docs: Field Trial Log + Decision KPIs + MEMORY update

- Created FIELD_TRIAL_LOG.md — observation protocol for real customer cases
  - Log entry template with 10 fields
  - Two example entries (accepted and rejected decisions)
  - Questions the log answers: adoption, accuracy, calibration, rejection analysis
  - Future KPIs: Decision Adoption Rate, Decision Accuracy, Time to Decision

- Updated MEMORY.md with Control Intelligence & Decision Model section
  - Decision Pipeline v1.0 summary
  - Decision Object v1.0 (STRUCTURE FROZEN)
  - Status: VALIDATED FOR FIELD TRIALS
  - Three target customer cases
  - Future KPIs
  - Key principle: No more modeling until first real customer case

- Added Decision Adoption Rate and Decision Accuracy as future product KPIs
  - Not implemented yet — start collecting data now, calculate later
  - Decision Adoption = accepted / total recommendations
  - Decision Accuracy = correct / total decisions

Rationale: Stop modeling, start observing. First real customer case
will teach more than the last twenty documents combined.

MEMORY.md

@@ -881,3 +881,49 @@ Mätvärden:
 - Leverabler: Engineering Readiness Score (viktad), Policy Enforcement, STOP Register (med risk), Release Gate, Meta-Rules
 - Exit Criteria: Varje STOP är eliminerad, har dispens, eller ersatts av kontrollerad process
 - EOS-regel: "EOS får aldrig blockera något utan att kunna förklara exakt varför och vilken minsta åtgärd som krävs för att häva blockeringen."
+
+---
+
+## 11. CONTROL INTELLIGENCE & DECISION MODEL (2026-07-02)
+
+**LandveX produces Control Intelligence, not AI analysis.**
+
+AI is implementation. Control Intelligence is the product.
+
+### Decision Pipeline v1.0
+```
+Reality → Observation → Evidence → Finding → Decision → Action → Business Impact → Learning
+```
+
+**Seven steps with input/transformation/output/owner.**
+
+### Decision Object v1.0 (STRUCTURE FROZEN)
+- 7 fields: Decision, Why, Evidence, Confidence, Consequence, Action, Business Impact
+- Changes require v1.1 + migration note + revalidation
+- Implementation/algorithms NOT frozen
+
+### Status: VALIDATED FOR FIELD TRIALS
+- 8 scenarios reviewed (6 PASS, 2 OBSERVATION, 0 FAIL)
+- Decision Invariance Test: PASS
+- Evidence Variation Test: PASS
+- Explainability Invariance Test: PASS
+- Ready for real customer testing, not production truth
+
+### Three Target Customer Cases
+1. Municipality — "Inspect or wait?" (Maintenance prioritization)
+2. Property Owner — "Repair now or plan later?" (Cost vs risk)
+3. Contractor/Operations — "Which action first?" (Operational planning)
+
+### Future KPIs (collect now, calculate later)
+- **Decision Adoption Rate** = Accepted recommendations / Total recommendations
+- **Decision Accuracy** = Correct decisions / Total decisions
+- **Time to Decision** = Minutes from login to decision
+
+### Key Principle
+**No more modeling until first real customer case has run through entire pipeline.**
+
+### Files
+- `docs/design/DECISION_MODEL_v1.0.md` — Decision Model
+- `docs/design/DECISION_PIPELINE_v1.0.md` — Decision Pipeline
+- `docs/design/DECISION_MODEL_REVIEW.md` — Manual Review Results
+- `docs/design/FIELD_TRIAL_LOG.md` — Observation Protocol