---
name: al-677-put-an-ai-first-responder-on-ev-charging-support-so-drive
description: "Salesforce published a Nov 6, 2026 customer story on Greenlane, which is building a high-power charging network for commercial electric trucks. With its first site live and more planned, drivers on tight delivery schedules needed fast answers about charging sessions, reservation holds, billing and onsite access, but shared call-center agents lacked the detailed context. Greenlane configured Agentforce on its existing Salesforce stack (Service Cloud, Data 360, Slack) so the agent pulls from curated knowledge articles and never invents an answer missing from approved sources. The team wrote over 100 test scenarios, including messy spoken paraphrases and alternate hardware names, and measured accuracy, handle time and escalation. Early testing reported 98% AI response capability across 106 scenarios, answers 58% faster than the shared call-center model, and 15% higher answer accuracy. Figures are Greenlane's as reported by Salesforce; the agent is positioned as first responder with a…"
---

# Put an AI first-responder on EV charging support so drivers get answers about sessions, billing and site access without waiting on a shared call center

Salesforce published a Nov 6, 2026 customer story on Greenlane, which is building a high-power charging network for commercial electric trucks. With its first site live and more planned, drivers on tight delivery schedules needed fast answers about charging sessions, reservation holds, billing and onsite access, but shared call-center agents lacked the detailed context. Greenlane configured Agentforce on its existing Salesforce stack (Service Cloud, Data 360, Slack) so the agent pulls from curated knowledge articles and never invents an answer missing from approved sources. The team wrote over 100 test scenarios, including messy spoken paraphrases and alternate hardware names, and measured accuracy, handle time and escalation. Early testing reported 98% AI response capability across 106 scenarios, answers 58% faster than the shared call-center model, and 15% higher answer accuracy. Figures are Greenlane's as reported by Salesforce; the agent is positioned as first responder with a clear route to humans for edge cases.

## Inputs to collect first
Ask the user for anything below that they haven't already given you. Don't guess missing facts.

- EV charging / field service
- FAQs, billing rules, site access notes, hardware names and slang…

## Instructions

Do the task below with the user's inputs in place of each [bracket].

Build a first-responder support agent for my [EV charging / field service] network. Knowledge I will paste: [FAQs, billing rules, site access notes, hardware names and slang drivers use]. Rules: answer only from that knowledge; never invent a price, status or fault code; escalate when the question needs live equipment control, a refund, or a human. 1) Turn my knowledge into short articles tagged by topic (start a charge, billing, access, hardware slang). 2) List 20 test questions in the messy way drivers actually talk, plus the expected answer or escalate. 3) Draft the agent instructions: greet, identify the site/session if mentioned, answer from articles, ask one clarifying question when needed, escalate with a handoff note. 4) Propose a weekly review: which tests failed, which slang to add, escalate rate. Do not connect to a live system in this chat.

## Safety checks (share these with the user)

- Check every figure, price and total against your own records before anything is sent, posted or booked. A person approves refunds, discounts, payments and price changes.
- Remove names, contact details, account numbers and other personal data the task doesn't need before you paste, and check your AI tool's data and training settings.
- Check names, dates, numbers and any claim against your own source material before you use the answer. AI can misread or invent details.
- Say clearly which parts need a person to review or approve before anything is sent, paid, posted or filed.

## About this skill

- Works with: Agentforce, Salesforce Service Cloud, Slack, ChatGPT, Claude
- Based on this real-world example: https://www.salesforce.com/customer-stories/greenlane/
- Free prompt from AgentPlaybook Real Estate: https://agentic-library.netlify.app/prompt/al-677-put-an-ai-first-responder-on-ev-charging-support-so-drivers/
- To install in an agent that supports Agent Skills, save this file as SKILL.md in a folder with the same name as `name` above (for example in your skills directory). Install steps for Claude.ai, Claude Code, Cursor and Codex: https://agentic-library.netlify.app/skills/