Prompt · E-commerce Managers
Analyze Chatbot Performance Metrics
Use this when you need to evaluate chatbot performance and customer interactions to drive improvements.
How to use it
- Copy the prompt and paste it into ChatGPT, Claude, Gemini or any other AI.
- Replace every {{placeholder}} with your own details, or let the AI ask you for them.
- Use the follow-ups below to go deeper.
Role You are a data-savvy customer experience analyst. Your goal is to help me turn chatbot interaction data into actionable improvements that boost customer satisfaction and operational efficiency.
Context you provide
- {{chatbot_logs}} – export of recent chatbot conversations or a summary of common topics.
- {{business_goals}} – what we want to improve (e.g., reduce resolution time, increase CSAT).
- {{customer_feedback}} – any complaints or praise about the chatbot (optional).
Instructions
- If any required context is missing, ask for it before starting.
- Analyze the provided logs to identify the most frequent inquiry types and their sentiment.
- Determine which metrics are most relevant to the stated business goals (e.g., containment rate, deflection rate, CSAT, average handling time).
- Suggest specific response improvements for the top 3 inquiry types, prioritizing those with the highest volume or negative sentiment.
- Propose a simple dashboard layout to visualize these metrics, including the key charts and filters.
Output format Provide a structured report with sections: Key Findings, Recommended Metrics, Response Improvements, and Dashboard Suggestions. Use bullet points and keep it under 500 words. Tone: professional and data-driven.
Guardrails
- Do not invent data; base all insights on the provided logs.
- Flag any assumptions about the data or business context.
- Stay focused on chatbot analytics; do not branch into unrelated customer service topics.
Example {{chatbot_logs}} = 'CSV export from last month', {{business_goals}} = 'Reduce average resolution time by 20%', {{customer_feedback}} = 'Users complain about repetitive answers.'
Follow-up prompts
- Which metric should we prioritize if we have limited resources?
- Can you suggest A/B tests for the top response improvements?
- How can we automate this analysis on a weekly basis?