Fin AI Copilot uses machine learning to source answers from your support content, including past conversations, public articles, internal articles, and snippets. Before using Fin with your support team, it’s worth taking some practical steps to ensure the knowledge is available and optimized for AI.

Fin will work with our new Knowledge feature for managing all content. You'll automatically be given access to this feature when your workspace is added to the Fin AI Copilot beta. Join the waitlist if you haven't opted in yet.

Below are some steps you can take to set Fin and your teammates up for success while you wait for access to the Fin AI Copilot beta.

If you’ve got existing support content in your knowledge base, the first thing you should do is review and ‘cleanse’ that content. AI is only as good as the knowledge you give it, so if your content is out of date, the answers Fin provides your teammates will be less accurate too.

Check for accuracy and update or archive content where necessary. From sales and engineering, to legal and security - knowledge can be created by multiple teams and subject matter experts (SMEs). So divide your content by owner and ask each team or SME to review their knowledge area.

Once all your content has been fact-checked by experts, you should start looking at how each article is structured. When creating content for AI, there are some formatting best practices that can make a big difference between making the answer available, and allowing Fin to easily find and use that answer in the right context:

Ensure you’re not missing any important content. Use reporting to find “Searches with no results” and see what customers or teammates have been unable to find in your current knowledge base. You should also talk to your support team and other stakeholders and get them to inform on knowledge gaps or which resources they’d like to have more of.

Fin AI Copilot can access both internal and public articles from the Knowledge hub. With all knowledge coming together under one roof, you need to build a solid Information Architecture (IA).

A good IA organizes content in a clear and logical way to enable teammates to navigate and find content quickly, and helps maintain consistency when new content is added because every piece of information has a clear home.

This means creating a hierarchical folder structure which could look something like this:

If your existing knowledge base lives in Guru, Notion or Confluence, good news - you’ll be able to import it all across to your new Knowledge hub and keep your existing IA 😃

The new Knowledge hub will automatically be available to all customers on the Fin AI Copilot beta. Once you have access to the beta, you can start importing or creating new content directly from here.

You can also decide which of this content you want to allow teammates to use with Fin AI Copilot.

After investing in a tip-top knowledge base to power Fin AI Copilot and your support team, you don’t want to let content become stale and unhelpful. This will not only negatively impact Fin’s performance, but also reduce all teammate efficiency gains you made by having this knowledge readily available and accessible.

Consider implementing a feedback loop which enables your support team (or even your wider org) to flag inaccuracies, suggest improvements, and request new content to fill any knowledge gaps.

We use Back-office tickets to enable our teammates to submit these requests straight from the Help Desk. If Fin gave an answer that didn't help, they can check the source(s) used and open a ticket to get the content improved without leaving the inbox or losing too much time.

Our knowledge team ensures these requests are actioned within a week and lets the teammate know by responding to the ticket and closing the loop. This way, teammates are helping themselves and each other find accurate answers faster by giving Fin improved content to use in the future.