Draft Agent is stuck + Feedback issues

Support
1

Hello,

I am really excited to do agents within MindStudio. However, a few things are keeping me from using it fully:

  1. Draft Agent is stuck in a loop, so I can test things. Example => https://app.mindstudio.ai/agents/untitled-ai-agent-e4f25c5b/run/d5150607-6756-4ded-8866-b85f6020024a?draftVersionId=bbd5e0e1-2003-43e3-80b0-9b26e4335180
  2. Logic seems to always use AI, but do we really have to? It seems like a waste of tokens/AI calls when one IF is to check if a variable is empty or not (maybe planned? Do you have a release date)
  3. The Deep Research did cost me $2.5 twice, but I never got the variable populated properly. If needed, you can see the logs on the agent I am building and test ran => https://app.mindstudio.ai/agents/6cb0bcf5-b6e1-4ead-97a9-2abcb5ec647e

Thank you for your help! MindStudio is the most promising AgentBuild I have seen so far!

2

Hi @rmarenco,

Thanks for the post!

Could you record the steps you’re taking when this happens? You can use the link below to capture your screen. Please press F12 before recording so the Console tab is visible.

Link to record: Record your screen

Can you share a bit more about your use case? For example, if you’re branching your workflow only to use different Generate Text blocks, you might be able to handle that with if-else logic directly in the prompt:

Could you please share the Debugger logs for the failed run that showed the error?

To do that, open the Debugger, select the run, click Share, and reply with the URL:

image

Please make sure there’s no sensitive information in that run, as the shared log will be public.