Hey all — we have put together an early prototype of how external agents show up inside Front, and we'd love your feedback before we lock scope.
I recorded a short walkthrough (6 min) so you can watch async on your own time:
🎥 Video Link, Passcode: !e6jPNn?
The video covers three things:
- Setting up an AI teammate — connecting your external agent to Front
- A live conversation — your agent picks up a conversation, drafts a reply, and asks a human a question
- The AI Command Center — where your agent's performance is measured and improvements are flagged
What we need from you — reply with the question number so we can follow the thread easily:
- In the setup flow shown, is anything missing or confusing for how you'd connect your agent?
- Looking at the conversation demo — does the way the agent drafts and hands off to a human match how you'd want it to work?
- How are you monitoring and governing your agents today, and what key quality/performance metrics do you track?
- What's the most impactful issue you've found and fix you've made to one of your agents?
- If Front surfaced diagnostic and improvement opportunities for your agent, would you be willing to share reasoning traces — sources used, reply failures — via Front's MCP?
If it's easier to talk live, drop a comment and we will add you to the recruitment list for future research sessions. Thanks 🙏
