feels like the industry figured out how to build ai agents faster than how to understand them.
everyone demos agents.
very few teams can confidently answer:
why an agent failed
what changed between runs
whether quality is improving or regressing
or if the agent is actually reliable over time
curious how people here are handling this today.
MyLens AI
Great pain to tackle, Sina. Good luck.
PandaProbe
Manufact (mcp-use)
Congrats on the launch and thanks for using mcp-use :)
PandaProbe
@pederzh thanks for the support Luigi. I'm a big fan of mcp-use :)