Question for Intercom users: How do you review risky support conversations?

Hey everyone 👋

I'm an indie founder building ChatShield, a tool that helps support teams identify potentially risky conversations across their workspace not just AI chatbot replies, but human-agent conversations too.

For example, an agent might accidentally promise an unauthorized refund, make an incorrect pricing commitment, or share information they shouldn't.

I'm trying to understand how Intercom teams currently catch these issues.

A few questions:

- Do you manually review conversations, use internal QA, or have another process?

- Are mistakes by human agents as much of a concern as AI-generated replies?

- Would automated flagging of conversations for human review be useful to your team?

I'd genuinely appreciate hearing how you're handling this today. I'm also looking for a few Intercom teams willing to test ChatShield and give honest feedback.

Product: https://chatshield.cloud/

Thanks!