Conversation design: How to make your AI Agent communicate like your team

Summary

AI agents need deliberate conversation design to communicate effectively with customers, covering tone, response structure, handoffs, interaction flow, and response quality. The post argues that without an explicit owner, an agent may over-explain, sound flat during frustration, or escalate too late, undermining trust and prompting customers to seek human help. It recommends defining a concise voice reference, adapting register to the situation, matching detail to the question, supporting customer-led topic changes, designing informative handoffs and follow-ups, and keeping behavioral instructions separate from knowledge-base content. Teams can begin without a dedicated hire by naming an owner, selecting a poorly performing conversation type, auditing instructions, and fixing the worst handoff first. At Fin, an A/B test raised CSAT from 72.8% to 78.4%.

Takeaways

1. 1

   At Fin, an A/B test of a warm, conversational opening message increased CSAT from 72.8% to 78.4%.

2. 2

   Handoffs should carry the conversation history, issue context, actions already taken, and escalation reason so customers do not have to repeat themselves.

3. 3

   Behavioral guidance belongs in Agent instructions, while content and information belong in the knowledge base; concise rules are preferred over lengthy explanations.