Great AI support starts with great documentation. To train Fin effectively, you need more than just a Help Center; you need a living, evolving knowledge management system that keeps pace with your business and meets customer expectations for fast, reliable answers.
At Intercom, we’ve refined our approach to knowledge management through hands-on experience, training Fin to achieve a 80% resolution rate. In this guide, we share the best practices and workstreams we’ve developed to help you implement a knowledge system that delivers results for Fin, your team, and your customers.
If you're just starting to build your knowledge base, we recommend reading this guide first. Once you're up and running, come back here for ongoing knowledge management tips.
Align knowledge with product changes
What we recommend:
Partner with your product team to establish a process for keeping support content in lockstep with product releases. This includes:
Asking product managers or engineers to share details of every product change (these can be scrappy internal notes!)
Translating product release notes into customer-facing help center articles and internal content like macros or troubleshooting documentation.
Updating screenshots, instructions, and embedded links whenever the product UI changes.
Running targeted audits for major updates to ensure all impacted knowledge is current.
Example:
For a typical product release, you might expect to create or update 3-6 articles and a similar number of macros. At Intercom, we use AI to generate first drafts from internal release notes and can review and publish the polished, customer-facing and AI-optimized content in less than an hour. A significant or widespread product change may require 5-8 hours to update relevant content across internal and external sources.
Use Fin's content suggestions
What we recommend:
Fin will surface suggestions when it identifies knowledge gaps based on conversations that required escalation. These may include article edits, removing duplicates, fixing contradictions, or adding entirely new articles/snippets from answers the support team provided. These are highly actionable suggestions which require minimal effort.
We recommend reviewing these suggestions weekly to decide whether to accept, revise, or reject them, then updating your content accordingly.
Example:
A weekly review might yield 10-15 Fin suggestions. Most are small updates that can be implemented in under an hour.
Enable your support team to flag issues
What we recommend:
Encourage your team to flag content gaps or errors they encounter in the course of helping customers. This could include:
Fin giving an incorrect or unhelpful response.
Customers being unable to self-serve an issue.
Outdated screenshots or language in articles.
Set up a simple submission process (e.g. a ticket form or inbox macro which tags the conversation), and review these suggestions weekly.
Example:
At Intercom, support teammates often surface 15-20 content suggestions per week. These involve clarifying steps in an article, correcting product behavior descriptions, or updating internal resources. Each suggestion typically takes 15-45 minutes to action.
Refresh outdated knowledge regularly
What we recommend:
At least every month, review content that hasn’t been updated in 6+ months. Focus on:
High traffic articles with high Fin involvement
Outdated UI images or terminology
Features that no longer exist
Redundant or duplicate content
Example:
Filtering your content by "last updated" might show 50-60 articles which haven't been updated for over 6 months. Reviewing and updating these can be completed in 7 hours by subject matter experts e.g. product managers, or support agents who handle that topic area. If you have a large knowledge base, just review one folder at a time.
Fix underperforming content and optimize for AI
What we recommend:
Even if your content is factually correct and up to date, it may still perform poorly when used by Fin. Unlike human readers, AI relies heavily on clear structure, unambiguous phrasing, and strong alignment with customer intent. Monitor Fin’s resolution rate with each piece of content to spot frequently used but underperforming content (these are prime candidates for improvement, and small changes here can have a big impact).
Focus on the top 20% of content by Fin involvement rate.
Flag items with a resolution rate below 50% as candidates for optimization.
Use AI tools like Claude or ChatGPT to quickly optimize content so it better aligns with the correct topic, uses common customer phrasing, removes ambiguity, and is easier for AI agents to parse.
Example:
Every month you might identify 10 articles with a high involvement rate but low resolution rate. Each one typically takes 5 minutes to restructure and publish an optimized version using AI.
Capture expected product behavior
What we recommend:
Sometimes a customer question uncovers a behavior that seems confusing or unexpected at first, but is actually how the product is designed to work. When this happens:
Capture the teammate’s explanation that resolved the customer confusion.
Tag the conversation so that it can be reviewed later.
Update the appropriate article to reflect this behavior and avoid future escalations.
Example:
Reviewing these conversations and making necessary updates to content often takes less than 10 minutes per conversation and can dramatically improve Fin’s ability to handle nuanced customer queries without escalation.
Track and prioritize knowledge work
What we recommend:
Use a task management tool (e.g. Coda, Trello, Asana) to prioritize and track:
Product updates and content required.
Incoming content suggestions.
Status of article audits, updates, or new content creation.
This helps you collaborate and share knowledge tasks, ensuring you have a clear overview of ownership and progress made.
Summary: Best practices for training Fin with great knowledge
Area | Key Activity | Recommended Frequency | Average Time Required |
Product Updates | Write/update content | Weekly | 9 hours |
AI Suggestions | Review and action AI content suggestions | Weekly | 1 hour |
Human Feedback | Review and act on teammate suggestions | Weekly | 8 hours |
Stale Content Review | Refresh articles older than 6 months | Monthly or Biweekly | 7 hours |
AI Optimization | Optimize content for AI (using AI!) | Monthly | 1 hour |
Document Product Behavior | Add explanations for identified expected behavior | Weekly | 3 hours |
Knowledge Tracking | Maintain a task board or tracking system for collaboration | Continuous |
|
When these workstreams are in motion, knowledge management becomes a dynamic, shared practice that continuously evolves to meet the needs of your team and your customers. With this strong foundation in place, Fin is equipped to deliver exceptional support at scale.
Need more help? Get support from our Community Forum
Find answers and get help from Intercom Support and Community Experts