UTILITIES

AI for the operator desk and the truck cab.

Outage Q&A wired to the OMS. Billing dispute resolution that reads the meter data. Field crew copilots that know the asset history and the safety protocols. Asset health narratives that surface real failures before they happen.

Utilities — electricity, gas, water — sit at the intersection of three pressures: the customer experience expectations of digital natives, ageing physical assets stressed by climate and load, and a regulatory environment that has tightened sharply on cybersecurity. AI is the obvious productivity unlock and the obvious risk surface at the same time.

Customer-facing AI use cases are the most visible (chatbots, billing self-service) but the bigger value is in operations: field crew copilots, asset health monitoring, outage response, regulatory filings. NIS2 has brought operational technology into scope of cyber incident reporting in the EU. NERC CIP has long imposed equivalent obligations on US bulk power. REMIT regulates trading in EU energy markets. AI tooling has to fit inside all of them.

Kosmoy is the operating layer between the utility's apps and the AI they call. Single-tenant Kubernetes deployment fits the typical utility hosting posture (private cloud, often on the same infrastructure as OMS/AMI/SCADA-adjacent systems). Every AI call is logged, attributed and contained.

What this industry runs into.

Customer experience laggard

Utilities historically score among the lowest CSAT in any industry. Chatbots done badly make it worse — chatbots done well, with the OMS and AMI plugged in, change the dynamic.

Ageing assets under climate stress

Asset failure modes are shifting under heatwaves, storms and floods. Predictive maintenance that reads sensor data and historical context becomes a safety question, not an OPEX question.

OT cybersecurity under NIS2 / NERC CIP

AI tooling has to coexist with OT environments without becoming a new attack surface. Air-gapped or DMZ-segregated deployment is common.

Regulatory filing burden

NERC CIP reports, ARERA submissions, Ofgem RIIO returns, FERC Form 1 — narrative-heavy reporting cycles that AI is well-positioned to draft, with care.

Regulatory landscape.

The regulations that shape AI in utilities — and where each one bites on AI deployment.

NIS2Network and Information Security Directive 2· EU

Energy, water and waste-water utilities are essential entities. AI infrastructure must meet incident reporting (24h/72h windows), risk management and supply chain security obligations.

NERC CIPNorth American Electric Reliability Corporation Critical Infrastructure Protection· US/Canada

Bulk power system applies CIP-002 through CIP-014. AI tooling that touches BES Cyber Systems is in scope of personnel training, change management, security monitoring obligations.

REMITRegulation on Energy Market Integrity and Transparency· EU

Insider information and market manipulation rules apply to energy trading. AI used in trading desks must not leak inside information through context windows.

IEC 61850Communication networks and systems for power utility automation· Global

Substation automation standard. AI tooling that reads or writes IEC 61850 data must respect the security profile.

GDPRGeneral Data Protection Regulation· EU

Smart-meter and AMI data is personal data. Customer chatbots and billing AI must respect data minimisation and consent rules.

Sector-specificARERA (IT), Ofgem (UK), CRE (FR), BNetzA (DE), FERC (US)· National

Each national regulator has tariff, conduct and reporting obligations that bound AI use in customer-facing and trading contexts.

Use cases that are actually shipping.

Outage management Q&A

Customer asks: 'when will my power come back?'. The chatbot is wired to the OMS and weather/storm centre — it returns a specific ETR (estimated time of restoration) for the customer's address, with the cause if known and the crew status. If the storm scope is unclear, it says so honestly and offers updates by SMS.

Storm-day call-centre volume drops 50–70% on the right pattern; crew dispatch productivity rises because supervisors aren't fielding 'when will it come back' calls. Customer complaints during major events drop measurably.

Powered byAI GatewayMCP GatewayGuardrails

Billing dispute resolution

Customer calls: 'my bill is double last month, why?'. The agent reads AMI data, weather, tariff changes and any recent appliance billing events, drafts a structured explanation, and offers either an immediate self-service path (revised bill if a meter error is detected) or a hand-off to a human if the dispute needs judgement. Citation-grounded — references the specific meter readings.

Dispute resolution time drops from a week to a same-day average for the typical case. CSAT on bill-related complaints rises 15–25 points.

Powered byAgent BuilderRAG-in-a-BoxInsights Dashboard

Field crew copilot

Line crew arrives at a substation incident. The copilot on the tablet reads the asset record, the recent maintenance history, the safety protocols (LOTO, working at heights, energised line distances), and the manufacturer's maintenance manual. Crew has the institutional answer plus the safety frame, on-site and offline if needed.

Field-time-per-task drops 15–25% on equivalent crews. Safety incidents on novel-equipment work decline because the protocol surfaces before the work starts.

Powered byAction CapsuleRAG-in-a-BoxAgent Registry

Asset health monitoring narrative

Vibration, thermal and electrical sensor data on a power transformer. The agent correlates with maintenance history, weather context and similar-fleet failure modes, and produces a weekly health narrative with predicted failure modes and confidence ranges. Maintenance planners decide intervention timing.

Forced outages on monitored assets drop 20–40%. Maintenance budget shifts from time-based intervals to condition-based actions, with the narrative surviving the regulator's ask.

Powered byAgent BuilderInsights DashboardGuardrails

Regulatory filing drafting (NERC, FERC, Ofgem, ARERA)

Annual reliability filing or RIIO performance return. The agent reads the operational data, the prior-year filing, regulatory guidance updates, and drafts the narrative consistent with the figures. Regulatory affairs reviews, edits, signs.

Filing prep cycle compresses by 40–60% on the standardised sections. Consistency across filings improves; audit findings on filing quality drop.

Powered byAgent BuilderRAG-in-a-Box

Agent governance

Where utilities agents need extra discipline.

Utility agents fall on a sharp risk spectrum. A customer billing agent is a low-risk Q&A surface; a field crew copilot dispatching switching procedures is a safety-critical agent with NERC CIP obligations. Kosmoy's Agent Registry captures the difference and binds each agent's allowed actions to its risk class.

The Action Capsule shows up most often for OT-adjacent agents — those that read SCADA, ADMS or AMI data. The Capsule's network egress is restricted to the AI Gateway and the specific MCP servers each agent is approved to call. An OT-side agent that tries to reach a corporate model fails at the boundary, and the Insights Dashboard captures the attempt.

Chatbot use cases

Chatbots, by surface and risk class.

Utility chatbots are split between customer-facing (largest call deflection opportunity) and field-facing (largest productivity opportunity). Each carries different governance posture and different deployment topology.

Customer self-service portal

Bill, plan, outage status, payment arrangements. Wired to AMI, billing system, OMS through MCP Gateway. Citation-grounded; never invents a tariff or a payment plan.

Outage SMS / WhatsApp updates

Push channel during storms — proactive ETR updates, crew progress, restoration confirmation. Lightweight, structured, multi-language.

Field crew tablet copilot

Offline-capable manual lookup, switching procedure verification, safety protocol surfacing. Runs on the tablet with periodic sync; no live cloud dependency.

Internal regulatory affairs Q&A

'What did we file last year on outage frequency for region X?'. Citation-grounded retrieval from the firm's filing library.

How Kosmoy fits.

Utilities benefit from Kosmoy's split-personality deployment model. Customer-facing AI (chatbots, billing, outage Q&A) runs in the corporate cloud and connects to the OMS/billing systems through the MCP Gateway with strict per-tool allow-lists. OT-adjacent AI (asset health, field crew, switching support) runs in a DMZ-segregated install closer to the OT boundary, often on dedicated GPU infrastructure.

Cost economics matter in this sector — utility margins are tight and call volumes are huge. The LLM Router and Cost Tracking modules pay for themselves quickly: simple Q&A goes to a small fine-tuned SLM running on internal infrastructure, with frontier models reserved for genuinely complex cases.

Module questions, answered straight.

How does Kosmoy fit our NIS2 obligations?

AI infrastructure that touches essential service systems is registered as part of the NIS2 supply chain register. Incident detection on AI-component failures flows through the Insights Dashboard. Reporting templates align with the 24h/72h windows.

Can we run AI tooling in a NERC CIP-secured environment?

Yes. Kosmoy supports air-gapped and DMZ-segregated deployments suitable for BES Cyber System adjacency. The platform itself produces no telemetry to Kosmoy; the customer controls the model image, the credentials, the retrieval set.

Does the field copilot work offline?

Yes — for the document-retrieval and procedure-lookup workflows that field crews depend on. Sensor-correlation features need connectivity to the asset health systems; the tablet caches the latest known state for graceful degradation.

How do we keep AMI data inside our perimeter?

AMI data never leaves the customer's infrastructure. Kosmoy's deployment is single-tenant in the utility's own cloud or data centre. Models that process AMI prompts are either local (vLLM/Ollama) or accessed via Azure OpenAI / AWS Bedrock private endpoints with zero data retention.

Bring AI to the customer, the operator desk and the truck cab.

See how Kosmoy runs alongside OMS, AMI and OT systems — with NIS2, NERC CIP and sector-regulator obligations addressed.

Book a demoEmail sales@kosmoy.com