge.