---
title: "The Ticket: Fueling The AI machine with the knowledge it needs"
description: "The performance of an AI-driven customer support engine depends directly on the quality of the knowledge that feeds it, as accurate, up-to-date content is critical for giving customers instant and trustworthy answers. Investing time and care into help content can significantly boost automated resolution rates, as Intercom has experienced firsthand. Many busy support teams struggle to prioritize maintaining their help centers due to limited resources, but filling content gaps and updating content after launching new products is essential for AI success. Knowledge content compounds in value over time; Intercom’s transition from its Resolution Bot to the Fin AI chatbot resulted in resolution rates skyrocketing from the start. Knowledge management should be cultivated as a company-wide responsibility, with input from product, engineering, sales, and marketing teams, and in the near future, internal knowledge will also be fed to AI to help agents answer complex queries."
---

# The Ticket: Fueling The AI machine with the knowledge it needs

[Intercom](https://yomu.fyi/company/intercom) · Oct 5, 2026

**Type:** Problem & solution

## Summary

The performance of an AI-driven customer support engine depends directly on the quality of the knowledge that feeds it, as accurate, up-to-date content is critical for giving customers instant and trustworthy answers. Investing time and care into help content can significantly boost automated resolution rates, as Intercom has experienced firsthand. Many busy support teams struggle to prioritize maintaining their help centers due to limited resources, but filling content gaps and updating content after launching new products is essential for AI success. Knowledge content compounds in value over time; Intercom’s transition from its Resolution Bot to the Fin AI chatbot resulted in resolution rates skyrocketing from the start. Knowledge management should be cultivated as a company-wide responsibility, with input from product, engineering, sales, and marketing teams, and in the near future, internal knowledge will also be fed to AI to help agents answer complex queries.

## Context

This is a summary of an episode of Intercom’s The Ticket podcast, where directors from Intercom discuss the role of knowledge management in powering AI customer support. They share lessons from Intercom’s own experience, including the move from Resolution Bot to Fin, and argue that keeping help content up-to-date and involving multiple teams is critical for AI success.

## Approach / What changed

The approach involves cultivating a company-wide culture of knowledge management where multiple teams (product, engineering, sales, marketing) contribute to creating and refreshing help content, and a system is established for teammates to flag outdated content or suggest new additions. This ensures the AI chatbot (Fin) is fed accurate, up-to-date knowledge.

## Takeaways

- Keeping the help center up to date is essential for AI to deliver instant, precise answers to customers, increasing satisfaction and reducing repetitive queries for support teams.
- Knowledge content compounds in value over time; Intercom’s move from Resolution Bot to Fin saw resolution rates skyrocket, demonstrating the long-term payoff of content investment.
- Knowledge management should be a company-wide responsibility, with input from product, engineering, sales, and marketing to create and maintain content, not left to support alone.

## FAQ

### Why is knowledge management critical for AI customer support?

AI support engines need accurate, up-to-date help content to give customers trustworthy answers. Without quality knowledge, the AI cannot resolve issues effectively, so investing in content management directly boosts automated resolution rates.

### How did Intercom improve its automated resolution rates?

Intercom transitioned from its old Resolution Bot to the Fin AI chatbot, which was fed with high-quality help content. This change resulted in resolution rates skyrocketing, showing the compounded value of good knowledge.

### Who should be responsible for knowledge management?

Knowledge management should be a company-wide responsibility. Input should come from product, engineering, sales, and marketing teams, not just support. A system should be established for flagging outdated content.

**Tags:** [AI](https://yomu.fyi/topic/ai), [Customer Support](https://yomu.fyi/topic/customer-support), [Knowledge Management](https://yomu.fyi/topic/knowledge-management)

- Source: [Intercom](https://www.intercom.com/blog/videos/fueling-ai-machine-knowledge)
- Source URL: https://www.intercom.com/blog/videos/fueling-ai-machine-knowledge
- Ingested by Yomu: 2026-10-05T18:01:04.315Z

[Read original post](https://www.intercom.com/blog/videos/fueling-ai-machine-knowledge)