Skip to main content
UlexIoTy
Conduitby UlexIoTy
Features
OT Engineers
Query data across historians
IT Directors
Security-first data access
Plant Managers
Real-time operational KPIs
Division Directors
Multi-facility visibility
Routing Intelligence
AI-learned decision routing
All Solutions
View all roles
Use Cases
Blog
Insights and tutorials
ROI Calculator
Calculate your savings
Glossary
Industrial data terminology
ContactRequest Demo
Features
Use Cases
ContactRequest Demo

Footer

UlexIoTy

Conduit — Industrial Context Mesh

The Industrial Context Mesh that adds meaning to your OT data without moving it.

Meaning without movement.

Product

  • Features
  • How It Works
  • Integrations

Resources

  • Use Cases

Company

  • About
  • Contact

Legal

  • Privacy
  • Terms

© 2026 UlexIoTy LLC. All rights reserved.

Production Features forIndustrial Intelligence

Everything you need to add context to your OT data, query across sources, and build a semantic layer that reflects your operations.

Request DemoSee How It Works

AI-Assisted Natural Language Queries

Ask questions in plain English. Our AI interprets your intent and generates a structured query that you can review and adjust before execution. Full transparency, full control.

  • AI generates queries you review before execution
  • Iterative AI-assisted query refinement
  • No black boxes - you always see what will run
  • Confidence scores and alternatives when ambiguous
Natural Language Query:

Real-Time Industrial Mesh

Live tag values delivered in under 2 milliseconds. NATS pub/sub replaces polling — your dashboards update the instant a value changes. Subscribe to any tag, any plant, with wildcard patterns.

  • 100x faster than polling — sub-millisecond tag subscriptions
  • Multi-plant federation connects facilities automatically
  • Edge-to-edge data sharing without touching the control plane
  • Push alerts and live dashboards update in real time
Sp
Splunk
Event logs & security alerts
MQ
MQTT
Real-time sensor metrics
OP
OPC-UA
SCADA & PLC data
Da
Database
Time-series analytics
MC
MCP Edge
Edge device telemetry
Unified Results
Cross-Source Execution
5 connectors queried in parallel — 142ms total
Zero Data Movement

Cross-Source Query Engine

Query data at the source without moving it. Conduit dispatches queries to Splunk, MQTT, and OPC-UA in parallel, merging results without data replication.

  • Zero data replication required
  • Reduced latency vs centralized architectures
  • Maintain compliance with data residency requirements
  • Scale horizontally by adding translators
Sp
Splunk
Event logs & security alerts
MQ
MQTT
Real-time sensor metrics
OP
OPC-UA
SCADA & PLC data
Da
Database
Time-series analytics
MC
MCP Edge
Edge device telemetry
Unified Results
Cross-Source Execution
5 connectors queried in parallel — 142ms total
Zero Data Movement

Cross-Source Correlation

Join events and metrics across different systems in a single query. Correlate alarms from Splunk with process data from MQTT and OPC-UA to find root causes.

  • Time-window based correlation
  • Support for anchor events with context windows
  • Combine time-series metrics with log events
  • Unified view across disparate data sources

Cross-Source Correlation Engine

DuckDB-Powered Time-Aligned Joins

Correlation
Process Data (Splunk)
Sensor Data (MQTT)
Correlate temperature from process_data with pressure from sensor_data by equipment during the last hour

Correlation detected: 94% match | Join key: equipment | Engine: DuckDB

Dynamic Unified Namespace

Build your UNS from actual usage patterns, not theoretical models. Source bindings, tag proposals, and formula definitions grow the namespace organically as your team queries data.

  • Source bindings map UNS paths to physical data sources
  • Tag proposals from queries grow the namespace organically
  • Formula definitions compute derived values across sources
  • Multi-source query planner builds DAG execution plans

Dynamic Unified Namespace

Built from actual usage, not theoretical models

enterprise/
chicago/
area_1/
area_2/
MQTT
OPC-UA
Splunk

Intelligence Layer

Routing Intelligence, Collaboration & Context

Beyond data querying, the platform learns your organization's decision trees, routes questions to the right experts, and builds persistent context from every interaction.

Routing Intelligence

AI that learns your organization's decision trees. It watches how questions flow, discovers who actually resolves them, and progressively takes over routing — from pure observation to fully autonomous.

  • Learns organically from real interactions — no configuration
  • Skip-level routing eliminates unnecessary hops
  • Exploration routing discovers hidden expertise
  • Confidence-adaptive: suggests at 40%, auto-routes at 75%+
Question
Plant Manager
Question Origin
AI Router — High Confidence
Confidence: 87%
Action: Auto-Route
< 40% Clarify40-75% Suggest> 75% Auto-Route
Engineering Lead
Skip-Level Bypassed
OT Specialist
Resolved 47 similar questions
✓

AI-Mediated Collaboration

Questions reach the right expert in seconds, not days. The AI acts as a smart chief of staff — clarifying intent, routing with confidence scores, and synthesizing answers from multiple experts when needed.

  • Multi-route fan-out for compound questions
  • Parallel NQE data queries via Conduit
  • AI synthesizes human expertise + machine data
  • Built-in redundancy — never single-point-of-failure

Hierarchical Question Routing

Active
VP
Why is Plant Chicago's OEE dropping?
AI
Routing to OT Engineering (87% confidence). Querying Conduit: `Show trend OEE by line during last_7d`
D
Conduit results: Line 3 OEE dropped 12% — bearing temperature anomaly detected at 02:14 on Feb 10
E
Confirmed: Bearing on Line 3 packaging unit reached 87°C (limit: 75°C). Maintenance scheduled for tonight's downtime window.

Portable Professional Context

Your expertise, proven through actual work. Build a context profile that captures what you know, what you contribute, and how you solve problems. It moves with you.

  • Expertise proven through resolution patterns
  • Composite scoring with temporal decay
  • Portable — goes with you to new companies
  • More valuable than any resume or LinkedIn profile
MR

Maria Rodriguez

Senior OT Engineer

ManufacturingEXPERT
Root Cause AnalysisHIGH
PLC ProgrammingHIGH
Monitoring & ObservabilityMEDIUM
142
Resolutions
2.3h
Avg Time
0.82
Depth
Composite Score
Frequency30%
Recency25%
Consistency20%
Depth25%
Activity (Last 30 Days)30-day half-life decay
Portable Verified Context

Enterprise-Grade Architecture

Built on a 3-database architecture with Neo4j for graph relationships, PostgreSQL for relational data, and pgvector for semantic search. 18 backend services, 72,000+ lines of production code, and 5,500+ tests across two interconnected platforms.

NATS
Real-time pub/sub with sub-millisecond delivery
Neo4j
Graph relationships and context mapping
PostgreSQL
Relational data and audit trails
pgvector
Semantic search and embeddings

And Much More

Additional capabilities that make Conduit enterprise-ready.

Enterprise Security

Multi-tenant RBAC, JWT authentication, mTLS and NATS TLS for mesh communication, and certificate rotation without restarts.

Golden Template System

Learn from user corrections with confidence scoring. Auto-promotion pipeline promotes patterns to golden templates when thresholds are met.

Multi-Provider LLM

Pluggable AI backend supporting Claude, OpenAI, Azure OpenAI, Ollama, and Mock providers.

Query Plan Caching

Redis-backed DAG caching with SHA-256 topology hashing. Identical query structures resolve instantly on repeat execution.

Partial Execution

Dispatch known fields immediately, return partial results, and update when remaining sources respond. Progress over perfection.

Pattern Detection Engine

Correction pattern analysis with confidence scoring. Tracks query corrections and promotes successful patterns to golden templates.

Enterprise Security

Built for IT Directors Who Care About Security

Security isn't an afterthought. It's the foundation of how Conduit works. Your data stays in your network, every query is audited, and access is controlled at every layer.

Your Data Never Leaves Your Network

Conduit queries data in place — no data replication, no centralized data lake, no data movement across network boundaries.

Zero Trust Architecture

Every query is authenticated and authorized. No implicit trust based on network location. Mutual TLS between all components with certificate-based identity.

Audit Everything

Complete query logging with user attribution, timestamp, data sources accessed, and results. Full audit trail for compliance and forensic analysis.

Defense in Depth

Multiple overlapping security layers: network segmentation, application-level access control, mutual TLS between services, and complete query audit trails.

Enterprise Security Features

End-to-End TLS Encryption

All data in transit encrypted with TLS 1.3. Support for mutual TLS authentication.

API Key Management

Scoped API keys for translators with automatic rotation and revocation.

Ready to add meaning to your data?

See how Conduit can transform your industrial data operations. Get a personalized demo from our team.

Request DemoSee How It Works