Improvement recommendations

The most powerful way to use MCP is to ask for actionable recommendations to improve your AI Agent’s performance. The AI assistant will analyze your conversation data, review your current configuration, and suggest specific improvements.

Prompt	What you’ll learn
”How can I improve my CSAT?”	Actionable recommendations based on patterns in low-satisfaction conversations.
”How can I improve my automated resolution rate?”	Specific suggestions for reducing unresolved conversations.
”What should I change to reduce handoffs to human agents?”	Recommendations for handling more conversations automatically.
”Analyze my unresolved conversations from last week and tell me what’s missing.”	Gap analysis with specific knowledge, coaching, or playbook suggestions.

These prompts work best when you’re specific about timeframes. For example: “How can I improve my CSAT? Focus on conversations from the last 7 days.”

Ask the assistant to call get_improvement_guide first — it explains which Ada entity types to use and recommends prioritizing articles and playbooks over coaching for root-cause fixes.

Prompt	What you’ll learn
”How can I improve my CSAT?”	Actionable recommendations based on patterns in low-satisfaction conversations.
”How can I improve my automated resolution rate?”	Specific suggestions for reducing unresolved conversations.
”What should I change to reduce handoffs to human agents?”	Recommendations for handling more conversations automatically.
”Analyze my unresolved conversations from last week and tell me what’s missing.”	Gap analysis with specific knowledge, coaching, or playbook suggestions.

These prompts work best when you’re specific about timeframes. For example: “How can I improve my CSAT? Focus on conversations from the last 7 days.”

Ask the assistant to call get_improvement_guide first — it explains which Ada entity types to use and recommends prioritizing articles and playbooks over coaching for root-cause fixes.