You can insert a code node in between to log the output, or enable the 'Return Intermediate Steps' option to view what is being sent.

I noticed you've included very extensive instructions in the user prompt, which is something I haven't seen before. You should only provide the user m...

Here is a comprehensive guide:

If you want to see all the steps the model is performing, enable Return Intermediate Steps docs

Veniamin_Veselovsky: Has anyone implemented a comparable solution or can offer guidance on best practices for tracking tool usage within agent memor...

Hello, I hope you are doing well. I encountered a similar issue previously, and augmenting the memory and tool with optimizations to the system prompt...

Hey there, Could you please share your workflow? This will help us provide more effective suggestions on what to add and where.