Fin Product Area

Hey Everyone, I just wondering some intercom users, I am working on Compliance Monitoring for Intercom users.

Fin doesn't read your knowledge base the way a person does. It reads structure, tags, and outcomes. Get those wrong during migration, and resolution rate suffers from day one — even if every article technically "moved."Across Intercom's customer base, Fin averages a 67% resolution rate. Top-performing teams hit 80% or higher. The gap between those two numbers usually comes down to migration quality, not the model.How Fin actually reads your knowledge baseFin doesn't treat your help center as a flat pile of articles. It uses hierarchy — Collection, Section, Article — to understand scope and context before it answers.Most help desks only support a three-level structure. Intercom allows a simplified Collection > Article path with no Section in between. That's fine natively. It's a problem in migration: if your source platform's categories don't map cleanly onto that structure, a migration tool has to guess, usually by dropping orphaned articles into a default folder. That default bucke

Hi everyone,We’re trying to build an Intercom Data Connector that retrieves customer-specific data from our backend.Our backend API requires a user-specific access token. This token is generated only after the customer completes an OTP/authentication flow, and each customer receives a different token.The flow we want to support is: The customer completes OTP authentication. The OTP/auth connector returns a response containing: { "data": { "access_token": "..." }} A second connector should then call our recommendations API using that token in the Authorization header: Authorization: Bearer <data.access_token>The issue:When we try to pass the token dynamically in the connector header, for example:Authorization: Bearer {{accessToken}}or by using a value returned from a previous connector/action, our backend does not receive the Authorization header/token.The only setup that worked was using Intercom’s Authentication Token feature with a static Text token. However, this does n

Test Environment:OS: Windows 11 version 25H2 (OS Build 26220.7271)Browser: Edge (Version 143.0.3650.75)Screen Reader: NVDA (2025.3.2), JAWS (2025.2508.120). NarratorURL: https://www.intercom.com/help/en/articles/9639255-getting-started-with-intercom User Impact:Screen reader users will miss the ‘Did this answer your question?’ label for feedback controls, making it unclear what the controls represent. This can lead to confusion and incorrect responses during feedback submission.Pre-Requisites:Enable NVDA Repro Steps:Open the URL: Getting started with Intercom | Intercom Help in edge browse in windows. Intercomm page will open. Press tab key to navigate to the Feedback controls. Verify whether Screen reader is announcing the 'Did this answer your question?' label for the feedback controls in windows or not.Actual Result:Screen reader is not announcing the 'Did this answer your question?' label for the feedback controls in windows.NVDA announces: Disappointed Reaction toggle button not p

Hello,I wanted to consult with my fellow Knowledge Content and Fin AI operators about an issue I’ve noticed while working through “Edit Article” Recommendations (previously called Suggestions).I’ve identified a couple of flaws in the editor panel that loads to the right of the Recommendations list:When an “Edit Article” Recommendation impacts one or two steps within a numbered list, the editor strikes through all steps (sometimes entire paragraphs) in the list instead of highlighting only the specific step(s) affected. Accepting these edit recommendations often breaks the formatting of our articles.   Similarly, when an “Edit Article” Recommendation impacts a section containing images (such as UI screenshots), accepting the edit removes the images entirely and leaves only the ALT text behind once the edits are applied.I’m curious if anyone else has experienced these issues or found reliable workarounds for them. At the moment, we’ve had to manually review and reformat affected articles

HelloWhen we try to send a picture on Instagram it doesn’t work anymore as it was working previously.If the customer send to us it’s working very well but not in the other way.It’s just red.Conversation : 215475580844736 

After every Fin update, the search history in the workspace is lost. We would like to retain this history.

Hi everyone,I'm hoping someone has run into this before.We're currently migrating our internal Knowledge Base into Intercom for Fin/CoPilot, but we're not manually creating each article in Intercom. Instead, we're uploading our existing documentation from Google Docs (exported as .docx) or as PDFs. We don't use Notion, Guru, or Confluence.The problem is that every upload loses a lot of its formatting, making the articles much harder for agents—and Fin/CoPilot—to read.I've already tried pretty much everything I can think of: Using Normal text only (no Heading 1, Heading 2, etc.) Using bold text instead of Word heading styles Keeping section labels (Purpose, Process, Before You Begin, etc.) as bold text on their own line Using bold for step titles (e.g. Step 1: Verify the order) with normal text underneath Keeping formatting very simple with basic bullet points Uploading both .docx and PDF versions The formatting still gets stripped or flattened during import.Has anyone success

I'm working on improving the support experience for a PC gaming content website and am considering Intercom for customer communication and self-service support.The website covers various types of PC gaming content, so visitors may need help finding guides, understanding technical information, or navigating its sections.I'm wondering how you would structure the Help Center. For example:Should articles be grouped by topic or user journey? How many categories are ideal for a smaller website? What are the best ways to identify common questions? Can Fin help visitors find the right information when their questions are vague?I'd appreciate hearing how others have structured Intercom for a content-focused website.

Hi - I am sure some of you got into this issue, so any best practices are more than welcome. I want to connect Confluence to Fin as a content sources, however I can see that the articles in Confluence are automatically synced as internal articles. So 2 questions? 1. did you find a way to sync as public articles or to move them in bulk to public articles? i2. if not, what workarounds do you suggest for Fin to be able to provide these articles as sources?   What I want to obtain is an initial Fin answer that at the end gives the link to the sources he used, and that includes Confluence articles. Thank you. 

When Fin replies or send a follow up for inactive customers, the outbound reply doesn't include the quoted thread below the message. Recipients only see the reply itself with no prior context.Is there a setting in Intercom to enable quoted/threaded replies so the previous email history is included in outbound replies the way traditional email clients handle it? If not, what's the recommended workaround for managing external partner email threads through Intercom without losing context for recipients?

Hi all,We're seeing an issue after conversations are handed off from Fin to Zendesk:Customer messages are successfully reaching Zendesk Conversations are being assigned to agents as expected Agents can reply from ZendeskHowever, the customer never receives the agent response in the Messenger widget. Instead, the widget remains stuck on: "Waiting for a teammate" The handoff itself appears to be working correctly, so the issue seems isolated to agent replies not syncing back to Messenger after the conversation is assigned. Has anyone encountered this before or have suggestions on where we should investigate? Screenshot attached for reference, thank you in advance!  

We need to implement a double approval process for FIN AI production releases.Before any deployment goes into production, a second level of validation and authorization should be required to ensure proper security and quality control. This will allow Team Leads to have visibility and governance over changes being released.Production deployments should never depend on a single person developing and pushing changes directly to production without an additional review and approval process.

I’m working on a gaming website called BaixarGame and want to make it easier for visitors to find useful information and get help when they need it.For a website with many game pages, what Intercom features would you recommend for improving the user experience? I’m particularly interested in using chat, automated answers, FAQs, and targeted messages without making the website feel overwhelming.What setup has worked well for other content-focused websites?

I’m having an issue with an Intercom workflow where automation does not consistently trigger when a new conversation is created.What I’m seeing:The workflow is enabled and the trigger conditions appear correct. Most new conversations enter the workflow normally. Occasionally, a conversation is created but the automation does not run. There is no obvious error shown for the affected conversations. Manually updating the conversation sometimes causes the workflow to trigger.I’ve already checked the workflow conditions and tested it with different conversations, but I haven’t found a consistent pattern. Has anyone experienced intermittent workflow triggers in Intercom, and is there a recommended way to troubleshoot why certain conversations are being skipped?

We are having trouble with office hours not being taking into account for the ticketing reporting. For example, the report says the ticket was open for 1 day and 4 hoursWhen you look at the breakdown on the ticket it says:ticket open: 22/05 at 1:36PMticket closed: 27/05 at 4:52PMThere is more than 1 day and 4 hours between those dates. If you convert the 1d 4hrs into 24 hour time you get 28 hours, then divide by 8 you get 3.5 working days which is correct but it is not displayed correctly. Does anyone have a work around for this? Thank you!! 

I want to ask how people feel about the Support in that specific interaction, and how they feel about our product overall. I can’t add two CSATs with intercom because one overrides the next. Is there an App you recommend to get this feel? 

Hi everyone,We're exploring how to measure content readiness before syncing our website pages to Fin. We want to ensure our content is structured so Fin can parse it cleanly and pull accurate answers without losing context.We know about the optimization guidelines,Rather than testing AI search results after the fact, I want to focus on scoring the quality and structure of the content itself before it gets synced. A few areas I'm looking to refine: Structure & Noise Removal: Verifying that HTML clutter (navbars, footers, sidebars) is stripped so only clean body text is processed. Chunk Self-Containment: Testing whether standalone sections or paragraphs make sense on their own without missing key context or relying on surrounding text. If you've built any checks or used tools to score content readiness before pushing to Fin, I'd love to hear what's working for your team!

Hi all,Whenever Fin escalates a conversation to our Customer Support team, it automatically sends its own handoff message to the customer (something like "A colleague from our support team will take a look..."). We can't find any setting to turn this off or customize the wording — it just fires every time an escalation happens.Has anyone found a way to disable this, or at least edit the copy? We'd like more control over what gets sent at the handoff point.Any pointers would be much appreciated — this is fairly urgent for us right now.Thanks in advance!

We help customers organize scattered content (recipes, PDFs, docs) into a single polished output using an AI layout tool called Cookbook AI. It keeps the original text unchanged and just handles categorization and layout.Curious how other teams here handle similar "many small pieces of content -> one organized deliverable" workflows for their own users. Do you build this in-house or point customers to existing tools?

Hi everyone,I'm having an issue with Dataset Export in Intercom.In Daily Report I can successfully filter by "Brand is not [specific brand]" and get the correct data.However, when I go to Dataset Export, the same Brand filter is available in the UI, but when I select it, there is no content inside (no brands to choose from). It feels like the filter is broken in Export.Has anyone experienced this? Is there a known limitation or workaround?Thanks in advance!

In office hours, the word “minuutin” is inflected incorrectly. Should be “minuuttia”.    

 I’m using `Intercom(“showArticle”, articleId)` to show article content inside the Intercom widget. Under certain circumstances, after calling `Intercom(‘showArticle’,  articleId)`, instead of seeing the expected article, I instead get a “broken” version of the home screen. In particular, The bottom navigation tabs are missing The help article links are inactive (clicking them does nothing) My best theory so far is that there’s a race condition in the widget between loading the home screen content and the article content. My evidence to support this theory isThe “broken” home state opens in the article frame (wide container, no navigation tabs) This state only (or exceedingly often) happens when calling `showArticle` before the messenger has been opened during the session. In that case, I believe `showArticle` is first loading/rendering the homescreen, increasing the likelihood of a race condition.  I can eliminate the bug by changing my article link onclick to `Intercom('show'); setTi

Hi intercom,In order to integrate with other chat service.We're evaluating the possibility of replacing the Messenger widget with our own chat UI, backed by the conversation API / or intercom-node. I found this post before: You will need to handle apps inserted into the messenger and conversations. You will miss out on a lot of the features offered by Operator. May I know what exactly will miss / break if connecting via API ?this is what i found so far: 1. Canvas Kit apps in conversations2. Fin replies: does Fin's answer arrive as a normal `comment` part (plain text/HTML we can render) ?3. Read/seen stateAnything else that silently breaks in a custom UI when Operator/Workflows run ?Or is there a guidance in document regarding this approach?Thanks

When searching for conversations or tickets or viewing a list created by a view, we often want to apply bulk updates to the list of conversations or tickets. Currently, the list of changes you can make to a conversation/ticket is very limited. We would like to be able to change any conversation or ticket field whether standard or custom field. Example:I have a view showing me tracker tickets. I want to bulk update all tickets in this list with a value from a custom ticket field called ‘Product’. I cannot do this at present.