After a lot of testing, iterations, and working through the Intercom review process, Iβm happy to share that ChatShield is now officially listed on the Intercom App Store. π
Β
ChatShield monitors customer support conversations across the workspace and helps teams surface conversations that may deserve human review whether the response came from an AI agent or a human support agent.
Β
It looks for things like:
Β
Unsupported promises or commitments
Β
Potential privacy/data issues
Β
Incorrect policy claims
Β
AI representation issues
Β
Potentially risky financial or compliance-related responses
Β
The goal isn't to replace human review or legal/compliance teams. It's simply to help teams find the conversations that are worth looking at instead of manually checking everything.
Β
This is still an early-stage product, so I'm especially interested in hearing from Intercom teams using AI or automation in customer support:
Β
How are you currently checking whether your AI/support conversations contain risky responses?
Β
If you'd like to take a look at ChatShield, it's now available through the Intercom App Store.
Β
ChatShield