Suggestions is an AI-powered feature that recommends specific actions to help teammates improve Fin performance. It identifies gaps in knowledge, unclear responses, and proposes updates to ensure Fin delivers better answers—faster.

Know what to fix and how – Suggestions highlight where Fin struggled and recommend clear, specific content updates.
Skip the manual QA – Suggestions scan unresolved Fin conversations, compare them to human replies, and surface what to fix—no transcript digging needed.
Fix what matters most – Each suggestion is ranked by impact so you can prioritize the fixes that improve the most conversations.
Stay in control – Edit, accept, or reject any suggestion before it goes live—so changes happen on your terms.

Note: We’re working on additional suggestion types like Fin Tasks and Guidance, but these aren’t available yet.

How to access Suggestions

Through the Optimize dashboard

For those needing extra context when reviewing suggestions, go to Analyze > Optimize to identify high-impact actions you can take for topics driving volume, handling time, or poor CX.

Access these Suggestions in the AI Topics table under the "Suggestions" column.

The overlay displays:

Number of edits required
Creation date
Source conversations used to generate the suggestion

Through the Suggestions page

For teammates who manage content, go to Train > Suggestions for a focused to-do list for optimizing content.

Suggestions appear in a scrollable list on the left, with your content always visible on the right.
Quickly move through suggestions without losing your place - each one loads automatically as you go.
No jumping between views - everything you need is in one intuitive space.
See the AI Topic and Subtopics each suggestion is related to.
Sort Suggestions by:
- Newest
- Oldest

How to use Suggestions

Suggestions are generated by analyzing:

Failed Fin responses (e.g. escalations or poor-quality replies) and comparing them to successful human replies to similar questions.
Teammate-handled responses to check whether there are gaps in your knowledge base.
Duplicates of the same content in multiple sources.
Contradictions of content in different sources.

Suggestions identify the likely root cause and recommend one or more actions.

Types of suggestions

Action	Goals	Availability
Add new content	Fill content gaps	Snippets
Edit existing content	Fill content gaps Ensure content is up to date and relevant Improve content quality	Snippets Zendesk articles Salesforce articles
Review contradictory content	Fixing potentially confusing sources for Fin	Snippets Webpages
Review duplicate content	Clean up content for Fin and knowledge managers	Snippets Webpages

Reviewing suggestions

You can review all suggestions before enabling them for Fin. Each suggestion includes:

A summary explanation
Creation date
Source conversations
Related content
Review actions required

Click the conversation icon in the suggestion card to view the source conversations. This helps you understand why and how the suggestion was generated.

Review options:

New content: Accept or reject the snippet
Edits: Scroll through multiple changes including:
- Red text (suggested removals)
- Green text (suggested additions)

After accepting a suggestion, it is immediately added to Fin's available content.

Tip: You can edit content directly before accepting or rejecting a suggestion.

Review edits to synced Zendesk articles

If you use Fin for Zendesk, you can receive AI-powered suggestions to edit Zendesk-synced articles and publish the article to your help center from within your Fin workspace.

Suggestions to edit articles in Zendesk appear under Train > Suggestions alongside other types.

After reviewing and accepting a suggestion, click Publish—a confirmation modal will appear with a link to the article in Zendesk so you can preview the changes there.

Once you click Publish to Zendesk, the article goes live in your Zendesk help center and can be edited as normal in Zendesk.

Note:

Only available with both Zendesk article sync and ticket data sync enabled.
Only available for articles synced through the primary integration subdomain used to sync tickets. Articles synced on other subdomains will not receive suggestions to edit.
Only available for articles with formatting supported in Fin (e.g., tables within tables are not supported).
When syncing content from Zendesk, images are re-uploaded to an Intercom domain; publishing an edit updates all image URLs in the Zendesk article to the Intercom domain.
This feature is in addition to suggestions to create content through snippets which is available to all customers. The type of suggestion provided will depend on the existing editable articles available.

Review edits to synced Salesforce articles

If you use Fin for Salesforce, you can receive AI-powered suggestions to edit Salesforce knowledge articles and publish the changes to your help center from within the Fin workspace.

In order to use this feature, you'll need to map the content field to a Salesforce field so that we know what field to publish the article to in Salesforce. Go to Train > Content and click on the 3 dot menu to manage your Salesforce knowledge articles. Select Manage sync then click Continue to map fields from Salesforce articles.

Here, add a new Salesforce field and select the corresponding field for your Salesforce articles, then map it to the content field for Fin. When you're finished, click Update sync from Salesforce.

Suggestions to edit articles in Salesforce appear under Train > Suggestions alongside other types.

After reviewing and accepting a suggestion, click Publish—a confirmation modal will appear with a link to the article in Salesforce so you can preview the changes there. After publishing, the article goes live in your Salesforce help center and can be edited as normal in Salesforce.

Note:

Only available with both Salesforce knowledge articles sync and case history sync enabled with the content field mapped to a Salesforce field.
Only available for articles synced through the primary integration subdomain used to sync cases. Articles synced on other subdomains will not receive suggestions to edit.
Only available for articles with formatting supported in Fin (e.g., tables within tables are not supported).
When syncing content from Salesforce, images are re-uploaded to an Intercom domain; publishing an edit updates all image URLs in the Salesforce article to the Intercom domain.
This feature is in addition to suggestions to create content through snippets which is available to all customers. The type of suggestion provided will depend on the existing editable articles available.

Remove/merge duplicate content

Duplicate content suggestions find pieces of content that contain the same information. Resolving these helps to clean up your Knowledge Hub and prevents Fin's context window from being cluttered with redundant information, allowing it to provide better answers.

For example, a suggestion might show you two articles that both contain very similar instructions on how to reset a password.

Fix contradicting content

Our contradicting content tool helps you pinpoint content with information that is at odds with one another. This lets you quickly review and resolve the discrepancies, ensuring your knowledge base is a single source of truth. By fixing these contradictions, you'll help Fin provide clear, accurate, and reliable answers to your customers.

Involvements and resolutions are also shown per content to help you decide how to proceed.

Fixing contradictions and duplicates helps ensure the information Fin uses is accurate and consistent, leading to more reliable and helpful responses. The more organized and clean the information is, the smarter and more helpful Fin will be. Regularly using these optimization tools is key to maintaining a high-quality knowledge base.

How to act on contradicting suggestions

To resolve a contradiction, you can:

Click Edit to open and update the content.
Click Delete article or Delete snippet to remove the content.
Reject the suggestion to remove the suggestion from your view.
Mark the suggestion as done when you have made the necessary updates.

Note: Suggestions are static as of the time they were generated. Since you may edit your content before reviewing a suggestion, the last updated time is displayed above the content with a tooltip indicating that the shown preview might be outdated.

Coming soon

Suggestions for Fin Tasks and Guidance.

FAQs

How often are suggestions created?

Create/edit content suggestions are triggered daily or weekly, based on:

Volume: High number of conversations where a question and answer can be found.
Topic activity: Regular queries (1+ a day) on the same topic for at least 7 days.
Spikes: Rapid increases in related queries over 4 days.

Duplicate/contradictory content suggestions are checked every Sunday. This scans your content and prepares up to 20 new suggestions for you to review on Monday. These may include a mix of potential contradictions (around 15) and duplicates (around 5), depending on what's found in your content.

What’s filtered out when generating suggestions?

Conversations without teammate responses
Abandoned conversations
Conversations where a teammate repeated the same answer as Fin
Conversations that mainly focus on a feature request or bug reporting
Existing content available to Fin (including from your external sources)

What’s the difference between suggestions in Train vs Analyze?

They are the same suggestions, but:

Train: Gives a prioritized task list for knowledge managers.
Analyze: More data-driven, ideal for support leaders and teams.

Are there any limitations for AI-powered suggestions?

Suggestions are only generated for conversations that have an AI topic assigned.
No option to fast-track or manually flag individual conversations for suggestions.
Low-volume customers (with fewer conversations) may receive fewer or no suggestions.

Why are AI suggestions enabled for Fin and Copilot before I've approved them?

When suggestions are generated, they appear in your review queue where they will be set to "Enabled" for Fin and Copilot by default, however they only become accessible to Fin and Copilot once you've approved them. Nothing goes live without your explicit approval first.

Why am I seeing older conversations in my suggestions?

You may notice that some suggestions reference conversations that are several weeks or months old. This is expected behavior and is part of how Suggestions are designed to identify meaningful patterns. Suggestions are created for a topic once enough conversations have accumulated to signal a clear knowledge gap or an opportunity for improvement. For some topics, it can take longer to gather a sufficient volume of conversations to meet this threshold. As a result, a single suggestion can be based on a mix of both recent and older conversations. This ensures that every suggestion is well-informed and addresses a recurring theme, rather than being based on a single, isolated interaction.

Use AI-powered suggestions to improve Fin