Hi Folks - I work for a small software company and we’ve been using FIN for a year or so. Its been doing really well and I am looking for different ways to improve its reach.
One item I am curious to hear from this community about is defect management. If a user is chatting FIN about a bug, what are your underlying training processes for the bot to handle this? At the moment, our bot points towards a human agent but I would like to find ways to automate this.
In our experience, it’s more about having established troubleshooting processes and documentation before something is escalated or characterized as a bug (for users, even expected behaviors might seem like bugs).
If you feed this knowledge to Fin along with some guidance prompts, you already have most of the zero-level/first support worked out for you.
In general, it might look something like:
1. Detailed troubleshooting articles (with solutions) or internal knowledge for Fin related to your product features.
2. Guidance that makes Fin more likely to ask follow-up questions to vague user requests (e.g. “it’s not working”.)
3. Clear escalation procedures and data collection with automated ticket creation (optional).
This would be a good use of Tasks.
Create a task and give fin the guidance if the user thinks they’ve found a bug, follow these steps to troubleshoot and collect info in your workflow, and if need be, create an internal ticket. Or connect to an external system like Jira, and then snooze the conversation to follow up later per your internal processes.
Join the Intercom Community 🎉
Already have an account? Login
Login to the community
No account yet? Create an account
Intercom Customers and Employees
Log in with SSOEnter your E-mail address. We'll send you an e-mail with instructions to reset your password.