INDUSTRY JOURNEY

Manufacturing

Line 3 went down twice this week. The cause is buried in different systems.

Production data scattered across SCADA, MES and historians makes root-cause analysis a guessing game. This journey brings it into one workspace, and gives every metric one saved definition.

The challenge

Manufacturing operations struggle with:

• Scattered data - SCADA, MES, historians, quality systems
• No single view - OEE calculated differently everywhere
• Reactive troubleshooting - problems found after the damage is done
• Manual reporting - shift reports, quality metrics, production summaries

What OpenX gives you

Capability	How it helps
One production view	Every source on surfaces in one workspace
Standard metrics	OEE, quality and downtime defined once as warm queries
A record of changes	Once Provenance is set up in your landing zone, Saves to connections, surfaces and warm queries are recorded; accepted proposals are not (what is recorded)
Any AI over MCP	Claude, ChatGPT or Cursor reads the same saved queries

When the plant manager asks "Why did we miss target?", you show them the saved query behind the number.

What you will build

Component	Description
Connections	SCADA, MES, historian, quality systems
Surfaces	A plant, line, cell and station hierarchy
Warm queries	OEE, cycle time, quality, downtime analysis
API endpoints	Dashboards, MES, alerting
MCP	Production questions answered by any MCP client

Two tracks

Track A: Hybrid - add OpenX without disrupting production

You have SCADA, MES and historians running. This track adds OpenX beside them:

• Bring existing production data in through a live-device connection
• Create surfaces by line, cell and station
• Build standard OEE and quality queries with Azi
• Call those queries from your existing dashboards

Start the hybrid track

Track B: Full - author your production intelligence

Starting fresh, or want complete control:

• Design your production data architecture
• Create a complete surface hierarchy
• Build a query library
• Give operations, quality and maintenance the access they need

Start the full track

Before you start

Requirement	Details
An OpenX workspace	See Get a Workspace
Azure (optional)	Live devices use Fathym's shared IoT hub until your workspace has its own landing zone and IoT fabric in your Azure subscription
Data sources	SCADA, MES, a historian, or a Simulator node

Why it matters

OEE everyone trusts

Problem	With a saved query
"My OEE is different from yours"	One query, one definition
"Where does this number come from?"	The query is there to read
"Can we trust the dashboard?"	The dashboard calls the saved query

Quality traceability

• Lot tracking: which batches, which inputs, which outputs
• Deviation analysis: what changed when quality dropped
• Root cause: driven by data, not by gut

Choose your track

Next steps

• Other industries -> Industry journeys
• Common query shapes -> Query Patterns