Introduction to AIMM Index
What is AIMM Index?
AIMM Index is a continuous compliance and governance twinning platform. Instead of producing a governance report once per quarter, AIMM Index recomputes each organisation's AI Maturity Score (AI$M) on every telemetry event — translating your AI model's real-time behaviour into an auditable maturity level from L0 to L6.
AIMM Level Scale (L0–L6)
| Level | Label | AI$M Range | What it means |
|---|---|---|---|
| L0 | Ad Hoc | 0–19% | No consistent AI governance |
| L1 | Aware | 20–34% | Awareness exists, processes informal |
| L2 | Repeatable | 35–49% | Some repeatable controls |
| L3 | Managed | 50–64% | Measured and tracked |
| L4 | Optimised | 65–74% | Proactive continuous improvement |
| L5 | Advanced | 75–84% | Systematic, data-driven governance |
| L6 | Production Ready | 85–100% | Fully governed, audit-ready |
Login & Account Access
Signing In
Role Capabilities
| Role | Register twins | Telemetry | Calibrate | Annexure | Admin page | Chat |
|---|---|---|---|---|---|---|
| Viewer | ✗ | ✗ | ✗ | ✓ | ✗ | ✓ |
| Operator | ✗ | ✓ | ✗ | ✓ | ✗ | ✓ |
| Auditor | ✗ | ✓ | ✓ | ✓ | ✓ | ✓ |
| Admin | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ |
Two Separate Frontend Files
| URL | Purpose |
|---|---|
| app.aimmindex.com/ (index.html) | Public landing page — product info, guide, pricing, registration |
| app.aimmindex.com/dashboard.html | RBAC command-centre — live KPIs, Growth Comparison, Annexure, Certification |
| app.aimmindex.com/console.html | Operational console — register twins, telemetry, calibrate, agent chat |
Compliance Twins
What is a Compliance Twin?
A compliance twin is a persistent digital governance record for one AI-enabled organisation or system. Each twin holds: its confusion matrix (TP/TN/FP/FN), system integrity parameters, a calibration baseline, the full AI$M time-series (aism_history), and the active domain agent's latest findings.
Registering a Twin
org_id (unique, no spaces), name, domain (determines which agent monitors this twin — see Domain Agents section).domain value selects the monitoring agent for this twin's lifetime. Choose carefully: "Semiconductor Fab", "HealthTech", "Retail MSME", "Logistics", "Automotive", "EV", "EduTech", "Agri" — see the keyword map in the Domain Agents section.Calibrating a Twin
Calibration locks the current AI$M as the baseline. Drift alerts only fire after calibration.
Twin States
| State | twin_type | Meaning |
|---|---|---|
| Uncalibrated | static | Registered, may have telemetry, no baseline set. Drift not tracked. |
| Calibrated/Live | live | Baseline locked. Drift tracked. Annexure shows full history. |
Submitting Telemetry
Telemetry Metric Reference
| metric_type | Measures | Component | Range |
|---|---|---|---|
| TP | True positives | ACI | Integer ≥0 |
| TN | True negatives | ACI | Integer ≥0 |
| FP | False positives (false alarms) | ACI | Integer ≥0 |
| FN | False negatives (missed detections — highest stakes in HealthTech) | ACI | Integer ≥0 |
| drift | Process/signal drift — each agent interprets differently | ACI | Float 0–1 |
| encryption_score | Cryptographic posture | SIR: Es | Float 0–1 |
| integration_score | API/system integration completeness | SIR: Ei | Float 0–1 |
| modularity_score | Architectural independence | SIR: Mp | Float 0–1 |
| continuity_score | Uptime / resilience — tightest floor for HealthTech | SIR: Cr | Float 0–1 |
| L0–L6 | Layer-specific governance score override | Layer scores | Float 0–100 |
Submitting via the API
POST /api/twin/telemetry
Authorization: Bearer <token>
{"org_id":"your-org","metric_type":"TP","value":780}The response includes updated aism, aimm_level, drift object, and agent_alerts array — findings the active agent raised from this event.
Domain-Specialized Agents
How Agent Selection Works
| Domain keyword(s) | Agent selected | Drift alert threshold |
|---|---|---|
| semiconductor, fab, chip | Semiconductor Fab | 8% (tighter) |
| retail, d2c, ecommerce | Retail / MSME | 12% |
| logistics, fleet, delivery, freight | Logistics | 10% |
| automotive, auto, ev, electric | Automotive & EV | 10% |
| health, medtech, clinical, diagnostic | HealthTech | 6% (tightest) |
| edu, learning, lms | EduTech | 16% |
| agri, farm, crop | Agri | 20% (loosest) |
| (anything else) | Generic fallback | 15% |
HealthTech Agent — Tightest Thresholds
| Check | Threshold | Code raised | Severity |
|---|---|---|---|
| Diagnostic miss-rate (FN/total) | >4% | HEALTH_MISS_RATE | warning/critical |
| Monitoring drift | ≥3% | HEALTH_MONITORING_DRIFT_WARNING | warning |
| Monitoring drift | ≥6% | HEALTH_MONITORING_DRIFT_ALERT | critical |
| Continuity/uptime (Cr) | <0.7 | HEALTH_UPTIME_RISK | critical |
Semiconductor Fab Agent
| Check | Threshold | Code | Severity |
|---|---|---|---|
| Yield variance (FP+FN/total) | >5% | FAB_YIELD_VARIANCE | warning/critical |
| Particle drift | ≥4% | FAB_PARTICLE_DRIFT_WARNING | warning |
| Particle drift | ≥8% | FAB_PARTICLE_DRIFT_ALERT | critical |
| Uptime (Cr) | <0.6 | FAB_UPTIME_RISK | warning |
Why tighter than generic: fab contamination compounds quickly. A 9% drift that the generic agent ignores triggers a critical alert here.
Retail / MSME Agent
| Check | Threshold | Code | Severity |
|---|---|---|---|
| Directional forecast bias (|FN–FP|/total) | >15% | RETAIL_FORECAST_SKEW | warning/critical |
| Return/fraud drift | ≥6% | RETAIL_FRAUD_RATE_WARNING | warning |
| Return/fraud drift | ≥12% | RETAIL_FRAUD_RATE_ALERT | critical |
| Inventory continuity (Cr) | <0.5 | RETAIL_TURNOVER_RISK | warning |
Logistics Agent
| Check | Threshold | Code | Severity |
|---|---|---|---|
| ETA prediction bias (|FN–FP|/total) | >15% | LOGISTICS_ETA_SKEW | warning/critical |
| Cargo damage/loss drift | ≥5% | LOGISTICS_DAMAGE_RATE_WARNING | warning |
| Cargo damage/loss drift | ≥10% | LOGISTICS_DAMAGE_RATE_ALERT | critical |
| Fleet utilisation (Cr) | <0.5 | LOGISTICS_FLEET_UTILISATION_RISK | warning |
Automotive & EV Agent
| Check | Threshold | Code | Severity |
|---|---|---|---|
| Defect/rework rate (FP+FN/total) | >6% | AUTO_DEFECT_RATE | warning/critical |
| Process drift (non-EV) | ≥5–10% | AUTO_PROCESS_DRIFT_WARNING/ALERT | warning/critical |
| Battery/thermal drift (EV) | ≥5–10% | AUTO_EV_BATTERY_DRIFT_WARNING/ALERT | warning/critical |
| Line/charging uptime (Cr) | <0.55 | AUTO_UPTIME_RISK | warning |
EV context is auto-detected from the domain field — battery/thermal language replaces generic process language when "ev" or "electric" appears.
EduTech Agent
| Check | Threshold | Code | Severity |
|---|---|---|---|
| At-risk learner miss-rate (FN/total) | >8% | EDU_DROPOUT_MISS_RATE | warning/critical |
| Assessment integrity drift | ≥8–16% | EDU_INTEGRITY_DRIFT_WARNING/ALERT | warning/critical |
| Platform continuity (Cr) | <0.45 | EDU_PLATFORM_CONTINUITY_RISK | warning |
Agri Agent — Sparse Data Aware
| Check | Threshold | Code | Severity |
|---|---|---|---|
| Low telemetry volume | <5 events | AGRI_SPARSE_TELEMETRY | info |
| Yield prediction skew (|FN–FP|/total) | >20% | AGRI_YIELD_SKEW | warning |
| Crop-stress drift | ≥10% | AGRI_CROP_STRESS_DRIFT_WARNING | info |
| Crop-stress drift | ≥20% | AGRI_CROP_STRESS_DRIFT_ALERT | warning |
Generic Agent — Fallback
| Check | Threshold | Code | Severity |
|---|---|---|---|
| AI$M drift from baseline | ≥8% | DRIFT_WARNING | warning |
| AI$M drift from baseline | ≥15% | DRIFT_ALERT | critical |
| Uncalibrated with ≥5 events | ≥5 events | CALIBRATION_DUE | info |
| Any layer score below floor | <35/100 | WEAK_LAYER | warning |
| No telemetry for 7 days | 7 days | STALE_TWIN | warning |
Command-Centre Dashboard
Overview Page — What is Live vs Reference
| Panel | Data | Status |
|---|---|---|
| AI$M KPI / Twin count / Alerts | GET /api/twin/list + agent endpoints | Live — auto-refresh 20s |
| Growth Comparison chart | GET /api/twin/compare (real aism_history) | Live — real data |
| AI/Agent Insights feed | Agent alerts from all twins | Live |
| Annexure download per twin | GET /api/twin/:id/annexure (generated live) | Live — real .docx |
| Global Distribution Map | Illustrative marker positions | Static placeholder |
| Certification Status | Static reference data (flagged in-app) | Manual |
| Training & Competency | Role-scoped static reference data | Manual |
| Audit Trail | Static reference data (flagged in-app) | Manual |
Growth Comparison (Geometric)
aism_history snapshots. Calibration events are marked with larger circles.Downloading a Compliance Annexure
Click ⬇ Annexure next to any twin in the Compliance Twins page. Generates and downloads a live .docx containing:
- Section 1: Twin Identity
- Section 2: Current AI$M Compliance State
- Section 3: Layer Score Breakdown
- Section 4: Identified Gaps — findings from the active domain agent, run at generation time
- Section 5: Growth History (last 15 snapshots)
- Section 6: Attestation
AI Chat Agent
REST API Reference
Quick Reference
| Method | Endpoint | Min Role | Description |
|---|---|---|---|
| POST | /api/twin/auth/login | — | Authenticate. Returns signed token. |
| GET | /health | — | Health check. |
| POST | /api/twin/register | Admin | Register new twin. |
| POST | /api/twin/telemetry | Operator | Submit telemetry event. |
| GET | /api/twin/list | Viewer | List all twins. |
| GET | /api/twin/:orgId/state | Viewer | Full twin state. |
| GET | /api/twin/:orgId/drift | Viewer | Drift analysis. |
| POST | /api/twin/:orgId/calibrate | Auditor | Lock baseline. |
| GET | /api/twin/:orgId/agent | Viewer | Open alerts. |
| GET | /api/twin/agent/sweep | Auditor | Sweep all twins. |
| POST | /api/twin/:orgId/agent/chat | Viewer | Chat with LLM agent. |
| GET | /api/twin/compare | Viewer | Growth comparison (?orgs=a,b,c). |
| GET | /api/twin/:orgId/annexure | Viewer | Download .docx Annexure. |
Example — Register and Submit Telemetry
# 1. Login
curl -X POST https://api.aimmindex.com/api/twin/auth/login \
-H "Content-Type: application/json" \
-d '{"email":"partha@is360technologies.com","password":"YOUR_PASSWORD"}'
# 2. Register a twin (Admin)
curl -X POST https://api.aimmindex.com/api/twin/register \
-H "Authorization: Bearer TOKEN" \
-H "Content-Type: application/json" \
-d '{"org_id":"retail-demo","name":"Demo Retail Co","domain":"Retail MSME"}'
# 3. Submit telemetry (Operator)
curl -X POST https://api.aimmindex.com/api/twin/telemetry \
-H "Authorization: Bearer TOKEN" \
-H "Content-Type: application/json" \
-d '{"org_id":"retail-demo","metric_type":"TP","value":780}'Annexure & Certification
Free Certification — Promo Code AIMM-LAUNCH25
RBAC & Authentication Details
How Authentication Works
Adding New Users
// src/auth.js — add this line and redeploy:
seedUser("newuser@company.com", "operator", "New User", "NEW_USER_PASSWORD");
// Then set NEW_USER_PASSWORD in EB environment propertiesKnown Limitations & Roadmap
What is Live vs Pending
| Feature | Status |
|---|---|
| AI$M engine + 7 domain agents | ✅ Live — 38/38 unit tests pass |
| RBAC / session auth | ✅ Live — real PBKDF2 + signed tokens |
| Annexure generation | ✅ Live — real .docx generated end-to-end |
| Growth comparison | ✅ Live — real aism_history time-series |
| Persistent data store (Postgres) | ❌ In-memory only — data lost on server restart |
| IoT / automatic telemetry ingestion | ❌ Manual API only — no MQTT bridge yet |
| Multi-user self-serve signup | ❌ Manual provisioning — requires backend redeploy |
| Live geolocation on map | ❌ Placeholder markers — no live coordinates per twin |