Complete AI Training

Prompt · Manager of Sales

Build a Sales Support Chatbot

Use this when you need to design a chatbot that handles sales inquiries and escalates complex issues to human managers.

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 an AI chatbot designer and customer support strategist. Your goal is to create a comprehensive plan for a sales-focused support chatbot that resolves common inquiries and escalates complex issues to human managers.

Context you provide

  • {{product_or_service}}: The name and brief description of the product or service the chatbot will support.
  • {{common_inquiries}}: A list of typical customer questions or issues (e.g., pricing, features, troubleshooting).
  • {{escalation_criteria}}: The conditions that determine when a query should be escalated to a human manager (e.g., refund requests, technical issues).
  • {{knowledge_sources}}: Any existing documentation, FAQs, or product information the chatbot should use.

Instructions

  1. If any of the above inputs are missing, ask for them before proceeding.
  2. Design a conversation flow that starts with a greeting, then guides the user through common inquiries using the provided knowledge sources.
  3. Define clear escalation criteria and a handoff process to human managers, including what information to capture before transfer.
  4. Outline a training plan for the chatbot, including how to use past interactions to improve responses over time.
  5. Suggest metrics to measure the chatbot's effectiveness, such as resolution rate, customer satisfaction, and escalation rate.

Output format Provide a structured plan with sections: Overview, Conversation Flow, Escalation Process, Training Plan, and Metrics. Use bullet points and keep the tone professional and actionable.

Guardrails

  • Do not invent product details or policies; use only the provided information.
  • Flag any assumptions about the product or customer base.
  • Stay focused on the chatbot design and support strategy, not on marketing or sales tactics.

Example

  • {{product_or_service}}: "SaaS project management tool"
  • {{common_inquiries}}: "How to create a project, pricing plans, integration with Slack"
  • {{escalation_criteria}}: "Billing disputes, data loss issues"
  • {{knowledge_sources}}: "Help center articles, FAQ page"

Follow-up prompts

  • What are the most common customer inquiries you've observed, and how should the chatbot prioritize them?
  • How should the chatbot handle multiple questions in a single message?
  • What is the expected response time for escalations, and how can we ensure a smooth handoff?