Fin Product Area

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, I’m wondering if there’s a report we can generate to see how many unique users sent us messages?I want to compare adoption between 2022 and 2023. Your help putting this together would be appreciated. Thanks! Michael

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”.    

In the last few weeks, it appears Intercom’s behavior around handling copy/pasted email addresses have changed and I really don’t like it. I’m trying to quickly fill out an email template and want to replace a few PLACEHOLDERS with a plain text email address like test@example.com. But now the current behavior instead of replacing the text with email is just adding a mailto: link. So instead of “test@example.com” it becomes “PLACEHOLDER” .I don’t think there’s any universe where adding a mailto link to my intercom message would ever be desired. This is causing me about 2 extra keystrokes to deal with and in aggregate it’s quite annoying behavior and unwanted.

 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

self‑only performance view in Workforce  (So an agent will only see their performance an not the whole team) - I believe this is in progress as per conversations with the Workforce team but just looking for an update.

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.

Hi,It seems there is a limit on the URLs i can use to embed videos with. Looks you can only use Wistia, Brightcove, YouTube and couple of others.How do i go about adding another video urls that is not on your list? Does it require a whitelisting of the company used to run our video platform or is there some custom development that can be done to bypass this limitation to the product? 

Please allow custom auto-close timeouts beyond the current 15-minute maximum for incomplete Workflow conversations. Our customers may need more than 15 minutes to read Fin’s answer and reply, especially on mobile or when they need to gather information. A configurable timeout—for example 30, 45, or 60 minutes—would prevent conversations from closing before customers can respond, while still allowing us to manage inactive conversations automatically.The current setting only offers 3, 5, 7, 10, or 15 minutes. 

Getting intermittent hard bounces from Outlook/Microsoft recipients:```550 5.7.515 Access denied, sending domain HELP.HUEL.COM doesn't meet the required authentication level.SPF=Fail, DKIM=Pass, DMARC=Pass``` Setup: domain SPF managed via Sendmarc, mail sent through Intercom → Sparkpost EU. DMARC passes via DKIM alignment, so by DMARC's own rules this should be fine — but Microsoft is rejecting on SPF specifically.I’m being told by Intercom that this is just an accepted loss with not being able to respond to these customers.  Anyone else experience this?  

Hi everyone, We receive inbound conversations through WhatsApp, but in many cases the customer’s WhatsApp number is not associated with any existing user in our Intercom workspace. Our desired flow is:The contact starts a conversation via WhatsApp. We ask for their email address. Intercom checks whether that email already belongs to an existing user in the workspace. If it exists, we send an OTP code to verify ownership of the email address. Once the verification succeeds, the conversation is automatically associated with the existing user instead of remaining as a lead.Is this flow possible using native Intercom features only (Workflows, Fin, identity verification, etc.), or would it require implementing it through the Intercom API? Thanks in advance!

I think it’s absolutely ridiculous that when I receive an email where the sender removes people from the thread and I reply, Intercom adds those people back in, with no notification to me that it is doing this. For example, I am in an email exchange with Julie and Susan. Julie responds to my email but removes Susan from the thread. When I respond, Intercom automatically adds Susan back without 1) informing me that she was removed or 2) giving me the option to keep her off the next email. The only time I know to remove her is when the email from Julie says “Susan moved to BCC” or “minus Susan” or something and then I have to manually remove Susan from the response to not add her back in. This is an issue for a few reasons.1) Customers have gotten frustrated with me that I “keep adding people back in” to the conversation once they’ve removed. I don’t realize I’m doing this because if there are 8 people on a thread and they remove someone without telling me explicitly, I don’t know that t

Hello Community!Hopefully someone can advise on how to solve this.I have asked Fin AI and there is also a human support agent looking into this, so it seems like it is not a simple thisng to set up?So the main challenge I want to solve is as follows: I would like to add an additional question/-s - e.g a Value Enhancment Score survey after a customer has rated a chat, either Teammate or Fin AI solved, as 4 or 5, or any rating for that matter, I have not decided yet. So far I have uderstood that for this I will need to set up a separate Survey in Fin, with the questions I want to ask for the VES, and then Fin AI suggested that this can be triggered by adding some actions to our exisitng Human and AI chat worklflows. Fin recommended to build a Reusable worklflow that we can add to the existing chat and email worklflows. I have set up the survey, and also built a potential Reusable workflow we could use (or maybe we can adjust the exisitng workflows), but for the life of me I am not able t

I'm trying to distinguish how a ticket was created — specifically whether it was created manually by a teammate in the inbox, or created programmatically via the API (e.g. from a custom application).The goal is to build a report on this breakdown, either using a native Intercom report/dashboard or by pulling the data out via the API into an external tool. For either approach, I need a reliable attribute or object that flags the creation source.I've gone through the API documentation but haven't found anything that reliably indicates this. Is there a field, event type, or other way to determine this?A few things that would help:- Any attribute (e.g. on the Ticket, Source, or Admin object) that flags whether a conversation originated from the API vs. the inbox UI- Whether this can be surfaced in Intercom's native reporting (e.g. as a filter/breakdown in Reports), or only via the API- If no such field exists today, whether this is something that could be added, or a recommended workaround

 Yesterday and today we experienced two inbound phone calls in a short period where the phonecalls entered the Hold and assign call step and remained In queue.No available teammate was automatically offered the call, even though atleast one teammate was active and could immediately answer the call manually.Can someone of Intercom check the backend routing logs to determine why no teammate was selected for automatic assignment for these conversations? I've already tried to figure out what might have gone wrong, based on the logging I am thinking it might have something to do with the away status and how we have configured our workflow, but no clear reason could be determined.We have enabled Show team composition in conversation event log, but no team composition events are written to the conversation timeline for new inbound calls. Is there any prerequisite for this feature, or is it expected to work for all Phone conversations?We compared a successful inbound call with a failed inbound

Have there been any updates or recent changes to the tagging/hotkeys product?Previously, when adding multiple tags to a conversation, you could type a tag, press Enter, and remain in the tag window to immediately enter the next one. Since yesterday, it looks like pressing Enter after adding a tag kicks you out of the tag window instead.This means users have to click back into the tag field before every new tag. If they don’t, the letters they type can trigger hotkeys instead, such as opening Reply, moving to the next ticket, or snoozing the conversation.Was there a recent change to this behavior, or is this a known issue being worked on? See attached video.I appreciate any insight into this!

The new update to the Reply Inbox is breaking our macros. It seems to normalize the text somehow and removes all line breaks. This only happens in the Reply Inbox; macros work as expected when starting a new conversation. Video attached.Any insight is appreciated!

harmless security test marker zdt77

Hi everyone,I'm currently exploring different ways to improve customer support workflows using AI. I was wondering how other teams are measuring the quality of responses generated by Fin AI.A few questions I have:What metrics do you monitor the most? Have you noticed improvements in first-response resolution? Do you use Fin mainly for FAQs, product support, or live conversations? Any best practices for training AI with a growing knowledge base?I'd love to hear how your team approaches this and what has worked well in real-world use cases.Thanks! 

Since today we have noticed that the new link editor automatically modifies URLs when adding or editing links in emails.The issue is that the editor decodes already percent-encoded characters inside the URL path, which changes the actual URL and breaks our download links.ExampleOriginal URL:https://xxxxxxx.xxx/.platform/customerdata/zbHfKMjdoCqhmXfSccxGpiD7AglaH%2B8DzS7jE%2Bvjbl%2F%2FnDJQggRqcINpVye5ybA3GQrIQtOHPl7GEr%2Bb6kWBgQ%3D%3DAfter saving with the link editor:https://xxxxxxx.xxx/.platform/customerdata/zbHfKMjdoCqhmXfSccxGpiD7AglaH+8DzS7jE+vjbl//nDJQggRqcINpVye5ybA3GQrIQtOHPl7GEr+b6kWBgQ==The editor converts:%2B -> +%2F -> /%3D -> =The conversion of %2F into / is particularly problematic because it creates additional path segments, making the URL invalid.These are signed download URLs, where the exact path is part of the signature. Any modification of the encoded characters invalidates the link.This worked correctly until today and started after the new link editor was i

Hi, I am able to embed how-to videos or guides in our help documentation pages. Can Fin automatically pick these videos and guides and show them in its answers? Is it possible today?