Short write‑ups of problems we hit running a real commerce operation and what we changed in the code because of them. No product announcements; just the reasoning.
We log every call an assistant makes to our MCP server — who, which tool, how long, did it fail and why — and put it on a sysadmin dashboard. Two weeks of data found a user whose assistant had made 454 calls with a 100% error rate, and fixed the server's instructions instead of the user.