Skip to content
Illustration for the E.ON case study

AI Productionization & Observability at E.ON

AI productionization for 8M+ energy customers under KRITIS. Six monitoring tools consolidated into one platform. 2M+ monthly LLM interactions.

Production AI at enterprise scale. One observability platform across IT, OT, and grid with agentic diagnostics.

  • Scalability
  • Security
  • Reliability
  • Observability
Visit websiteopens an external site in a new tabAll work

Programme results

2M+ monthly
45% faster
6 → 1
Illustration: two paper hills joined by a power line

Two remits, one dependency

E.ON runs 1.6 million km of energy networks for 47 million customers across 17 countries. When something breaks, people lose power. The work had two priorities: get AI into production for 8M+ energy customers and fix the observability foundation it depended on. The second turned out to be a precondition for the first. AI-assisted operations reason over telemetry, and E.ON's telemetry was split across six monitoring tools.

Consolidating under the workflows people already had

Six tools across IT, OT and grid operations, none with the full picture. Decentralised renewables were making the grid more volatile by the quarter, and alert fatigue was burning out on-call teams. Ripping the six out would have thrown away years of scripts, integrations and habits wrapped around them, so the E.ON programme consolidated underneath them instead. OpenTelemetry became the single, vendor-neutral standard for traces, metrics and logs, with New Relic as the platform layer: APM, infrastructure monitoring, Kubernetes auto-discovery via eBPF, AI-assisted root cause analysis.

We pushed hardest for semantic conventions so teams would name things consistently. Automated correlation only works on labels that agree, and the AI diagnostics planned for later in the programme depended on it.

Putting AI into production under KRITIS

For critical infrastructure, getting AI into production is mostly governance and delivery work. The E.ON programme's MLOps pipelines replaced manual release steps with automated testing, and model deployment time fell 45% while production incidents fell 60%. The customer-service LLM deployment now handles 2M+ monthly interactions. All of it ships inside the regulatory envelope: BSI C5 controls, NIS2, KRITIS/IT-SiG 2.0, with DSFA documentation for every AI-driven use of customer data.

On that baseline the E.ON programme piloted the agentic layer: MCP-connected LLMs against New Relic in AWS and Azure, doing automated diagnostics and remediation with human-in-the-loop guardrails. A working group from observability, operations and data science checked that the collected metrics mapped to defined SLOs, so the pilot had to prove its value in numbers the operators already trusted.

Illustration: small paper dials folding into one larger dial
Illustration: a raised red paper flag with a blank tag

Alerts that name the business impact

Pathpoint mapped customer journeys, order flows and backend services to shared KPIs, and grid operators got real-time state estimation and congestion detection. An incident used to arrive as "this service is down". Now it arrives as "this is affecting X customers in their billing flow", and the prioritisation arguments got shorter.

Scaling without a bottleneck

Self-service dashboards and templates took observability to thousands of users without queueing on a central team. A reusable onboarding playbook covering collectors, alerts, SLOs and dashboards meant new teams reached production-grade observability in days.

Production AI and one observability platform

  • Production AI serving 8M+ energy customers: 2M+ monthly LLM interactions
  • 45% faster model deployment and 60% fewer production incidents through MLOps pipelines with automated testing
  • Six monitoring tools consolidated into one OpenTelemetry platform spanning IT, OT, and grid
  • Agentic diagnostics piloted with MCP-connected LLMs, gated by human-in-the-loop guardrails
  • BSI C5, NIS2, and KRITIS-compliant governance with DSFA documentation

The AI-native Platform Playbook describes how the programme decided what an agent could do on its own and what guardrails it needed.

Energy is the industry Annex III calls critical infrastructure when a system is a safety component of the grid. The customer-service models in this engagement are a separate placement. We use the EU AI Act product quick-check to mark that distinction before treating either one as minimal risk. The distance between a green tool and a customer who cannot finish is why your SaaS observability stack is lying to you.

A similar situation on your side?

Start a project

Next project

Scaling PVS Integrations and Embedded Finance at Nelly Solutions