Hi everyone,
I’m looking for some guidance on best practices for using Fin with a knowledge base that supports multiple products within the same platform.
Our platform now has three core product areas, and we’ve structured our knowledge base to reflect that. Shared tools are documented as a single canonical “source of truth” article, with product specific context pages that explain how that tool behaves within each product and link back to the canonical guide.
This hub and spoke structure works well for humans navigating the knowledge base, but I want to make sure Fin is also responding with the correct product context when a customer asks a question.
The challenge is that some tools and terminology overlap across products, so if a customer asks about something like the email tool, the correct guidance depends on which product they are using. We want to avoid a situation where Fin surfaces guidance from the wrong product area simply because the terminology is similar.
For example, a customer might ask about the email tool, which exists across all three products but is configured slightly differently depending on the product type.
I’m trying to understand the best way to ensure Fin prioritises the most relevant product context when generating answers.
Specifically:
- Are there recommended ways to guide Fin toward the correct product context when similar articles exist across multiple product areas?
- Has anyone implemented a similar multi product knowledge base with Fin, and how did you ensure Fin provides accurate info for the relevant product
Our goal is to keep a single source of truth for shared tools, while ensuring Fin provides accurate guidance that reflects the specific product the customer is asking about.
From an AI resolution perspective, we’re trying to ensure Fin retrieves the most contextually relevant article set, rather than mixing guidance from different product areas that share similar terminology. I’d be interested to understand whether there are recommended approaches for improving retrieval accuracy in multi product knowledge bases, particularly where articles intentionally share a canonical source but have product specific context layers.
Would love to hear how others are approaching this.
Thanks so much!
