What actually breaks when an agent meets real customers, real orders, and a real invoice. Written from the code in the catalog.
LatestEvery vendor now says agent. Most of them ship a search box with a personality. The line is simple and testable: when the conversation ends, did anything in your systems actually change?
Not the checkout. Not the theme. What changes is that two jobs nobody had time for — answering the shopper who is stuck, and working the catalog nobody opens — start happening every day.

The failure mode of a production agent is never a bad sentence. It is a real action taken confidently and wrongly. Four patterns that keep an agent useful without making it dangerous.

A chat message costs a fraction of a cent. An agent run costs twenty to a hundred times that, and the heaviest customer costs fifty times the median. Flat pricing over that is a bet, not a model.

The agent loop is a weekend. Everything around it — traces, approvals, retries, cost caps, accounts, billing — is a quarter. Here is the line I actually draw, having sold both sides of it.

1–5 of 5 posts