You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
To get visibility into what agents are doing, I'm logging all actions to LangFuse. This was already non-trivial (see previous discussion and my solution).
This is a good start, but the main pitfalls are:
Logs are aggregated by agent, which makes it hard to recover a linear timeline (the events/actions within one agent are sorted by time, which is nice).
For parallel workflows, I'd like to see a DAG of invocations, which by definition doesn't agree with the linear nature of LangFuse.
Any advice on how to get better monitoring of what the agents are doing (preferably some sort of DAG visualization)?
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
To get visibility into what agents are doing, I'm logging all actions to LangFuse. This was already non-trivial (see previous discussion and my solution).
This is a good start, but the main pitfalls are:
Any advice on how to get better monitoring of what the agents are doing (preferably some sort of DAG visualization)?
Current visualization via LangFuse:
Beta Was this translation helpful? Give feedback.
All reactions