Fin Product Area

Hi all,Looking for guidance on customizing Fin's default human handoff behavior (We use Fin over API).Right now, when a user asks for a human (Right from the first message), Fin responds with:"I understand you would like human support. Would you like me to connect you to a human agent? You can also continue working with me and provide more details if you prefer."We're building a multi-stage escalation flow (a short ladder of clarifying prompts before handoff) to collect 3 key infos for our support team (What customers were trying to do in the product, where are they in the product, what happened), but we need the final stage to first check whether the user already gave issue details earlier in the conversation, rather than asking for information a third time if they already provided it. I understand that Escalation Guidances are stateless so we can’t store anything in there. How can we build a robust support detail collection flow in case customer asked directly for human agents? i.e (

We’re going to stop using Fin AI. It’s a shame because the product itself is really good, but the pricing isn’t suited to marketplace business models like ours.With margins of around €1 per user per month (incl. VAT) and high volumes, the cost quickly becomes unsustainable.If possible, it would be great to share this feedback with your product teams internally — there’s likely a broader pricing vs. business model fit issue for marketplaces.

Hi there, The new ‘From and Reply‑to’ fields are always visible when you’re writing an email, I’ve noticed this change today, 23 July 2026.Can you please make this a preference so that one can toggle this on/off based on experience. I get that this is nice for people to see who they are sending the email to which is great but not ideal if it is going to take up that much space.It takes up the view in a conversation so make the conversation section smaller due to the block.Thank you in advance.Best regards,

I review the questions customers ask FIN. At some point in the last 5 days a change was made and now when I view the conversation (from Reports, FIN involved) the convesation automatically goes the bottom and I have to scroll up to the top for every conversation. How can I change this behavior?

We have some team members that are not on Intercom all the time. However, some message do need their input. It would be great to be able to slack teammate when they are mentioned @____ in the notes.And also, when the chat is assigned to the person.

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

Hi, we have our workflow set up to allow 5 minutes to have a team member answer incoming chats and emails during office hours,  Fin kicks in before the 5 minutes and answers the chat or email. When one our team members replies to a chat or email Fin will then reply to the team member. Has anyone experienced this? I feel like its an easy fix , not sure if we are missing a step in our workflow. Any advice would be greatly appreciated

I want to be able to distinguish between mentions on conversations that have been resolved vs. conversations on tickets that are unresolved. Using the “unread” view doesn’t help me a lot because I want to be able to view and come back to mentions on open tickets (esp. given that tickets can’t be assigned to multiple people). I guess mentions on closed tickets will be visible on the “read” view forever?

Hello Team,I would like to request for a feature with regards to the option for Closed conversations on first contact.Your current parameter and help documentetion says that if the conversation was handled entirely by one agent but if it is a reopened conversation it will not be incuded in the single agent closure.We currently are measuring the performace for the agents depending on the single agent closures which creats a huge imact, also we do not want the reopen option to be blocked for the customers.We weould like to request for a feature where the single agent clsoure incudes the reopened conversations as well. Thank you.  

Issue: Fin sometimes have a follow up question, “Is that what you were looking for?” / “Did that helped?”Customer replied: “ok” “okay thanks” “cool” “got it” BUT, they’re not totally done with their concern. This is affecting Fin CSAT. 

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.

Hi team!I'm trying to understand how a customer ticket that was closed 3 months ago got reopened, despite our settings that should prevent it. I'd appreciate help understanding the mechanism.Setup:Tickets Portal is enabled for our customers Under Settings > Channels > Messenger > Control inbound volume, "Prevent users replying to closed tickets" is ON, set to 30 days (same for visitors and closed conversations) We have a workflow with the trigger "When a ticket is created" (Customer tickets, Web, Users) that applies an SLA and assigns tickets to our support teamWhat happened (from the ticket activity log):3 months ago: customer submitted a ticket via a Messenger ticket form, it was handled and manually closed by a teammate 4 days ago, on the same ticket ID, this sequence appears in the activity log: Company attribute set (by AI/automated attribution) Moved to "Submitted" and shared SLA applied by our "when a ticket is created" workflow Assigned by that same workflow Import

I am no longer able to highlight text to copy it. It unhighlights too quickly. I never had this problem before I started seeing little floating icons for Co Pilot next to everything I highlight. Now that it’s there, nothing stays highlighted long enough for me to even press control + c

Hi everyone,I’m running into a frustrating glitch with the email builder and could really use some help or workarounds.The Issue: Whenever I send a newsletter (even just a test email to myself), the template's background colour completely disappears. To make matters worse, the system seems to inject random blocks of alternative colours out of nowhere, which completely breaks and "crashes" the newsletter's layout.What I’ve already tried to fix it: Custom Templates: I built brand new custom templates from scratch to see if the original was corrupted. Inspecting Settings: I went through every single style setting to ensure nothing is left on "default" and everything has a specifically assigned colour. Despite all of this, the layout still breaks every time it hits the inbox.Has anyone else experienced this colour-stretching/disappearing bug recently? Is there a hidden setting or a specific CSS clash in the new editor causing this?Thanks in advance for any insights!

After the recent update I cannot properly reply to customers on the iOS app. It goes to a new line randomly, then the text disappears. It’s unusuable.

Is there a way to create a new KB section and set visibility to be hidden to end users/customers)? Use case: I need to create a new section and add articles to it (to work ahead on my timeline) and change the visibility of the section to show for customers when the features related to the kb section is live. 

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? 

I'm working on a Nintendo-focused gaming website called TomodachiLifeROM, where I publish game guides, 3D-related content, and tutorials.I'm considering using Intercom to improve the support experience for visitors and would appreciate some advice.My questions are:What's the best way to organize a Help Center for gaming-related content? Can AI automatically recommend relevant articles based on what a visitor is asking? How do you reduce repetitive support questions with chatbots or workflows? Is it possible to guide users to the correct game guide or FAQ before they contact support? Any best practices for websites with a large library of gaming articles and tutorials?I'd love to hear how others use Intercom for content-heavy websites and any recommendations you have.

Hi everyone,I’ve been working on integrating the Intercom Messenger into a custom web application, and I’ve run into a specific technical hurdle that I’m hoping the community can help with.I am currently using a delta vietnam setup to execute some background scripts and handle task automation within the site's environment. While everything works perfectly on the desktop version, I’ve noticed that when this executor is active in a mobile web view, the Intercom Messenger launcher fails to initialize. It seems like there might be a conflict between how the script executor manages the DOM and the window.Intercom boot sequence.I’m seeing a couple of related issues as well:I'm not sure if the asynchronous loading of the script executor is competing for resources with the Intercom snippet, or if it's potentially masking the user identity variables needed for a successful boot. Has anyone else used a delta vietnam community workflow or a similar third-party script manager alongside the Interco

Please consider replacing randomly generated names such as "Cyan Kangaroo" with more natural placeholder names in the format "Firstname Lastname". Random animal-based names may appear unusual or unprofessional to visitors across different geographies and industries, whereas a standard name format provides a more familiar and professional experience.

Test Environment:OS: Windows 11 24H2(OS Build 26100.4946)Browsers: Edge (version 150.0.4078.42)URL: https://www.intercom.com/help/en/articles/415-get-feedback-at-scale-using-message-reactionsUser Impact:Keyboard-only users, including individuals with motor disabilities or those relying on assistive technologies, will be unable to access the feedback emoji tooltip on Windows. This limits their ability to provide feedback and violates accessibility standards for inclusive design.Repro Steps:Open the URL: https://www.intercom.com/help/en/articles/415-get-feedback-at-scale-using-message-reactions in edge browser. Intercom page will open. Press tab key to reach to the feedback emoji control. Verify whether Tooltip for Feedback emoji controls are accessible using keyboard in windows or not.Actual Result:While navigating using keyboard tab key, Tooltip is not appearing on feedback emoji controls in windows.Refer Attachment:Tooltip for Feedback emoji controls are not accessible using keyboard

Our subdomain managed by intercom was flagged as ‘Unsafe Implementation Of Subresource Integrity’ issue."Unsafe Implementation of Subresource Integrity" usually comes from a scanner flagging that you're loading external scripts or stylesheets (typically from a CDN or third-party service) either without an integrity attribute, with a weak hash, or with integrity present but missing crossorigin. Subresource Integrity (SRI) lets the browser verify that a fetched file hasn't been tampered with by comparing it against a cryptographic hash you specify.Can you do something to mitigate this? Like<script  src="https://cdn.example.com/library@1.2.3/file.min.js"  integrity="sha384-<hash>"  crossorigin="anonymous"></script> 

We are seeing an issue with Intercom outbound welcome messages in our Flutter Android app where the same outbound message is rendered multiple times repeatedly in the conversation/preview screen.Instead of showing the welcome message once, Intercom displays the exact same content duplicated 2–3+ times in the same thread/UI.Note:Issue comes in Android version 14 and 15. No issue in Android 16.  

Hello,We're seeing localized email headers displayed to customers in email conversations.For example, the quoted conversation history contains russian language:От: Отправлено: Кому: Тема:and timestamps such as:(UTC+07:00) TomskOur workspace language is set to English, and we'd like all customer-facing communication to appear in English.Could you please clarify:Where these localized headers are coming from? Whether there is a way to force them to appear in English? Whether there is a setting to prevent timezone names such as "Tomsk" from being shown?I've attached screenshots for reference.Thank you. 

Our need is to have agents always taking chats/calls at all times, without ability for them to switch away from one or the other.  A setting that prevents agents from modifying this is desirable.