Agent studio
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
a month ago
HI Everyone,
Does Anyone knows how to conditionally display outputs in agent studio.
Example: every tool has configuration like display output Yes/No. But can we configure tools like based on the scenarios it should display output or else it shouldn't
Use case:
First tool : I have to check if an RITM ticket was already created for a specific CatLog item for a specific item if yes then i have to display The RITM number
Second Tool: This tool should create the RITM ticket for the catalog item.
The issue the output of first tool will always be displayed even though there is no RITM number
So is there any way we can conditionally display these..
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
a month ago
I’m not sure, but have you tried using the decision table in Agent Studio? I have no idea whether this is feasible or not, but it’s worth giving it a try.
Regards
Dr. Atul G. - Learn N Grow Together
ServiceNow Techno - Functional Trainer
LinkedIn: https://www.linkedin.com/in/dratulgrover
YouTube: https://www.youtube.com/@LearnNGrowTogetherwithAtulG
Topmate: https://topmate.io/dratulgrover [ Connect for 1-1 Session]
****************************************************************************************************************
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
a month ago
Hi!
There are several ways to tackle this and it all depends on how you are configuring the interaction. If the interaction is being done through a Virtual Agent then what you are describing should be on configured on the Virtual Agent conversation side. Can you please share which channel you'll have the interaction through?
If the entire action is carried from the agent itself and that is how you want it to be invoked then this all needs to be addressed within the agent instructions.
In your agent's system prompt, explicitly instruct the agent: "Only present the RITM number to the user if Tool 1 returns a valid result. If no RITM is found, silently proceed to Tool 2 without surfacing Tool 1's output." This is the most practical approach — the LLM will respect well-crafted instructions on when to speak vs. stay silent. You can then tie that to a flow or even another agent that performs the second half of your request.
