Manage AI skills and customer memory

AI skills and customer memory solve different problems. Skills are reusable business capabilities. Customer memory adds context for one specific customer.

AI skills#

Open AI → AI skills to inspect adopted and generated capabilities. A skill detail can show:

• trigger or applicable customer question;
• response steps, tool calls, and handoff boundaries;
• learning source and version;
• tests, runs, and real usage;
• current enablement state.

The execution diagram is for explanation and replay, not a requirement for merchants to edit a low-level workflow. If a skill is wrong, pause or roll it back, then create a corrected version through correction and learning review.

Customer memory#

Customer memory stores preferences, restrictions, or durable context for one customer, such as language preference or a material allergy. It does not become a skill shared with every customer.

Open AI → Customer memory or the customer profile to manage it. Incorrect memory can be edited or removed. Customer memory cannot override policy facts in the knowledge base and should not contain unnecessary sensitive data.

Use AI skills or knowledge for behavior shared across customers, customer memory for one customer's preferences, and Yuna long-term memory for the merchant team's own working preferences.