Factory AI Platform ● Live Build

End-to-end industrial intelligence — from raw PLC signals to AI-driven root cause analysis.

What it is

A unified, real-time system that brings together disconnected factory data and enables AI-driven intelligence across every layer of the production floor.

Active build · Apr 2026 – Dec 2026
5 system layers
20/s PLC samples
<100ms streaming latency

The Problem — Three Isolated Silos

PLCs
isolated
"What's the machine doing?"
MES
isolated
"What are we making and where?"
Historical data
isolated
"What was the outcome yesterday?"
Factory AI Platform
unified
Full context · real-time intelligence

The Solution — 5 Layers

Observability "What's happening now?"
Anomaly Detection "Is something wrong?"
Real-Time Streaming "How do we process at scale?"
Analytics & Storage "What patterns exist?"
AI Reasoning "Why did it happen? What to do?"

Tech Stack

Layer Tech Role
EdgeRustMock PLC (20 samples/sec)
StreamingNATS JetStreamLow-latency event routing
EnrichmentGoJoin PLC data + MES state
Analytics DBClickHouseTime-series storage
Anomaly DetectionPython / FastAPIStatistical + ML signals
AI ReasoningLLM + Extracta AIContext-aware root cause analysis
DashboardReact / TypeScriptReal-time visualization

Business Value

ProblemOutcome
Quality escapesCatch anomalies before parts ship — 5–10% fewer defects
DowntimePredict failures before they happen — 20–30% less downtime
Root cause mysteryAI explains what went wrong in seconds — 50% faster resolution
Bottlenecks unknownOEE trends show where to optimize — 10–15% throughput gain

What This Demonstrates

Manufacturing domain knowledge

PLCs, MES, OEE, real production constraints

Distributed systems

Event streaming, NATS, concurrent processing

Production patterns

Observability, graceful degradation, backpressure

Full-stack depth

Rust + Go + Python + React + databases

AI in production

ML inference in a real systems context, not notebooks

Current Status

  • ✅ Complete — Streaming, enrichment, storage, dashboard

    NATS JetStream event routing · Go enrichment service · ClickHouse time-series · React real-time dashboard

  • ⏳ In Progress — Observability & anomaly detection

    Prometheus / Grafana metrics · Statistical anomaly signals · ML-based detection layer

  • 🔜 Planned — GraphQL, Kubernetes, Extracta AI

    GraphQL query layer · Container orchestration · LLM-powered root cause analysis via Extracta AI