Anyone Else’s Automation Break Since the New Rovo Model?

Patricia Modispacher (K15t)

 

I’m running into a strange issue with a Confluence automation that uses a Rovo Agent, and I’m curious whether anyone else has seen the same behavior.

I built an automation rule that works like this:

• a page gets a label (<span>seo-check</span>)
• the rule triggers
• a Rovo Agent is used to audit the page
• the result should be posted as a page comment
• the label is then removed

This setup used to work for me.

Since switching the agent to the new model, the automation no longer completes properly. In the audit log, the runs stay stuck on WAITING under In Progress and never finish.

What I already checked:

• the rule structure itself looks fine
• <span>{{agentResponse}}</span> is correctly used in the comment step
• I tested with my original prompt
• I also tested with a much shorter and simpler prompt
• same result: still stuck on <span>WAITING</span>

What’s even stranger is that switching back to the old model did not seem to fix it either.

So now I’m wondering:

• has anyone else seen Confluence automations with Use agent getting stuck on <span>WAITING</span>?
• did this start for anyone else after the new model rollout?
• is this a known issue with Rovo Agents in automation?

Would really appreciate any experiences or ideas. 

Arkadiusz Wroblewski

@Patricia Modispacher _K15t_  @Tomislav Tobijas 

I still believe it will take quite some time before agents behave in a truly predictable and reliable way. That is probably my biggest concern at the moment. The core issue is not only capability, but consistency: the results are still not stable enough from one case to another, which makes it difficult to fully trust them in more critical or repeatable Scenarios.