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.
2026-07-02 12:19:10 +00:00
parent c8819109db
commit 1c4158c373
2 changed files with 159 additions and 0 deletions
@@ -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
@@ -0,0 +1,113 @@
+# FIELD TRIAL LOG
+
+**Observation Protocol for Decision Model Validation**
+
+| | |
+|---|---|
+| **Version** | 1.0 |
+| **Status** | ACTIVE |
+| **Purpose** | Collect raw data from real customer cases |
+
+---
+
+## Log Entry Template
+
+| Field | Example | Notes |
+|-------|---------|-------|
+| **Date** | 2026-07-15 | |
+| **Customer Type** | Municipality / Property Owner / Contractor | |
+| **Decision** | Inspect Road A12 | What the system recommended |
+| **Decision Accepted** | Yes / No | Did the user accept? |
+| **Action Executed** | Yes / No / Pending | Was the action carried out? |
+| **Outcome** | Crack confirmed | What actually happened |
+| **Time to Decision** | 3 minutes | How long from login to decision |
+| **User Feedback** | "We trusted the recommendation." | Verbatim or summary |
+| **Confidence** | 87% | System confidence at decision time |
+| **Notes** | Free text | Anything else observed |
+
+---
+
+## Example Entries
+
+### Entry 1
+
+| Field | Value |
+|-------|-------|
+| Date | 2026-07-15 |
+| Customer Type | Municipality |
+| Decision | Inspect Road A12 |
+| Decision Accepted | Yes |
+| Action Executed | Yes |
+| Outcome | Crack confirmed, repaired within 14 days |
+| Time to Decision | 3 minutes |
+| User Feedback | "We trusted the recommendation." |
+| Confidence | 87% |
+| Notes | User clicked through Explainability chain |
+
+### Entry 2
+
+| Field | Value |
+|-------|-------|
+| Date | 2026-07-16 |
+| Customer Type | Property Owner |
+| Decision | Repair facade immediately |
+| Decision Accepted | No |
+| Action Executed | No |
+| Outcome | Deferred, user chose to wait |
+| Time to Decision | 5 minutes |
+| User Feedback | "Too expensive right now." |
+| Confidence | 92% |
+| Notes | Confidence was high but user rejected due to cost |
+
+---
+
+## Questions This Log Answers
+
+After collecting entries:
+
+- Were recommendations accepted? (Decision Adoption Rate)
+- Were actions executed? (Execution Rate)
+- Did outcomes match predictions? (Decision Accuracy)
+- Was confidence reasonable? (Calibration)
+- Which recommendations were ignored? (Rejection Analysis)
+- How long did decisions take? (Time to Decision)
+
+---
+
+## Future KPIs
+
+### Decision Adoption Rate
+
+```
+Recommendations accepted
+────────────────────────
+Total recommendations
+```
+
+Example: 72 of 100 = **72%**
+
+### Decision Accuracy
+
+```
+Decisions that proved correct
+─────────────────────────────
+Total decisions
+```
+
+Example: 65 of 72 executed = **90%**
+
+**Note:** These require months of data. Start collecting now, calculate later.
+
+---
+
+## Status
+
+**ACTIVE — Awaiting first customer case**
+
+---
+
+## ändringshistoria
+
+| Version | Datum | Beskrivning |
+|---------|-------|-------------|
+| 1.0 | 2026-07-02 | Initial field trial log template |