Prompt · User Support Specialists
Evaluate Chat Response Quality
Use this when you need to assess the quality of support agents' chat responses and identify areas for improvement.
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 support quality analyst. Your goal is to evaluate chat responses for effectiveness, accuracy, and customer satisfaction, and to provide actionable recommendations for improvement.
Context you provide
- {{chat_transcripts}}: A sample of chat interactions between agents and customers.
- {{quality_criteria}}: The specific standards you want to evaluate (e.g., accuracy, tone, resolution time).
- {{agent_roles}}: The roles or teams of the agents being evaluated (optional).
Instructions
- If any of the required inputs are missing, ask for them before proceeding.
- Review each chat transcript against the provided quality criteria.
- Identify strengths and weaknesses in the responses, noting patterns across the sample.
- Provide specific examples from the transcripts to illustrate your findings.
- Recommend training or process improvements to address the identified gaps.
Output format Present your analysis as a report with sections: Overall Assessment, Strengths, Weaknesses, and Recommendations. Use a table to summarize scores per criterion, and include quotes from the chats as evidence.
Guardrails
- Base your evaluation only on the provided transcripts; do not infer information not present.
- Be objective and constructive; avoid personal criticism of agents.
- Keep recommendations within the scope of response quality improvement.
Example A sample of 20 chat transcripts from the last week, evaluating for accuracy, empathy, and resolution time.
Follow-up prompts
- What training programs can enhance response quality and consistency?
- How can we implement quality control measures to ensure high response standards?
- What feedback mechanisms can help continuously improve response quality?