What I like most is how easy it is to build AI agents without extensive coding.
The low-code experience feels familiar for teams already using UiPath.
It allows us to combine AI reasoning with existing automation workflows.
Testing and refining agents is straightforward.
This helped us experiment with agentic automation much faster. Review collected by and hosted on G2.com.
One area that could be improved is debugging and troubleshooting.
When an agent does not behave as expected, identifying the root cause can take time.
More detailed logs and diagnostics would be helpful.
Since the product is still evolving, some features feel less mature than core UiPath offerings.
Overall, these have been manageable challenges. Review collected by and hosted on G2.com.