Field notes · Topic
Customer & commerce.
Customers notice every AI mistake, so the work starts with helping the people who serve them. These notes cover service operations and online selling, from the first suggested reply to catalogs spread across several marketplaces.
8 notes
Notes on this topic
-
Chatbot or agent assist: where should customer service AI start?
Start with AI that helps agents: suggested replies with sources, summaries and routing. Agents catch the mistakes while you learn which requests are safe to automate, then open self-service for those few, with a person always one step away.
-
How to measure AI in customer service beyond handle time.
Average handle time can fall while customers call back. Measure resolution, repeat contacts, the accuracy of cited answers, how much agents edit drafts, escalations and satisfaction by request type, against the baseline recorded before launch.
-
WhatsApp customer service with AI: what to automate and what not to.
Customers treat WhatsApp like a conversation with a person, so automation has to be quick, honest about being automated and one message away from a human. Automate lookups such as order status first; keep complaints, payment problems and anything sensitive with people.
-
Handing a customer from bot to person without making them repeat it.
The handover decides how customers remember the automation. Escalate on clear triggers, pass a summary with the data already gathered, and tell the customer honestly what happens next.
-
How to design an intent taxonomy that AI routing can live with.
Routing fails more often because of the categories than because of the model. Fewer, mutually exclusive intents, each with examples and an owner, make AI routing measurable.
-
Product descriptions with AI that don’t all sound the same.
Generated descriptions go wrong in two ways: invented features and identical copy across thousands of products. Write only from verified attributes, vary structure by category, list the claims the model may never make, and let merchandisers approve what is published.
-
Mapping your catalog to every marketplace’s categories with AI.
Each marketplace has its own category tree and required attributes, and a wrong category hides a product or gets it rejected. AI can propose categories and fill attributes from your data, while people approve each new mapping once.
-
Making AI replies sound like your brand in Turkish and English.
Models follow examples better than adjectives. A tone guide for AI replies needs rules a model can apply (form of address, sentence length, what never to say, how to apologize), paired examples in each language and checks in the evaluation set.