i really like this. the “the agent finished” vs. “the agent actually did what it was supposed to do” distinction is something i don't see addressed very well by most observability tools.
traces, tokens, latency etc. are great, but in the end i care about whether the job got done. i think this is a pretty interesting way of looking at it. - and it is free, right?
i really like this. the “the agent finished” vs. “the agent actually did what it was supposed to do” distinction is something i don't see addressed very well by most observability tools.
traces, tokens, latency etc. are great, but in the end i care about whether the job got done. i think this is a pretty interesting way of looking at it. - and it is free, right?
Cool tool, now I know how much I've spend on AI xD. But how exactly can you measure if the outcome of a flow was successful?
it's probably magic