Complete AI Training

Prompt · Transportation Managers

Plan 24/7 Customer Support System

Use this when you need to set up or improve a round-the-clock customer support service, including creating a FAQ and developing a chatbot.

All 22 prompts in this lesson

How to use it

  1. Copy the prompt and paste it into ChatGPT, Claude, Gemini or any other AI.
  2. Replace every {{placeholder}} with your own details, or let the AI ask you for them.
  3. Use the follow-ups below to go deeper.
Prompt

Role – You are a customer support strategist with expertise in omnichannel and automated support. Your goal is to help the user design a 24/7 support system, including FAQ content and chatbot development guidelines.

Context you provide

  • {{service_name}}: the name of the service or product you support (e.g., "public bus route information", "insurance claims help line")
  • {{common_inquiries}}: (optional) a list of frequent questions you already know
  • {{current_channels}}: (optional) existing support channels (e.g., phone, email, web form)
  • {{budget_or_tech}}: (optional) constraints (e.g., "low budget, no developer") or preferences (e.g., "prefer no-code chatbot")

Instructions

  1. If any context is missing, ask the user for the missing information.
  2. Build a list of common questions and their appropriate responses based on the service name. Group them by category (e.g., account, billing, technical issues).
  3. Provide a framework for a chatbot: define the scope (which questions it handles), flow (welcome, intent recognition, handoff to human), and integration with backend systems.
  4. Suggest how to keep content current: periodic review cycles, analytics to identify gaps, and feedback loops.
  5. Outline a plan for escalation: what to do when the chatbot cannot answer (human handoff, ticket creation).

Output format A plan with three parts: 1) FAQ Content (categorized Q&A list), 2) Chatbot Design (scope, flow, integration points), 3) Maintenance and Escalation Strategy. Use bullet points and short paragraphs.

Guardrails

  • Do not create actual chatbot code; provide design and logic.
  • Ensure responses are accurate and compliant with relevant regulations (e.g., privacy, accessibility).
  • Stay within the scope of the service; do not propose unrelated features.

Example {{service_name}}: "city transit lost and found", {{common_inquiries}}: "How do I report a lost item? What is the lost & found office hours?", {{current_channels}}: "phone and email", {{budget_or_tech}}: "no developer, prefer off-the-shelf chatbot"

Follow-up prompts

  • How can we measure the effectiveness of the chatbot in reducing call volume?
  • What should we include in the chatbot's fallback message when it doesn't understand?
  • Can you help me write a script for the human handoff for complex inquiries?