boc/docs/design/LANDVEX_INTELLIGENCE_LAB.md

LANDVEX INTELLIGENCE LAB

Internal Development Environment for Control Intelligence

Version	1.0
Status	SPECIFICATION
Purpose	Build, test, and verify LandveX Control Intelligence before production

---

Core Principles

LandveX Intelligence Lab does not produce AI models. It produces verified Control Intelligence.

This is an internal tool. Never a customer product.

All artifacts are immutable and versioned.

• Raw images are never modified
• Annotations are versioned
• Models are versioned
• Evaluation reports are versioned
• Decision Cases are versioned
• Replay results are saved as new artifacts

Every change must be traceable to a specific experiment, model version, dataset, and decision.

Quality Standards for Government & Public Sector

LandveX serves municipalities, government agencies, and public infrastructure owners. The Intelligence Lab must be built to standards that satisfy public sector procurement, audit, and compliance requirements.

Code Quality

Requirement	Standard	Rationale
Type Safety	Strict TypeScript or Rust	Eliminates entire classes of runtime errors
Test Coverage	≥80% unit, ≥90% critical paths	Public sector demands verifiable quality
Static Analysis	ESLint + SonarQube + Snyk	Catch issues before deployment
Code Review	All changes require 2 approvals	No unreviewed code in production
Documentation	Every public API documented	Procurement requires documentation

Security

Requirement	Standard	Rationale
Authentication	OAuth 2.0 + MFA	Government security requirements
Authorization	RBAC with audit logging	Who did what, when
Encryption	AES-256 at rest, TLS 1.3 in transit	Data protection regulations
Secrets Management	HashiCorp Vault or AWS Secrets Manager	No secrets in code
Vulnerability Scanning	Weekly automated scans	Continuous security

Audit & Compliance

Requirement	Standard	Rationale
Immutable Audit Log	Append-only, signed logs	Tamper-evident history
Data Retention	Configurable per jurisdiction	GDPR, local laws
Export Capability	Full data export in standard formats	Freedom of information requests
Accessibility	WCAG 2.1 AA	Public sector requirement
Localization	Swedish + English	Government customers

Infrastructure

Requirement	Standard	Rationale
Deployment	GitOps (ArgoCD/Flux)	Reproducible, auditable deployments
Observability	OpenTelemetry + structured logging	Debug production issues
Backup	3-2-1 rule, tested restores	Business continuity
Disaster Recovery	RPO < 1h, RTO < 4h	Critical infrastructure
Scalability	Horizontal scaling, stateless services	Handle peak loads

AI/ML Specific

Requirement	Standard	Rationale
Model Versioning	MLflow or similar	Track every model version
Data Lineage	Full provenance for all datasets	Explain model decisions
Bias Testing	Automated fairness metrics	Prevent discriminatory outcomes
Explainability	SHAP or LIME for all predictions	Right to explanation
Model Cards	Documented for every model	Transparency

Development Practices

Requirement	Standard	Rationale
Git Workflow	Trunk-based or GitFlow	Clear, auditable history
CI/CD	Automated testing, staging, production	No manual deployments
Infrastructure as Code	Terraform or Pulumi	Version-controlled infrastructure
Dependency Management	Renovate or Dependabot	Keep dependencies updated
Incident Response	Documented runbooks	Handle outages systematically

Product Architecture

quiXzoom
    ↓
Observations
    ↓
LandveX Intelligence Lab
    ↓
Improved Models
    ↓
LandveX
    ↓
Better Decisions
    ↓
Feedback
    ↓
Intelligence Lab

Two products:

• quiXzoom — produces observations
• LandveX — produces decisions
• Intelligence Lab — the factory that improves both

---

Repository

landvex-intelligence-lab

Separate from:

• quixzoom-app
• landvex-web
• aamos-core

---

Architecture

LandveX Intelligence Lab
│
┌─────────────────┼─────────────────┐
│                 │                 │
Developer UI    Training API    Experiment API
│                 │                 │
└─────────────────┴─────────────────┘
│
Event Bus / Queue
│
─────────────────────────────────────────────────────
Storage Layer
Images │ Videos │ Missions │ Models │ Logs
S3/R2 Buckets + PostgreSQL + Neo4j
─────────────────────────────────────────────────────
│
Processing Pipelines

Navigation

Dashboard
├── Models
├── Datasets
├── Annotations
├── Training
├── Evaluation
├── Decision Cases
├── Replay
├── Validation
├── Promote Model
└── Settings

---

Dashboard

Shows AI status, not business data.

┌─────────────────────────────────────┐
│ Datasets                            │
│ Healthy: 12                         │
│ Needs Review: 3                     │
│ Corrupted: 0                        │
├─────────────────────────────────────┤
│ Training Jobs                       │
│ Running: 2                          │
│ Queued: 1                           │
│ Completed: 47                       │
│ Failed: 0                           │
├─────────────────────────────────────┤
│ Decision Cases                      │
│ Validated: 23                       │
│ Pending: 5                          │
│ Rejected: 2                         │
├─────────────────────────────────────┤
│ Replay Jobs                         │
│ Ready: 8                            │
│ Running: 1                          │
│ Finished: 34                        │
└─────────────────────────────────────┘

---

Mission Replay

Click through the entire chain:

Video → Frame → Bounding boxes → Detected objects → Evidence → Finding → Decision → Business Impact

---

Annotation

┌─────────┬─────────────┬──────────────┐
│ Video   │ AI Suggestion│ Manual       │
│         │              │ Correction   │
├─────────┼─────────────┼──────────────┤
│         │ Object:      │ Correct?     │
│         │ Road Crack   │ YES / NO     │
│         │ Confidence:  │              │
│         │ 82%          │ Severity:    │
│         │              │ Low / Medium │
│         │              │ / High       │
└─────────┴─────────────┴──────────────┘

---

Decision Cases

The most important asset.

Not images. Not videos. Not AI models.

But:

Observation → Evidence → Finding → Decision → Outcome → Learning

After a few years, hundreds of thousands of verified Decision Cases. Not just a training dataset — a library of how real observations lead to real decisions and real outcomes.

Case #4232
├── Reality
├── Observation
├── Evidence
├── Finding
├── Decision
├── Outcome
└── Learning

All cases playable.

---

Benchmark

Compare models:

Model	Precision	Recall	F1	Latency	Decision Accuracy
YOLO v8	0.89	0.87	0.88	45ms	—
Grounding DINO	0.91	0.85	0.88	120ms	—
SAM	0.88	0.90	0.89	200ms	—
Custom	0.92	0.91	0.915	60ms	0.87

---

Replay

Find regressions:

Mission 213
├── Play
├── Show AI
├── Show Human Annotation
├── Differences
├── New Model
└── Old Model

---

Validation

Field Trials
Scenario Tests
Decision Tests
Evidence Tests
Golden Failures
Regression Tests

---

Promote Model (Not Deploy)

Development → Validation → Pilot → Production

Not "Deploy". "Promote Model".

---

Experiments

Experiments
├── EP-1.0
├── DS-001
├── DS-002
├── DS-003
├── Field Trials
└── Metrics

Link experiment protocol to real development and validation data.

---

Processing Pipelines

1. Ingestion Pipeline

Input: Images, video, GPS, EXIF, metadata Checks: Checksums, versioning Output: Raw Dataset

2. Dataset Pipeline

Input: Raw Dataset Checks: Sort, deduplicate, quality control, resolution, blur detection, GPS validation Output: Validated Dataset

3. Annotation Pipeline

Input: Validated Dataset Process: AI suggestions, manual correction, label versions, consensus Output: Verified Dataset

4. Training Pipeline

Input: Verified Dataset Process: Start training, hyperparameters, checkpoints, GPU jobs Output: Model Artifact

5. Evaluation Pipeline

Input: Model Artifact Metrics: Precision, recall, F1, decision accuracy, regression Output: Evaluation Report

6. Replay Pipeline

Input: Old missions, Model v14, Model v15 Process: Run both models, compare differences Output: Regression Report

7. Decision Validation Pipeline

Input: Observation Process: Full chain — Observation → Evidence → Finding → Decision → Business Impact Output: Decision Validation Report

---

Bucket Structure

raw-images/
raw-video/
missions/
datasets/
annotations/
training/
models/
replays/
evaluation/
decision-cases/
field-trials/
exports/
archives/

All content is versioned:

model-v14/
model-v15/
model-v16/

---

AI Job Queue

All jobs are asynchronous:

Upload → Queue → Worker → GPU → Storage → Notification

Not synchronous API calls.

---

What This Tool Collects

• Model training
• Annotation
• Datasets
• Replay
• Decision chains
• Validation
• Regression tests
• Experiments
• Model promotion

---

New Developer Experience

A new AI engineer should open the repo and within minutes understand:

"This is the tool where we build, test, and verify LandveX Control Intelligence before anything reaches production."

---

Relationship to Principles

• All development in Git
• All experiments reproducible
• All models traceable from training to validation to production
• Version control and traceability

---

MVP Milestone: "First Verified Decision"

Definition: A developer can:

1. Film a real object with quiXzoom
2. Import material to Intelligence Lab
3. Review and correct AI interpretation
4. Create a Decision Case
5. Follow the entire chain from observation to decision with full traceability

When this works, you have the first complete, verifiable Control Intelligence pipeline.

Development Phases

Phase 1 — Essential (for pilot missions)

Feature	Purpose
Ingestion	Upload images/video, show metadata (GPS, time, device), store raw data immutably
Dataset Explorer	Browse missions, filter, search, open a mission
Annotation	AI suggestions, manual correction, version history
Decision Case Viewer	Observation → Evidence → Finding → Decision → Business Impact → Learning

This is the heart.

Phase 2 — Scale (when running many missions)

Feature	Purpose
Replay	Compare model versions on same mission
Benchmark	Model comparisons
Evaluation	Regression tests

Phase 3 — Advanced (when having multiple models)

Feature	Purpose
GPU Jobs	Training queue
Hyperparameter Runs	Automated experiments
Model Promotion	Development → Validation → Pilot → Production
Canary Releases	Gradual rollout

New Areas

Data Quality

Before training anything:

Images
├── Healthy
├── Blurred
├── Duplicate
├── Wrong GPS
├── Night
├── Rain
└── Occluded

Coverage:

Roads, Buildings, Signs, Drainage, Vegetation

Quickly shows why a model performs well or poorly.

Decision Analytics

Not AI metrics. Decision metrics.

Metric	Question
Acceptance Rate	How many recommendations were accepted?
Ignore Rate	How many were ignored?
Accuracy	How many proved correct?
Insufficient Evidence	How many lacked enough evidence?
Data Collection Value	How often did "Collect more data" lead to a better decision?

Closer to LandveX business value than traditional AI metrics.

---

ändringshistoria

Version	Datum	Beskrivning
1.0	2026-07-02	Initial specification for LandveX Intelligence Lab
1.1	2026-07-02	Added architecture, pipelines, immutability
1.2	2026-07-02	Added MVP milestone, development phases, Data Quality, Decision Analytics
1.3	2026-07-02	Added Government Quality Standards for public sector compliance

---

STATUS

SPECIFICATION — Awaiting development decision

Next decision: Begin MVP implementation (Phase 1: Ingestion, Dataset Explorer, Annotation, Decision Case Viewer) or wait for further input.