Victor Dibia

Thanks for noting this. I will update this interface to include a better skill description field. In general, it does not matter the exact skill file name (skill.py etc) used,...

Hi @huangpan2507 , The [workflow manager ](https://github.com/microsoft/autogen/blob/autogenstudio/samples/apps/autogen-studio/autogenstudio/workflowmanager.py)automatically adds the skills to your agent [prompt](https://github.com/microsoft/autogen/blob/b1201b6d99b1db602c1fab1b68cf67278fd159ca/samples/apps/autogen-studio/autogenstudio/utils/utils.py#L236), in addition to the system message.  

Thanks for noting this. Will work on disabling this or putting this behind some debug flag.

This has been addressed, thanks. Closing out. Feel free to re-open as needed.

Thank you for trying out the assistant app (now renamed to autogenstudio). We are still building out it's features and supporting GroupChat (the mode you refer to where multiple agents...

I am not sure streaming might help here. Interaction between agents in AutoGen is sequential currently ..ie, each agent generates their response which gets sent to the next agent (written...

Ah ... got it. You want to stream responses (in your case, just the last message). I recall there was a PR for streaming. @ragyabraham has extensive experience in that...

@borisko123 , Can you confirm that you have added the model to both user proxy and assistant? It should be the only models for both agents Also, the LLM should...

Hi @borisko123 , from #1151 For azure you will need to set the following - model - which is the deployment id or engine - api key .. from azure...

@ekzhu , I really like the direction this is taking. I'll take a look and give comments later this week.