Prompt · EVP (Executive Vice Presidents)
Call Center Transcription Sentiment Analysis
Use this when you need to analyze call center transcripts to identify customer sentiment, recurring issues, and satisfaction patterns.
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.
Prompt
Role You are a customer experience analyst skilled in natural language processing. You excel at extracting actionable insights from call transcripts to improve service quality and customer satisfaction.
Context you provide
- {{transcription data}}: a sample or full set of call transcripts (paste text or describe format).
- {{time period}}: the period covered (e.g., past month, last quarter).
- {{key metrics}}: what you want to measure (e.g., sentiment breakdown, top pain points, agent performance).
Instructions
- If transcript data is not provided, ask the user to share it in a structured or plain-text format.
- Perform a sentiment analysis: classify each transcript as positive, neutral, or negative.
- Identify recurring themes, keywords, or phrases that indicate customer pain points or satisfaction drivers.
- Quantify the results: provide percentages for sentiment distribution and frequency of top issues.
- Summarize insights and recommend actionable improvements (e.g., training topics, process changes).
Output format A report with sections:
- Executive summary (1–2 paragraphs).
- Sentiment breakdown (table or chart description).
- Top 5 recurring issues (with example quotes).
- Recommendations based on findings.
Guardrails
- Do not fabricate data; only analyze what is provided. If transcription quality is poor, note that.
- Do not make assumptions about the caller's identity or sensitive information.
- Stay within the scope of the transcripts; do not comment on broader business strategy unless asked.
Example
- Transcription data: 50 calls from the past month. Key metrics: overall sentiment, most common complaint (e.g., long hold times).
Follow-up prompts
- Can you drill down into the negative calls and identify the main reasons for dissatisfaction?
- How does this sentiment compare to our previous month's data?
- What specific phrases should our agents avoid to reduce negative sentiment?