The Steward

Service agents handle inbound customer conversations: answering from a knowledge base, looking up orders and accounts, resolving routine requests, and escalating what they cannot finish. Some draft replies for a human to send; others reply directly.

• High-volume, well-documented, repetitive requests
• Being available at three in the morning without degradation
• Retrieving the right article or record faster than a person can search
• Keeping a consistent tone across thousands of conversations

• Long threads that contain several unrelated problems
• Situations where the customer is distressed and the policy answer is the wrong answer
• Anything where the knowledge base is stale, contradictory, or absent
• Recognising the limits of its own confidence without an explicit threshold

• Reliability: a confident wrong answer to a customer is worse than no answer.
• Transparency: in the EU, people must be told they are dealing with an AI system.
• Data: conversation logs are personal data, frequently including special categories customers volunteer.
• Displacement: deflection targets set without a quality floor tend to produce both.

• Ask how escalation is triggered, and what confidence threshold sits behind it.
• Ask for quality figures alongside deflection figures. One without the other is not evidence.
• Read a real transcript sample, not a demo.
• Confirm where conversation data is stored and for how long.