Train Fin

I would like to setup for all of 2026 for FIN give advance notice when a holiday office closure is approaching and then set proper expectations for human responses during the holiday.I don’t want to create a separate workflow for each holiday. Appreciate any suggestions, thanks. 

Hi everyone,We’re using Fin with an escalation rule that hands the conversation off to a human when certain conditions are met.Right now, when escalation triggers, Fin sends the customer a fixed handoff message that repeats word-for-word across conversations. The phrasing doesn’t match our support tone of voice, and it feels robotic.Is there a way to control or customize the customer-facing text that Fin sends at the moment of escalation/handoff?  

I want to establish a consistent daily ritual where I review Fin AI performance and make meaningful updates (I currently make content updates based on Fin AI DSAT ratings).  I’ve already seen this post.What Intercom features do folks use in their daily maintenance of Fin? How much time do you spend on this daily? Looking for ideas!  I still do sprints outside of the daily routine to explore certain Intercom features, so this would be in addition to that.

We are a SaaS environment where FIN supports two separate products that are able to be connected to one another.  We are working with audience content targeting and other documentation flows and guidance to ensure the proper resources and content are sourced for the correct inquiries.  We’ve also had issues where changes were implemented before we were able to ALL sourced content updated, and instruction was given that couldn’t be followed. Has anyone come up with a way to track conversations that specifically are giving information the customer is unable to follow?Current Idea going over this afternoon is to make an attribute, and have the key words and things often asked include “its not there” “i’m unable to do that” “that is missing for me” and other example statements we’ve seen in chat, and have that be a specific attribute used in an escalation guidance, and get those customers to reps to verify their environment. But would also then be able to get reporting on that guidance bei

Hi community, I'm trying to set up Fin to provide different responses to different audiences using audience-targeted Snippets, but Fin is completely ignoring them and not using them at all. What I've configured:• Created specific Audiences based on user attributes • Created Snippets with different content for each audience• Assigned the appropriate Audience to each Snippet using Audience Targeting• Verified that users match the correct Audience criteriaThe problem:Fin is NOT accessing the audience-specific Snippets at all - it completely ignores them and uses general content or other articles instead. Even when the Snippet is perfectly relevant to the question and targeted to the correct audience, Fin doesn't use it.Context:We're a fintech company with complex financial products. It's critical for us to have a SCALABLE solution that ensures Fin provides accurate, segment-specific information to the audiences we've pre-defined. Providing incorrect or generic information could lead to co

Earlier, under Fin AI Agent → Train → Content, there was a Custom Answers tab within Content Sources, where I had added several custom answers.I no longer see the Custom Answers option in this section.Could you please clarify: How can I access the custom answers that were previously added? Are these existing custom answers still being used to train the AI agent? What is the current process for adding new custom answers?

I would love to have an option to involve in only for collecting conversation Attributes. Right now it is not possible and any workaround works.  Even if I create a special tag/inbox for collecting attributes Fin must be involved which means even if it meet the escalation rule, it will reply that the conversation has been passed on. I would like Fin working in the background, collecting attributes from ALL conversations.  Maybe managing the Fin’s steps (in Let Fin handle nod in workflows) would be a solution. I mean turning off using content, guidances and leaving just collecting attributes would do the trick.  

Is there a way to have the Fin AI agent reference information (including hyperlinks to PDFs) on a website but restrict it from linking customers to the site? We have a page with links to user manuals for devices listed on our website that was meant to just be for AI reference rather than for public consumption. We want Fin to be able to answer a question troubleshooting use of a specific device type with the user manual, but don’t want to take customers to a page with a huge table of devices on it.

Hello! I wanted to report a couple of issues we’ve been experiencing with the FIN Suggestions feature: Suggestions tab showing empty results – We sometimes see that a suggestion appears to be available, but when we open it, it’s actually empty (no comments or text). Article changes not saving – When trying to edit an article through FIN Suggestions, we often get an error saying the changes could not be saved. In some cases, the changes aren’t even saved as a draft, which has caused us to lose work and time. Could you let us know if these are known bugs or if there are any current workarounds?Additionally, we were wondering if there are any options to guide or rate suggestions so the system can learn from our feedback. At the moment, many suggestions seem repetitive and often just reword content without explaining why the original version might not be good. It would be great to have a way to indicate which suggestions are more helpful and steer the system toward providing more useful

Hi Intercom Community,I’m trying to fine-tune how FIN handles unresolved issues. Specifically:Is there a way to set a limit on how many times FIN tries to resolve a customer’s question before escalating? Can FIN automatically hand off to a human agent after those attempts?I want to make sure customers aren’t stuck in a loop if FIN can’t help. Ideally, it would try a few times, then gracefully pass the conversation to a person.Has anyone set this up successfully? Would love to hear how you approached it—or if there’s a built-in way to do this.Thanks in advance!—Vanessa

Hey everyone 👋We’re currently using Fin as the first line of support, handling all incoming customer conversations.It works great — once a human agent joins the conversation, Fin automatically stops responding, which makes perfect sense in most cases.However, there are many situations where the agent realizes that Fin could actually continue handling the customer effectively after their short intervention.It would be super helpful if agents could reactivate Fin in a conversation — ideally with a simple button or command — so Fin can pick up right where it left off.Is there a way to do this today? If not, we’d love to see this added as a future feature 🙏Thanks!Tamir

We utilize Fin as the first line of defense in supporting our software. I’d like to explore having Fin handle chats related to known bugs/issues. Right now, a user will message saying “I’m experiencing XYZ issue” and Fin will go through the normal troubleshooting steps. Ultimately these chats often get routed to a human agent who then lets the user know we are aware of the issue and working on a resolution. Users are often annoyed that they had to go through the process of explaining the issue to Fin just to find out we knew there was an issue. Sometimes these issues only impact a small subject of our user base so we don’t want to widely exclaim that there is an issue. Thoughts/Questions:Best way to implement something like this - I’m curious if we can utilize the Content and Sources (beta) section under Guidance? Best way to track these conversations - we track these reports so we can reach back out to the user once the issue is resolved. Ideally, these conversations would be assigned

I’ve been back and fort with the support team on this for weeks, and made sure to set up Finn correctly. I have this very simple instruction asking Finn to not reply to my customers if it doesn’t know the answer to their question. No matter how I phrase it or how many ways I repeat it, Finn will “behave” for a while and then go back to replying, mostly embarrassing nonsense responses.It’s ridiculous! I keep having to apologize to my customers for the dumb responses it will give to super basic questions. See below my current instructions - I can’t think of another way to repeat this… I keep adding them.Is Finn just not ready for real world usage?Or is it just my account that’s cursed? I can’t keep coming up with different ways to phrase this simple instructions (and the support team can’t either, aparently).   

Friends! I LOVE the suggestions feature with Fin! I want to try and accomplish something that I feel would be table stakes but not sure how to go about it: I’d like to filter tickets we got last year within a specific date range (our customers are accountants, so for tax season), then I’d like Fin to aggregate and analyze the trends of the tickets and suggest where our content gaps are so that we can fill them preemptively and flatten the curve for the upcoming season. Anyone know how I might go about that?! Best, Malachi

Is there a way to train or edit customer sentiment within CX Scores assigned to a conversation? For example, I reviewed a low CX Score conversation and it was determined the customer was frustrated, but that was not the case when reading the customer's response. Any tips to reduce the number of low customer sentiment scores? 

Hi Folks - I work for a small software company and we’ve been using FIN for a year or so.  Its been doing really well and I am looking for different ways to improve its reach.One item I am curious to hear from this community about is defect management.  If a user is chatting FIN about a bug, what are your underlying training processes for the bot to handle this?  At the moment, our bot points towards a human agent but I would like to find ways to automate this.

Friends, are there any Paid Consultations around Fin optimization? I’m wanting someone to hop on a call with me so that I can check my logic. I pulled ticket information via the MCP into claude and did some ticket analysis. We’ve learned what our top support gaps are and we created documentation with SME’s to fill those gaps especially on the troubleshooting side. The rub is that I don’t know how to effectively attribute the benefit of the document(s) that we created - to the potential improvement of Fin Resolution rate (nor by how much).  Also, separate thought - is there a way to review edits that were updated through the suggestions in Train? Sorry for the vomit, I just want the effort we put it to count! :)

We’re loving Fin, but running into customer questions where Fin is answering using incorrect product articles. Is there a way for Fin to recognize a product tag on a conversation (or possibly a field from Salesforce?) and default to using knowledge from a particular product help center? I looked into using audiences as well, but there are a number of product combinations that customers can use and I don’t want to limit Fin to only using Product A knowledge when a customer may have Product A and Product B. The Content and Sources guidance section in beta only allows tagging individual articles, not a whole help center section. If I go that route, I have to tag 100+ articles per product...not ideal. Any suggestions would be helpful! 

I am the admin of a help center - facebook group. How can I feed this into FIN as this would be an incredible source of information for my software?

hi all,  The content we want to import from is https://wellthy.com/faq The settings I use to import the content are: The result that intercom imports are like this:   So it looks like it’s not getting the information from the clickable links. So when I test and ask Fin a question, sometimes it would say something like this:   Wondering how I can actually have those clickable links expand so sync can grab the information and not go “based on the FAQ structure...” but just answer the question.  Or does anyone have a better thought?

Friends! What capability does Fin have in terms of creating a response hierarchy based on seasonality? For example: we service Accountants - during tax season we want Fin to default to a specific answer based on snippets we’ve created for that inquiries during tax season, and in the “off-season” we want the response to be more general.  Has anybody solved for this or done some work around to provide Fin this training? 

We have separate articles for our website and our mobile app. Each mobile app article includes "mobile app" in the title. We want Fin to select the appropriate article based on the channel from which the customer is reaching out—whether it's iOS/ Android, or Web Messenger.We have attempted to use guidance, but it hasn't been effective. Additionally, we tried implementing audiences based on the "current channel" filter, but when testing on our website, Fin only utilizes the web articles if they are open to everyone and not restricted by an audience.Is anyone else using Fin with different articles based on the channel? If so, how did you overcome this challenge? I would appreciate any suggestions.

Please, I need my workspace to be lifted soon. After signing up for the first time and my workspace got suspended without going against and rules. How do I reach out to the support team to help me out?? Below is the attached error message.   

Hi everyone,I noticed that Fin now displays article references as small numbers at the end of a sentence, which customers have to hover over and click to access the linked help center article. Our team really doesn’t like this change. We want to make sure customers can easily see and select the full help center article that answers their question.Is there a way to turn this feature off so that the full article title appears as a clickable hyperlink in the conversation, or so the source is clearly listed at the bottom of the chat like it was previously?Most of our customers access Fin through mobile and are Gen X and Boomers, so we’re concerned they won’t realize they need to click the small reference number to get the information they need.Any help would be greatly appreciated!