After a lot of testing, iterations, and working through the Intercom review process, Iโm happy to share that ChatShield is now officially listed on the Intercom App Store. ๐
ย
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.
ย
It looks for things like:
ย
Unsupported promises or commitments
ย
Potential privacy/data issues
ย
Incorrect policy claims
ย
AI representation issues
ย
Potentially risky financial or compliance-related responses
ย
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.
ย
This is still an early-stage product, so I'm especially interested in hearing from Intercom teams using AI or automation in customer support:
ย
How are you currently checking whether your AI/support conversations contain risky responses?
ย
If you'd like to take a look at ChatShield, it's now available through the Intercom App Store.
ย
ChatShield