1 business day → 7 minutes. Customers notice.
EV Energy manages customer support across 26 utility programs for energy utilities globally. We built an AI agent that handles compatibility tickets in minutes — and their customers started noticing unprompted. Within six weeks, first response times dropped from one business day to seven minutes, first contact resolution rose from 35% to 55%, and CSAT improved from 50% to 70% positive.
EV Energy is a software platform that manages electric vehicle charging and distributed energy resources for energy utilities across the globe. By aggregating individual EV chargers, batteries, and solar installations into virtual power plants, EV Energy helps utilities balance grid demand, reduce energy costs, and improve system reliability. Their customer support team handles ticket volume across 26 utility programs in the US and Europe — each with unique compatibility rules, business logic, and customer communication requirements. Delivering a world-class driver experience isn't just a support metric — it's a business-critical function. Drivers who have a poor experience disenroll from programs, which directly reduces the size of the virtual power plant and the flexibility EV Energy can offer its utility clients.
The challenge
As EV Energy's utility program portfolio grew, their support team faced increasing pressure from volume spikes, specialist knowledge requirements, and the manual overhead of researching every ticket individually. A backlog that grew faster than it could be cleared was the clearest sign that the old approach couldn't scale.
Key pain points
Every compatibility ticket required individual research — checking program-specific vehicle and charger lists by geography. Each ticket demanded specialist knowledge that wasn't easily shared or scaled.
Staff leave and ticket volume spikes created backlogs that were hard to recover from. Response times stretched to two business days during peak periods.
Each utility program had unique rules not easily transferable across agents. When key team members were unavailable, quality and speed dropped with them.
Human-drafted responses varied across agents and programs. Tone, accuracy, and structure differed based on who was handling the ticket.
The existing model could not scale cost-effectively to support continued growth in utility programs and driver enrollments without proportionally increasing headcount.
Business impact
~1 business day average first response time for compatibility tickets
Backlogs difficult to recover during staff leave or volume spikes
High training overhead to reach program-specific proficiency
Risk of human error applying complex, program-specific business rules
The solution
Phased AI automation for customer support — starting with human-in-the-loop validation, then expanding to autonomous responses as quality proves out. Built on EV Energy's own infrastructure, with full data sovereignty and GDPR compliance.
Phased human-in-the-loop rollout
Built trust incrementally. Helper notes first so the team could see and verify quality before relying on it — then autonomous responses once confidence was established. Higher-risk categories remained in helper-note mode while confidence was built.
26-program compatibility engine
The AI agent manages the full complexity of utility program rules — vehicle compatibility lists, geographic eligibility, business logic variations, and program-specific response requirements — automatically detecting the relevant program from each incoming ticket.
Self-hosted on EV Energy's AWS
The entire system runs on EV Energy's own AWS infrastructure using n8n. No third-party data access. Full data sovereignty with the information security standards required to maintain trust with both utilities and consumers. As an EU-headquartered company subject to GDPR, this was non-negotiable.
Real-time response under 7 minutes
Compatibility tickets are now answered in an average of 7 minutes — including outside business hours. Customers began noticing and volunteering feedback on the speed without being prompted.
AI customer support agent for high-volume teams
The same phased AI automation approach deployed for EV Energy. Human-in-the-loop validation, then autonomous responses as quality proves out. Built on your infrastructure.
How it works
Helper Notes — AI generates a draft response as an internal ticket note. Human agents review and approve before sending. Used to validate quality and refine prompts.
Direct Responses — High-confidence, low-risk ticket categories (compatibility and eligibility queries) switch to fully automated direct responses — no human review required.
Ongoing Expansion — Higher-risk categories (incentive queries, charging session earnings) remain in helper-note mode while confidence builds. Gradual, controlled expansion across more programs and categories.
Infrastructure Hardening — Transition from rapid proof-of-concept to production-grade architecture embedded within EV Energy's engineering infrastructure, enabling their internal team to independently maintain, update, and deploy changes.
"We wanted to try and relieve the team quickly, so we had a scrappy approach — which was perfect. And now we're moving across to something that is more secure, instills confidence with our partners, and allows us to maintain and deploy changes effectively. Some pretty compelling metrics. Very pleased with how it's all going, and there's still more headroom to go after."
Team impact
The internal team's response evolved from initial resistance to active enthusiasm. Early concerns about job displacement and AI hallucination risk gave way to recognition that the AI tools freed agents to focus on complex, high-impact work. Team members now actively contribute to shaping and improving the AI workflows, viewing the technology as enabling more sustainable work patterns and creating space for professional development. EV Energy's leadership was careful to frame AI as a tool rather than a replacement — with human agents remaining accountable for the overall customer experience.
What's next
Expanding AI coverage
Progressively moving more programs and ticket categories from helper-note mode to full direct response.
Proactive issue detection
Using AI to diagnose IoT device issues and virtual power plant dispatch problems before drivers need to contact support.
Energy optimization with AI agents
Applying AI to optimize the real-time dispatch and control of distributed energy resources across the virtual power plant.
AI-powered business case modeling
Enabling utility clients to model the value of energy flexibility in minutes rather than months.
Consumer agent integrations
Preparing for a future where personal AI assistants can enroll consumers into smart energy programs on their behalf.
Ready to achieve similar results?
Book a discovery call to see how Ability.ai can scale your operations.
Book a Discovery Call