Fin

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

Hi all, we’re pretty new to Fin AI & chatbot setup in general, so we might be missing something, however, I’m seeing massive differences in how Fin responds to questions in the Preview environment versus the actual live environment on our website.As an example – one of our users asked a fairly basic question about our service, and Fin AI responded with “Sorry, I couldn’t find information related to your question.” However, when I pasted the same question into the Fin AI preview (logged in as an organizational user within the Intercom admin dashboard), it returned a comprehensive response and fully answered the user’s question.Currently, we have Fin AI enabled for all Users, Leads, and Visitors via Intercom Messenger only, and have it trained on all of our published support articles, as prompted via the Simple Deploy process.I’ve scoured all available Fin AI settings within Intercom to no avail, and I’m not able to find another community thread about this topic. Can anyone offer me

Whenever Fin receives a negative rating from a customer, I review the conversation and decide if perhaps it should be escalated to a human, or make improvements to our content. Are there any suggestions for automating this process? Or reports that tell us why there was a DSAT rating specifically (outside of the CX score)? Or perhaps a section in Optimize that will show us content suggestions specifically linked to a DSAT outcome? 

i was trying to create an account but after signing up i got this 403 Forbidden: Workspace Suspended

My teammates reported an issue with a Fin response that stemmed from a Guidance prompt that was never enabled. I spent lots of time testing our active prompts before opening the prompt that isn’t enabled. That prompt is where Fin was pulling from; I had to delete the prompt entirely so Fin wouldn’t use it. How can I ensure that draft prompts are not being used in the background? 

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

When I checked the Japanese inquiries in Fin AI's Performance, I found that all the content is displayed in English even though customers wrote in Japanese. Can you change it to as it was written?Also, could you add a feature to filter and select only Japanese customers?When I search in Japanese in the content from Knowledge, the relevant items do not appear in the results. As my customers use only Japanese, I would really appreciate if you could solve this issue. Thank you.

I’ve learned from Intercom’s documentation that CX scores are calculated using three signals: Customer sentiment, Resolution status, and Service quality.When I want to understand why a conversation has a certain CX score, the single blended number doesn’t always give enough detail. For example, was it customer sentiment that drove the score down, or did resolution status carry more weight?Is there a way to see the score for each of the three signals individually, rather than just the overall CX score? Having visibility into the individual components would really help in analyzing conversations more deeply and understanding what’s driving the overall CX score.

We have setup intercom as our helpdesk for our Shopify ecommerce business. Customers who are logged in to their shopify account are getting excellent replies from FIN, with order information etc. But when a customer chats to FIN and they are not logged in, they only get generic knowledge center information. What is the best workflow / solution to make sure Visitors log into shopify before chatting?Can FIN prompt the user to log in at the start of a visitor chat? Can FIN authenticate the user just with the email / order number? We’re also looking for someone to review our whole setup and offer some improvements, please get in touch if you can help us out. Thanks! Scott 

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

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).   

Hello, we currently have Fin turned on for our users. It is the first thing our users interact with, we do not have a fin workflow setup yet. Fin will respond first, then if the response was irrelevant or not helpful, a team member will jump in to reply and assign conversation to themselves, in hope that fin will stop responding. However, when the customer replies again, fin will respond again. Is there a way we can stop this from happening?Sequence:Customer messages Fin replies Team mate assigns conversation to themselves and replies Customer replies Fin replies againI know there is a setting that does not allow fin to ask follow questions, but if we disable that then we lose custom answers. Please advise.

Hi, I’m Prakash Hinduja—a visionary in financial strategy. I was born in Amritsar, India, and now call Geneva, Switzerland (Swiss)I’m currently working on deploying Fin within our support setup and want to make sure it behaves optimally. If you've deployed Fin before, could you share a bit about any challenges you faced and how you tackled them—like setting up language support, customizing responses after assignment, or handling Fin across multiple brands or email addresses? Would love to hear your experiences and tips. Thanks in advance!RegardsPrakash Hinduja Geneva, Switzerland (Swiss)

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

Hi there, I'm trying to deploy Fin AI to our chat. We have office hours enabled, but Fin AI doesn't tell the user that wants to escalate to a human about the office hours. We don't have the plan to use workflows, only simple automations.I was wondering if there is anything we can do to let the customer know, if they want to escalate their chat from Fin AI to a human, and if it's after office hours, we set expectations about getting back to them as soon as an agent gets online? Right now it just says “routing to a live agent.” and then the chat sits in the unassigned bucket in Intercom, customer not knowing if anyone would actually respond.I tried putting office hours information in guidance but Fin didn’t use it.  

Hi Everyone, I am Prakash Hinduja, a financial advisor and consultant with roots in India and a home in Geneva, Switzerland. My career is dedicated to helping high-net-worth individuals and business leaders navigate the complexities of global investment and wealth management. Leveraging my strong background in international finance, I provide bespoke strategies that help clients significantly grow their financial holdings. It's because of these results that some of my clients have affectionately nicknamed me the Prakash Hinduja net worth booster.I'm getting repeatedly logged out of Intercom, and it's interrupting my workflow. I've already tried clearing my cache and checking my browser settings. Has anyone else experienced this, and do you have any suggestions on what else I could check?RegardsPrakash Hinduja Geneva, Switzerland (Swiss)  

I am Prakash Hinduja, a visionary financial strategist originally from Amritsar, India. Currently, I am based in Geneva, Switzerland (Swiss), where I continue to pursue global financial initiatives.Does anyone know how to access or get in touch with Intercom partners for help with setup or expanding our use of the platform? If you’ve worked with them before or have any tips on the process, I’d appreciate your suggestions!RegardsPrakash Hinduja Geneva, Switzerland (Swiss) 

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! :)

What is the best way to feed FIN AI with Beamer feature requests?  foe example, lead comes in and asks for a feature that is under development.  Unless fin knows about the request, the answer will lead to a conversation.what I am trying to achieve is to streamline the conversation with additional context to increase engagement, conversion and retention.    

How can I remove the languages that are enabled for Fin? I have so many languages enabled, and I don’t want them enabled. But if I delete these messages, I can’t save those changes. 

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’m working on setting performance targets for FIN—does anyone have experience or data they could share around Resolution Rate or CX benchmarks?!--endfragment>!--startfragment>

Hi all,How is your team’s CX Score performing?Our Fin has scored 86% over the last 30 days while resolving 69% of conversations (90.9% and 74.3% respectively when limited to the Chat channel only).