See It Work
See It Work
SYSTEM: OPERATIONAL OT/IT CONNECTORS: 150+ AUTONOMOUS OPERATION: 15+ DAYS GOVERNED AUTONOMY: ENFORCED AUDIT TRAIL: IMMUTABLE INDUSTRIES: ASSET-INTENSIVE & MISSION-CRITICAL DEPLOYMENT: 3-6 MONTHS VIA APEX CONTROL LOOPS: 3,400+ SYSTEM: OPERATIONAL OT/IT CONNECTORS: 150+ AUTONOMOUS OPERATION: 15+ DAYS GOVERNED AUTONOMY: ENFORCED AUDIT TRAIL: IMMUTABLE INDUSTRIES: ASSET-INTENSIVE & MISSION-CRITICAL DEPLOYMENT: 3-6 MONTHS VIA APEX CONTROL LOOPS: 3,400+

DATA STREAM DESIGNER · TIER 1 — DETERMINISTIC

Connect live operational data to decision workflows.

Connect industrial sources. Process live events. Feed every downstream XMPro decision with the context that matters.

View Integration & Connectors

WHERE IT FITS

Operational data → Stream Designer → applications, recommendations, workflows, agents.

Stream Designer sits at the start of every XMPro flow. Industrial sources feed in — OT, IT and engineering systems — and the curated, contextualised signals feed every other component of the Agentic Operations Platform.

Stream Designer in the XMPro architecture — from operational sources through to applications, recommendations, workflows and agents.

Primarily supports

  • Monitor & Predict.
  • Data access & contextualisation.
  • Live event processing.
  • Agentic Operations Platform integration.

THE INTEGRATION CHALLENGE

50% of digital transformation cost goes to integration.

The reason is structural: industrial data sits behind a wall of fragile point-to-point connections that break every time a system changes. Stream Designer replaces that wall with a visual, drag-and-drop pipeline.

Without Data Stream Designer

  • Data siloed across SCADA, historians, ERP and IoT platforms.
  • Fragile point-to-point connections that break with every change.
  • Manual integration absorbs engineering time meant for the operation.
  • SQL expertise required to do anything useful with operational data.

With Data Stream Designer

  • Unified data layer across every operational source.
  • Visual, drag-and-drop pipeline composition — zero code.
  • 150+ certified connectors maintained centrally.
  • SMEs compose flows in their own language — no SQL needed.

THE FOUNDATION LAYER

One Data Layer. Two Intelligence Paths.

Stream Designer is the shared intelligence pipeline that feeds both human operators via App Designer and autonomous agents via MAGS — from a single, unified data integration layer.

SHARED DATA LAYER

An anomaly is detected.

Pump P-301 vibration exceeds baseline. The data flows through OIM -- the shared intelligence layer that both paths draw from.

AppDesignerHUMAN PATH
OEE
94.2%
ALERTS
3
UPTIME
99.7%
Pump P-301: Bearing replacement

PdM Agent recommends maintenance within 48 hours.

ApproveDeferOverride
OIM
Data
Graph
MAGSAUTONOMOUS PATH
14:32:01
Anomaly Detected
Vibration spike on bearing assembly
14:32:03
Root Cause Analysis
Bearing wear from lubrication degradation
14:32:05
Action Proposed
Schedule replacement, reduce speed to 80%
14:32:08
Approved & Executing
WO-4821 created. Speed adjusted.

THE DATA ORCHESTRATION CONTINUUM

Three tiers, one platform foundation.

Stream Designer is Tier 1 — deterministic data orchestration. Tier 2 adds governed AI reasoning to the same canvas. Tier 3 brings full cognitive agent teams. Customers progress along the tiers as their operations mature.

TIER 1

You are here

Stream Designer

Deterministic data orchestration. Visual composition, industrial-grade connectors, edge deployment, real-time observability. If the flowchart can be drawn before runtime, use a Datastream.

Tier 1 — Deterministic

TIER 2

When reasoning is needed

AI Workflow Harness

The same Datastream canvas, now governing an LLM reasoning agent. Context assembly, tool access, output validation and routing all visible on-canvas. Single-pass reasoning, no autonomous cycles.

Explore AI Workflow Harness →

TIER 3

When autonomy is required

Cognitive Agents (MAGS)

Multi-agent generative systems. Observe-reflect-plan-act cycles, persistent memory, objective functions, team coordination. Full autonomous operation inside policy guardrails.

Explore MAGS →

HOW IT WORKS

Visual Data Pipeline — Six Stages, Zero Code

Drag and drop connector agents onto a visual canvas. Configure properties without writing code. Data flows from ingestion through enrichment, transformation, analytics, and action — all in real time.

01 LISTEN

Listeners

Consume or ingest data as it arrives from sensors, historians, SCADA, and third-party systems in real time.

02 ENRICH

Context Providers

Add contextual information from databases and services — equipment specs, maintenance history, operating thresholds.

03 TRANSFORM

Transformations

Clean and wrangle data — replace missing values, convert types, normalise units, filter noise. 35+ built-in agents.

04 COMPUTE

Functions

Apply mathematical and statistical operations — FFT, aggregations, rolling averages, custom calculations.

05 PREDICT

AI & Machine Learning

Embed anomaly detection, predictive models, Azure ML, Jupyter notebooks, and MLFlow pipelines directly in the stream.

06 ACT

Action Agents

Trigger actions in third-party systems — create work orders in SAP, send alerts via Teams, update CMMS records.

From raw sensor signal to autonomous action — one visual pipeline, zero code.

CONNECTOR ECOSYSTEM

150+ Certified Connectors

Pre-built connectors for enterprise, industrial, and emerging technologies. From edge sensors to cloud analytics — connect your entire operational landscape without custom code.

CERTIFIED CONNECTORS
01Historians & Time-Series
OSIsoft PI
InfluxDB
35
02SCADA, DCS & PLC
Siemens
Rockwell
40
03ERP, CMMS & MES
SAP
IBM Maximo
30
04Cloud Platforms
Azure
AWS
25
05Collaboration Tools
Teams
ServiceNow
20

INTELLIGENCE BUILT IN

AI & Analytics in Real Time

Embed predictive models, anomaly detection, and machine learning directly into your data streams. No separate analytics platform — intelligence runs where the data flows.

DETECT, PREDICT, OPTIMISE

Live analytics where the data flows.

Anomaly detection catches process deviations and equipment degradation as they happen. Predictive analytics forecasts remaining useful life and production output. Operational intelligence drives live OEE visibility, root-cause analysis, and recommendations — on the canvas, in real time.

BRING YOUR OWN MODELS

Embed your models, enriched with context.

Drop Azure ML, Jupyter notebooks, MLFlow pipelines, R scripts and custom Python straight onto the canvas. The Operational Intelligence Model layers semantic context across every signal, so models reason on data that already carries meaning.

DEPLOY ANYWHERE

Run where the data lives.

Deploy data streams at the edge, in the cloud, or hybrid. Process signals at the source — cut latency, bandwidth and egress cost, while still feeding the same canvas the rest of the platform consumes.

INTERACTIVE TOUR

Take a tour of Stream Designer.

PRODUCTION PROVEN

Trusted by Industrial Operators

VERIFIED RESULT — OIL & GAS
$16M Saved every year
18% Reduction in field service trips
95% Reduction in maintenance planning

Customer Case Study

Using XMPro, a global oil and gas supermajor rapidly composed and deployed an intelligent oil well maintenance solution in just three months -- achieving over $8 million in calculated value within the first six months.

VERIFIED RESULT — MINING
$10M Saved every year
30% Reduction in conveyor downtime
9,000t Saved every month

Customer Case Study

Using XMPro, the world's largest potash mining company rapidly composed and deployed a predictive maintenance solution for over 50 miles of underground conveyors in just 30 days, achieving $10 million in savings every year by reducing unplanned downtime by over 30%.

VERIFIED RESULT — ENTERPRISE SCALE
6 Sites with in-house adoption
1,000+ Assets monitored
35+ Operational, tactical and strategic use cases

Customer Case Study

XMPro enabled the in-house engineering team at a major North American miner to independently compose 35 operational, tactical and strategic solutions across six sites, scaling to monitor and manage over 1,000 diverse critical assets.

"XMPro successfully triggered a real predictive maintenance alert for a Haul Truck that appears to have a Strut issue - This was particularly impressive, considering we have only deployed the development environment a few weeks ago"

-- Advanced Predictive Maintenance Lead, major global mining company

Start building your intelligence pipeline.

See how Stream Designer can unify your operational data and power both human decisions and autonomous operations.