web
You’re offline. This is a read only version of the page.
close
Skip to main content

Notifications

Announcements

Community site session details

Community site session details

Session Id :
Power Platform Community / Forums / Copilot Studio / Issues with Multi-Agen...
Copilot Studio
Unanswered

Issues with Multi-Agent Orchestration in Microsoft Copilot Studio (Teams vs. Test Behavior)

(0) ShareShare
ReportReport
Posted on by 10

I’m building a multi-agent solution in Microsoft Copilot Studio with a parent agent acting as a “Reception” bot and three child agents (System QA Bot, HR Agent, and General Affairs Agent). The parent uses generative orchestration to route queries to the appropriate child agent based on intent.

 

Problem:

In the Copilot Studio test environment, everything works as expected. For example, when I ask “I want to create an email signature,” the parent correctly calls the System QA Bot, and the child agent responds using its knowledge base.

 

However, when I publish the parent agent and run it in Microsoft Teams, the behavior changes:

 

  • The parent correctly calls the child agent.

  • The child agent immediately falls back (even for simple queries that work fine in test).

  • After the fallback, the parent agent generates its own answer using orchestration, which is often irrelevant.


  •  
 

What I’ve confirmed:

 

  • Generative orchestration is enabled only on the parent agent (as required for multi-agent).

  • Child agents are published and work perfectly when used standalone in Teams.

  • “Pass conversation history” is enabled.

  • Parent agent has zero knowledge sources (it’s meant to be a pure router).

  • The fallback message from the child agent is customized, and I see that message in Teams, so the child is definitely being invoked.


  •  
 

Observation:

When checking the child agent’s activity logs, the same query produces very different results:

 

  • In the test environment, the child retrieves relevant knowledge and generates a detailed answer.

  • In Teams, the same query shows a 0% confidence score and no knowledge retrieved.


  •  
 

Question:

Has anyone else experienced this discrepancy between test and Teams when using multi-agent orchestration?

 

  • Why would the child agent fail only when invoked via the parent agent in Teams?

  • Is there any way to adjust fallback timing or confidence thresholds?

  • Are there best practices to prevent the parent from generating answers after a child fallback?


  •  
 

Any insights or workarounds would be greatly appreciated!

I have the same question (0)

Under review

Thank you for your reply! To ensure a great experience for everyone, your content is awaiting approval by our Community Managers. Please check back later.

Helpful resources

Quick Links

Forum hierarchy changes are complete!

In our never-ending quest to improve we are simplifying the forum hierarchy…

Ajay Kumar Gannamaneni – Community Spotlight

We are honored to recognize Ajay Kumar Gannamaneni as our Community Spotlight for December…

Leaderboard > Copilot Studio

#1
Michael E. Gernaey Profile Picture

Michael E. Gernaey 261 Super User 2025 Season 2

#2
Romain The Low-Code Bearded Bear Profile Picture

Romain The Low-Code... 198 Super User 2025 Season 2

#3
S-Venkadesh Profile Picture

S-Venkadesh 93 Moderator

Last 30 days Overall leaderboard