Intellica AI  ·  Energy & Critical Infrastructure Capability Register  ·  2026

The control plane for grids,
plants, and pipelines that can't go down. Sovereign. Provenance-chained. Air-gap ready.

Cortex connects to the SCADA, ADMS, GIS, EAM, and historian systems you already run — and gives operators, planners, and regulators one auditable interface, with every agent action cryptographically signed and every dispatch-affecting decision gated by human approval.

85%
SaaS cost
eliminated on-prem
72%
EU utilities lack
OT/IT integration
'28
NERC CIP-015-1
INSM deadline
9
Active signals
tracked this cycle
48h
Architecture
turnaround
NERC CIP-015-1 ready
CISA OT/IT segmentation
EU AI Act Art. 12
Air-gap capable
CortexGuard kill switch
NERC CIP-015-1 — INSM by Oct 2028
CISA OT/IT segmentation — required now
FERC "Energized for 2026" — DLR priority
ERCOT Enterprise Data & AI org — Jan 2026
EU AI Act — enforceable Aug 2026
PSE — AI dispatch pre-approval mandate
UAE Future Fit Seal — AI tendering in production
Busan Port digital twin — production
Ontario Sovereign HPC RFP — Jul 6

Where to start

The big picture in 60 seconds

Not sure where AI fits in your operation? Here is how every successful utility, grid operator, or operator-of-critical-infrastructure AI programme is structured — and where Cortex enters.

The problem
Your AI pilots can't see your operations

Only 28% of European utilities have basic OT/IT data integration — so AI pilots run on stale data exports, control rooms run on SCADA and historians that have never spoken to IT, and every "AI tool" your teams buy becomes another disconnected island. None of this is your fault — the OT/IT gap predates the AI era by decades.

What we do
Cortex is the sovereign layer underneath everything else

We are not a forecasting tool, a digital twin vendor, or a chatbot. Cortex is the connector and provenance layer that lets your existing SCADA, ADMS, GIS, AMI, and EAM systems — plus every AI tool you add later — operate through one auditable, air-gappable interface that you own.

The outcome
An agentlake, not another fragmented tool

Forrester projects most enterprises will be forced to compose "agentlakes" — shared architectures to orchestrate fractured AI deployments built without coordination. Deploy Cortex first and every subsequent AI tool plugs into one provenance ledger, one kill switch, one audit trail — instead of one more silo.

How a typical engagement unfolds
01
Assess & Orient

We map your OT/IT landscape — SCADA, historian, ADMS/OMS, GIS, AMI, EAM — and identify the highest-value Cortex connector to build first.

2–4 weeks
02
Design the Architecture

Cortex deployment tier, connector roadmap, NERC CIP-015-1 / CISA evidence mapping, and a procurement spec — all before a line of code runs against live systems.

3–6 weeks
03
Build the Pilot

One SCADA/historian connector plus one agent skill — digital twin, predictive maintenance, or outage triage — built to production quality on one substation, plant, or feeder.

4–8 weeks
04
Train Your People

Executive briefings for utility leadership, OT/IT integration bootcamps for engineers, and HITL oversight training for control-room operators supervising agentic outputs.

Parallel track
05
Scale with Confidence

Additional connectors, additional agent skills, agency-wide rollout — every addition runs through the same provenance ledger and kill switch established in the pilot.

Month 3 onward
What we build — by domain
01 // Sovereign OT/IT Infrastructure
Connect what's never been connected.

Cortex deployment plus the SCADA/historian, ADMS/OMS, GIS, AMI, and EAM connectors that close the OT/IT integration gap — the precondition for every other use case.

  • No rip-and-replace — Strangler Fig migration with rollback
  • 85% cost reduction vs per-seat commercial AI SaaS
  • Air-gapped, Ed25519-signed, Merkle-chained provenance
OT/IT integration assessment ($9,720)
02 // Agentic Grid Operations
AI that proposes — operators decide.

Digital twin, predictive maintenance, outage triage, demand response, and dynamic line rating advisory — every dispatch-affecting recommendation gated by Crypto HITL.

  • Advisory-only on anything that touches dispatch
  • Reduces restoration sequencing time during storm events
  • Full provenance trail on every recommendation
Cortex Energy Pilot ($32,400)
03 // Compliance & Regulatory
Audit-ready before the deadline lands.

NERC CIP-015-1 INSM evidence, CISA OT/IT segmentation and kill-switch documentation, and EU AI Act Art. 12 traceability for any AI touching dispatch.

  • Maps Cortex's existing controls to each requirement line-by-line
  • Advisory-only design pre-aligned to PSE-style pre-approval regimes
  • Audit-ready reporting straight from the provenance ledger
NERC CIP-015-1 readiness ($18,360)
04 // Workforce Training
Your control room runs it. Not us.

Executive briefings for utility IT/OT leadership, OT/IT integration bootcamps for engineers, and HITL oversight training for control-room operators.

  • Leadership reads vendor AI claims critically before procuring
  • Engineers build and extend connectors in-house
  • Operators know exactly when and how to override an agent
Executive briefing — energy IT/OT ($6,480)
05 // Interconnection & Markets
Answer the data-centre queue with data.

Grid digital twin and DLR advisory agents aimed directly at FERC's 2026 priority: squeeze more capacity from the grid that exists before new transmission is built.

  • Simulates safe load absorption for interconnection studies
  • Surfaces dynamic line rating opportunities from existing sensors
  • ISO/RTO market feed connector for demand-response planning
Digital twin agent (Cortex Energy Pilot)
06 // Sector Programmes
Same stack, midstream and ports.

The SCADA/historian connector and predictive maintenance agent transfer directly to pipeline SCADA and compressor stations. Smart port digital twins reuse the same GIS and IoT pattern.

  • PI System dominates both power and pipeline historians
  • Direct fit for Trinidad's midstream and port infrastructure
  • Sovereign HPC sizing for national grid operators and NOCs
Sovereign HPC for energy ($10,800)
01 // Sovereign OT/IT Infrastructure
Software · Sovereign Control Plane Cortex core

Cortex Deployment for Energy & Utilities

Most "AI for energy" platforms either route operational data to a vendor cloud or bolt a dashboard onto a single system. Cortex is a single Rust binary plus PostgreSQL/pgvector that runs on your infrastructure — air-gap capable, with every action Ed25519-signed and Merkle-chained. It is the foundation every connector and agent below plugs into.

TCO case

A utility running commercial AI SaaS across 1,000 seats at $30/seat/month = $360K/year recurring, with operational data leaving the jurisdiction. Cortex on-prem: $50–120K hardware, one-time, zero per-seat licensing, full data sovereignty. Break-even in 6–18 months.

What you receive
  • Cortex binary deployment on agency/utility infrastructure (Tier B or Tier C)
  • Security Fortress (7-layer) and CortexGuard kill switch configured
  • Provenance ledger (TraceCaps, BLAKE3, Ed25519, IETF SCITT) live from day one
  • Dell AI Factory reference architecture sizing if hardware procurement is in scope
Pilot tier — Contact us
90-day single-department pilot, up to 4 connectors
Defence, banking, and energy
customers run fully air-gapped
Cortexon-premair-gapprovenance
Software · Connector Closes the #1 gap

SCADA / Historian Connector (OPC-UA, PI Web API)

Siemens Energy's 2025 benchmark found only 28% of European utilities have basic OT/IT data integration — without it, AI pilots run on historical exports and can never reach real-time operational AI. This connector mirrors tag-level historian data (OSIsoft PI, Ignition, AVEVA) into Cortex's TraceDB via the existing Mirror Engine, closing the single most-cited blocker in every 2026 utility AI report.

What you receive
  • OPC-UA and PI Web API client integration into Cortex's Mirror Engine
  • Tag-level CDC mirroring with sub-100ms p95 latency at production volumes
  • Secure DMZ architecture pattern between OT and IT networks
  • Data quality monitoring tuned for high-noise sensor data
  • Read-only by default; write-back gated behind Crypto HITL
$10,800 – $13,800
10-day connector build
Universal — power, oil & gas,
water/wastewater historians
OPC-UAPI SystemhistorianCDC
Software · Connector Universal

ADMS / OMS & GIS Connectors

Outage events, switching states, network topology, and asset geolocation live in Advanced Distribution Management, Outage Management, and GIS systems that rarely talk to anything else. These connectors map vendor-specific CIM dialects (Schneider, GE, Oracle) into a common internal schema, feeding Cortex's Genesis Engine to render outage maps, asset density, and vegetation-risk overlays natively.

What you receive
  • ADMS/OMS connector: outage events, switching states, topology — read-first
  • CIM (Common Information Model) data mapping to Cortex internal schema
  • GIS connector: ArcGIS REST / OGC WFS, PostGIS-backed spatial dashboards
  • Write-back for switching orders gated through Crypto HITL (L3)
$12,960 – $24,840
ADMS/OMS (12 days) + GIS (6 days)
T&D utilities · ISOs/RTOs
Regional and municipal utilities
ADMSOMSGISCIM
Software · Connector Extends existing connector

AMI / Smart Meter Connector & Maximo Energy Extension

Cortex already connects to IBM Maximo. This is a schema-mapping extension — mapping asset hierarchies to substations, feeders, and transformers — plus a new AMI/MDM connector ingesting consumption, voltage, and outage last-gasp signals via batch CDC, the foundation for demand-forecasting and DER-visibility agent skills.

What you receive
  • AMI/MDM batch ingestion connector (Itron, Landis+Gyr, Oracle MDM, or flat-file)
  • Maximo schema extension: substation/feeder/transformer asset hierarchy mapping
  • Predictive-maintenance work orders surfaced directly into Maximo queues via write-back
  • Outage last-gasp signal integration for restoration prioritisation
$8,640 – $11,040
8-day connector + extension
Utilities already running Maximo
or any major MDM platform
AMIMaximoEAMDER
02 // Agentic Grid Operations
Software · Build Phase 1 of 3

Cortex Energy Pilot — Connector + Agent Skill

Agentic AI for grid modernisation pays off most when deployed as a governed workflow orchestrator integrating OMS, ADMS, GIS, AMI, SCADA, and EAM — producing action-ready, traceable outputs. This pilot delivers the SCADA/historian connector plus one production-ready agent skill, on one substation, plant, or feeder. Every recommendation is advisory; operators retain dispatch authority.

Option A
Grid Digital Twin & State Estimation Agent
Ingests SCADA, GIS, AMI, and weather data into a continuously updated network model. Answers natural-language "what if" queries for load and interconnection scenarios — directly relevant to data-centre interconnection studies, a named FERC 2026 priority.
Option B
Predictive Maintenance & Asset Health Agent
Reads historian and Maximo data to flag transformers, breakers, and feeders trending toward failure. Drafts work orders with provenance-chained justification for human approval before write-back.
Option C
Outage Triage & Restoration Sequencing Agent
During storm events, correlates OMS alarm floods with AMI last-gasp signals and crew locations, proposing a prioritised restoration sequence — proposal only, dispatcher confirms via Crypto HITL before any switching order is logged.
CortexOPC-UApgvectorCrypto HITLTraceCapsDocker
Engagement breakdown
Discovery & connector scoping (3 days)$3,240 – $4,140
SCADA/historian connector build (10 days)$10,800 – $13,800
Agent skill build — one option (10 days)$10,800 – $13,800
Dashboard, Knowledge Snap & testing (5 days)$5,400 – $6,900
Documentation & handover (2 days)$2,160 – $2,760
Phase 1 pilot total$32,400 – $41,400
Scale-up trajectory
P1
Pilot (this engagement)
One connector, one agent skill, one site — reference deployment
$32–41K
P2
Multi-connector, multi-agent expansion
ADMS/OMS/GIS/AMI connectors, remaining agent skills, multi-site
$150–300K
P3
Production hardening & rollout
Agency- or utility-wide deployment, NERC CIP / CISA evidence in production
Enterprise
Software · Agentic · Markets FERC named priority 2026

Demand Response & DER Visibility Agent

Renewable integration and electrification strain a grid built for predictable, centralised generation. This agent aggregates AMI and DER data — solar, battery, EV charging — to forecast demand-response capacity and surface it in plain language for planners, directly supporting the renewable-integration goals cited across every 2026 utility AI report.

Capabilities delivered
  • AMI and DER data aggregation across solar, battery, and EV charging assets
  • Demand-response capacity forecasting in plain-language summaries
  • ISO/RTO market feed connector for day-ahead and real-time price signals
  • Advisory-only — no automated dispatch or market bidding
See Cortex Energy Pilot
Universal — highest priority where
renewable share is rising fastest
agenticDERdemand response
Software · Agentic · Transmission FERC Order 1920 / DLR

Dynamic Line Rating (DLR) Advisory Agent

FERC's January 2026 "Energized for 2026" priorities name dynamic line ratings, advanced demand response, and operational-level cybersecurity as critical deployment focus areas — squeezing more capacity from existing lines while new transmission works through the queue. This agent combines weather, conductor temperature sensors via SCADA, and topology to recommend real-time line rating adjustments — advisory only, never auto-dispatched.

Capabilities delivered
  • Real-time conductor temperature ingestion via SCADA connector
  • Weather-correlated dynamic line rating recommendations
  • Direct support for FERC Order 1920 grid-enhancing technology planning
  • Recommendations logged to provenance ledger for transmission planner review
See Cortex Energy Pilot
Transmission providers responding
to FERC Order 1920 / ANOPR AD22-5
agenticDLRFERCtransmission
Software · Agentic · RAG Multi-jurisdiction

Regulatory Filing & Compliance Reporting Agent

FERC, NERC CIP, and national regulator filings require pulling structured data from across operational systems into rigid templates — a recurring, time-consuming, error-prone task. This agent drafts filings by pulling data directly from Cortex-connected systems, with every populated field provenance-chained back to its source for regulator-facing audit.

Capabilities delivered
  • Automated draft generation for FERC, NERC CIP, and national-regulator filings
  • Every populated field linked to source system and timestamp
  • Output formatted for direct regulatory submission, human-reviewed
  • Reusable across recurring filing cycles once configured
See Cortex Energy Pilot
US (FERC/NERC) · Canada · EU
National grid regulators
agenticregulatoryRAGprovenance
03 // Compliance & Regulatory
Software + Consulting · Compliance INSM deadline Oct 1, 2028

NERC CIP-015-1 Internal Network Security Monitoring Readiness

FERC Order No. 907 (approved June 26, 2025) requires high- and medium-impact Bulk Electric System Cyber Systems with External Routable Connectivity to implement Internal Network Security Monitoring inside Electronic Security Perimeters by October 1, 2028, with all other applicable systems by October 1, 2030. The standard requires entities to collect network data feeds on a risk-based rationale, detect and evaluate anomalous east-west traffic, and retain data for investigation — a multi-year build for entities that haven't started.

What you receive
  • Asset classification: identify high/medium-impact BES Cyber Systems with ERC in scope
  • INSM architecture design — network data feed sources, retention, risk-based rationale documentation
  • Cortex CIP-015-1 compliance agent pack: maps connector-level visibility to INSM requirements R1–R3
  • Audit-ready evidence reporting generated directly from the provenance ledger
  • Roadmap aligned to the Oct 2028 / Oct 2030 phased deadlines, including anticipated CIP-015-2 (EACMS/PACS) scope expansion
Why start now

NERC must submit CIP-015-2 modifications (extending INSM to EACMS and PACS outside the ESP) by September 2, 2026. Entities that delay planning for the 2028 deadline risk falling behind well before the 2030 deadline hits — and the SCADA/historian connector built for this engagement is the same connector that powers every agentic use case above.

NERC CIP-015-1 readiness engagement
Discovery & asset classification (3 days)$3,240 – $4,140
INSM architecture & data feed mapping (5 days)$5,400 – $6,900
Cortex CIP-015-1 compliance pack config (6 days)$6,480 – $8,280
Evidence reporting & documentation (3 days)$3,240 – $4,140
Readiness engagement total$18,360 – $23,460
CISA OT/IT segmentation evidence pack

CISA requires air-gapped development and testing, IT/OT network segmentation, autonomous-agent kill switches, and mandatory human review for any autonomous action affecting critical infrastructure. Cortex's CortexGuard and Security Fortress already satisfy these by design — this 5-day pack ($5,400–$6,900) documents the mapping for auditors.

NERC CIP-015-1INSMCISAFERC Order 907
Consulting · Governance PSE-style mandate spreading

AI Governance Framework for Grid-Affecting Systems

PSE (Poland's transmission operator) requires pre-approval for any AI system capable of influencing grid dispatch decisions — a regulatory posture other transmission operators are expected to converge toward. We design the governance framework that classifies your AI use cases by dispatch-influence risk, defines human oversight protocols per tier, and produces the documentation a pre-approval regime requires.

What you receive
  • AI use-case inventory classified by dispatch-influence risk tier
  • Human oversight protocol per tier, aligned to Cortex's Crypto HITL design
  • EU AI Act Art. 12/14 traceability mapping for any system affecting citizens or grid operations
  • Pre-approval documentation package suitable for regulator submission
$10,800 – $17,940
9-11 day framework engagement
EU transmission operators · PSE-aligned
regulators · EU AI Act regulated entities
governanceEU AI Actdispatch risk
Software · Discovery Universal entry point

OT/IT Integration Assessment & Cortex Architecture

Most energy organisations sit at Stage 1 (Ad-hoc Experimentation) of AI maturity — strong on governance from decades of safety compliance, weak on the technology integration that makes operational AI possible. This assessment maps your SCADA, historian, ADMS, GIS, AMI, and EAM landscape and produces the Cortex connector roadmap and procurement-ready specification.

What you receive
  • OT/IT data source inventory: system, protocol, quality, sensitivity classification
  • Secure DMZ architecture recommendation between OT and IT networks
  • Cortex connector roadmap sequenced by leverage (SCADA/historian first)
  • Cortex deployment tier recommendation (Pilot / Sovereign Enterprise / Air-Gapped)
  • Procurement-ready technical specification
$9,720 – $15,180
9-11 day discovery + architecture
Universal — utilities, ISOs/RTOs,
oil & gas, ministries of energy
discoveryOT/ITCortex
04 // Workforce AI Training
Training · Executive Fastest entry point

AI & OT/IT Strategy for Utility & Energy IT Leadership

CIOs and IT directors at utilities are evaluating AI vendors — forecasting platforms, digital twins, analytics overlays — without a shared framework for what's real versus what's a dashboard with nothing underneath. This 2-day executive workshop covers the OT/IT integration gap, Cortex's agentlake positioning, the NERC CIP-015-1 and CISA timelines, and how to read a grid-AI vendor's claims.

Programme — up to 20 participants
  • Day 1 Frameworks: OT/IT integration gap, agentic vs analytics-overlay vendors, NERC CIP-015-1 / CISA / EU AI Act timelines
  • Day 2 Applied: benchmarks from ERCOT, PSE, UAE Future Fit Seal, Busan Port translated to your operation
  • Deliverables: utility-customised deck, AI/OT readiness scorecard, vendor evaluation cheat sheet, post-workshop gap report
$6,480 – $9,660
Prep + delivery + report + travel
Universal — highest-leverage
engagement for utility entry
executiveC-suiteOT/IT
Training · Technical 70% repeat margin

OT/IT Integration & Agent Development Bootcamp

Vendor dependency on grid AI is a long-term operational risk — especially when the vendor's forecasting model can't explain its own recommendations. This 5-day hands-on programme builds in-house capability to extend Cortex connectors, build agent skills against historian and ADMS data, and design Crypto HITL workflows for dispatch-affecting recommendations.

Programme — up to 12 engineers
  • Module 1: OPC-UA / PI Web API integration patterns and CDC mirroring
  • Module 2: CIM data mapping for ADMS/OMS/GIS connectors
  • Module 3: Agent skill development (digital twin, predictive maintenance patterns)
  • Module 4: Crypto HITL design for dispatch-affecting recommendations
  • Module 5: Capstone — extend a Cortex connector against the utility's own historian
$10,800 – $17,940
Curriculum + delivery + lab setup
Utilities · ISOs/RTOs · NOCs
building in-house Cortex capability
OT/ITOPC-UAagent dev
Training · Operations Required under CISA / dispatch-risk regimes

Control-Room HITL Oversight for Agentic Recommendations

CISA's guidance requires mandatory human review for any autonomous action affecting critical infrastructure. Deploying agentic AI in a control room without training operators to interpret, override, and escalate its recommendations creates automation liability with none of the productivity benefit. This programme trains control-room operators on exactly when and how to intervene.

What you receive
  • HITL mechanics for digital twin, predictive maintenance, and outage triage agents
  • Provenance ledger interpretation — tracing any recommendation back to source data
  • Override and escalation protocols with documented decision trees
  • CortexGuard kill-switch drills — when and how to halt all agents
Custom scoped
Utilities deploying any agentic
recommendation into a control room
HITLcontrol roomCISA
05 // Sector Programmes — Midstream, Ports & Sovereign Compute
Software · Midstream Direct connector reuse

Pipeline SCADA & Compressor Station Integration

PI System dominates process historians across both power generation and pipeline/midstream operations — meaning the SCADA/historian connector built for grid operators transfers directly. The predictive maintenance agent applies with minimal rework to compressor stations and pipeline integrity management, giving national oil companies and pipeline operators the same Cortex foundation at a fraction of the original build cost.

What you receive
  • Pipeline SCADA / process historian connector (same OPC-UA / PI Web API base)
  • Predictive maintenance agent retargeted to compressor stations and pipeline segments
  • NERC CIP-015-1 equivalent evidence mapping for midstream cybersecurity regimes where applicable
  • Cortex Knowledge Snap for midstream operations
Custom scoped
Reduced cost where Cortex Energy Pilot is already deployed
National oil companies · pipeline operators
Direct fit for Trinidad's energy sector
midstreamPI Systempipeline integrity
Software · Logistics · Digital Twin Benchmark: Busan 2026

Smart Port Digital Twin & AI Logistics Platform

Port operations are among the most data-rich, highest-throughput energy-adjacent environments — and among the least optimised. We build AI-driven digital twins for port operations, integrating IoT sensor data, GIS, and the same digital-twin agent pattern used for grid state estimation, with blockchain-based cargo documentation and autonomous routing. Busan Port is the 2026 production benchmark; Trinidad's port infrastructure is a direct regional opportunity.

Capabilities delivered
  • Real-time port digital twin integrating IoT sensor feeds and GIS
  • AI-optimised vessel routing and berth allocation
  • Blockchain-based cargo documentation and provenance tracking
  • Predictive maintenance scheduling across port infrastructure equipment
Custom scoped
South Korea (production)
Singapore · Caribbean ports
digital twinIoTblockchainports
Software · Infrastructure · HPC Ontario RFP closes Jul 6, 2026

Sovereign HPC for National Grid Operators & NOCs

National AI ambitions collide with foreign-owned compute — a strategic vulnerability that Singapore addressed with a $1 billion sovereign R&D compute commitment. We design and size sovereign HPC infrastructure for grid-scale digital twins, state estimation, and predictive maintenance workloads, sized specifically for the inference loads Cortex's energy agent skills generate.

What you receive
  • Workload requirements analysis for digital twin / predictive maintenance inference loads
  • Hardware sizing: GPU type, VRAM, storage, network — Dell AI Factory / NVIDIA reference architecture
  • Software stack: vLLM/Ollama inference, Kong/Traefik gateway, Prometheus/Grafana, MLflow registry
  • 3-year TCO model vs commercial cloud, RFQ-ready procurement specification
$10,800 – $17,940
Design engagement · Build contract: $200K+
Canada (Ontario · Jul 6)
National grid operators · NOCs
HPCsovereign computevLLM

Global procurement signal

Where energy-sector demand is live right now

Active regulatory deadlines, RFPs, and national programmes shaping AI procurement across energy and critical infrastructure.

North America
  • NERC CIP-015-1 — INSM by Oct 2028 / 2030
  • FERC "Energized for 2026" — DLR & demand response
  • ERCOT — dedicated Enterprise Data & AI org (Jan 2026)
  • Ontario — Sovereign HPC RFP (Jul 6)
  • CISA — OT/IT segmentation guidance (required now)
Europe
  • EU AI Act — enforceable Aug 2026 (Art. 12/14)
  • Siemens Energy benchmark — 28% OT/IT integration
  • PSE (Poland) — AI dispatch pre-approval mandate
Middle East
  • UAE — Future Fit Seal, AI-native tendering in production
  • Saudi Arabia — SDAIA programmes active
Asia-Pacific
  • South Korea — Busan Port digital twin (production)
  • Singapore — $1B sovereign R&D compute commitment
Caribbean
  • Trinidad — midstream & port infrastructure
  • Regional utilities — OT/IT integration gap

Why Intellica

We don't sell another tool.
We sell the layer underneath all of them.

Forrester projects most enterprises will be forced to compose "agentlakes" — shared architectures to orchestrate AI tools built without coordination. Cortex is designed to be that layer from day one, not retrofitted after the fragmentation has already happened.

Sovereign by construction

Your operational data never leaves your infrastructure.

Cortex is a single Rust binary plus PostgreSQL/pgvector. It runs on your servers, validates its licence offline, and never makes an outbound call. Defence, banking, and energy customers run it fully air-gapped with updates on physical media.

Provenance, not promises

Every agent action is signed, chained, and replayable.

Every query, write, and dashboard generated produces a BLAKE3-hashed, Ed25519-signed TraceCaps capsule, chained into a Merkle tree and anchored to IETF SCITT — satisfying EU AI Act Art. 12 and NERC CIP-015-1 evidence requirements out of the box.

Migration nobody notices

No rip-and-replace. Instant rollback.

The Absorption Pipeline mirrors your existing SCADA, ADMS, and EAM systems in real time, gradually generating accessible interfaces behind a Strangler Fig façade — with instant rollback to the legacy system at any workflow step.

Advisory by default

Agents propose. Operators decide.

Crypto HITL (L3) requires Ed25519 manifest signing for high-risk operations. Every agent skill in the energy module is advisory-only on anything that touches dispatch — pre-aligned to PSE-style pre-approval regimes before they're mandated elsewhere.

One kill switch

CortexGuard halts every agent, instantly, even offline.

A single administrator action — POST /admin/kill — returns 503 on every subsequent agent request, fully audited, and works identically online or air-gapped. This is the CISA-mandated kill switch, already built.

Vendor-independent

No referral fees. No vendor alignments.

We don't resell forecasting platforms, digital twin tools, or analytics overlays, and hold no commercial agreements with AI vendors. Every recommendation — including which connector to build first — is determined by your operational requirements alone.

Start the conversation

Tell us your hardest
OT/IT integration problem.

We will send you a complete Cortex architecture assessment within 48 hours. No cost for the first review. If it solves your problem — and it will — we discuss what engagement looks like from there.