
One of the very first things that we did as a company was include a feedback endpoint that the agent could auto trigger if it ran into any issues We had a setup where it would get sent to my support email and would flag it in our slack, so we could take a look and implement a fix if needed Super effective mechanism, MCP's are also very early
This is why you should actively invest in an embedded agent and an MCP. MCP observability only allows you to see tools called and you have to reverse engineer intent. If you have an actively used embedded agent, you would have seen this query and been able to ID that the proper filters were not in place. Fix the tool and it benefits both surfaces. You can also get a lot of benefits by adding a submit_feedback tool to your MCP to gather this data.
















