Fin Product Area

Hello support, We are running into a recurring issue where intercom occasionally drops attachments. We are able to download the attachment only by going to the actual email that’s sent, but not through the intercom app itself. See attached screenshot. The file in this example was 1mb in size. We appreciate any help you can provide.  

I'm looking for a streamlined QA process for managing Fin’s performance as a one-woman team. Would love some suggestions for best practices for maintaining quality without getting overwhelmed with all the reports and data Intercom provides for Fin performance.

Hi Community 👋We’re currently doing a large cleanup of our Intercom workspace — workflows, macros, tags, attributes, reports, roles, permissions, etc. — and we’ve run into a major limitation regarding report access for Admins.Even as Workspace Admins, we cannot see, edit, or delete all reports. Access is limited to only those reports explicitly shared with us. This creates challenges when trying to maintain workspace. For example, if we want to remove or archive a tag or attribute, Intercom blocks the action if it’s used in a report we don’t have access to. That forces us to track down the report owner, request full access, and wait for them to respond — which can take days.The situation becomes even more complicated when report owners are on maternity/paternity leave or long-term leave. Support has informed us that they cannot delete these reports on our behalf, leaving us effectively blocked from cleaning up parts of the workspace.We actually submitted this as a feature request to P

Hi guys, I’m wondering if agents can send our customers a calendar feature for them to book a onboarding call but something that’s built in Intercom rather than a external calendar app, I haven’t seen it yet, is there such a feature already?Thank you in advance 

Hi,Could someone help me confirm whether I’m using the Intercom report correctly?For one of our clients, we need to generate a weekly report and track ticket follow-ups. Currently, the report only includes tickets that were created during that specific week. However, if I’m waiting for a customer’s response and the conversation is closed the following week, it doesn’t appear in the report.Is there a way to include these tickets in the follow-up, or am I missing a setting in the report?Any guidance would be greatly appreciated 😊Thank you!

It would be extremely helpful if agents could give Fin instructions directly inside an ongoing conversation, without having to update global content or wait for retraining.ExampleAn agent could write internal instructions like:    •    updated information    •    temporary notes    •    clarifications    •    corrections…and Fin would immediately apply these instructions and continue the conversation with the customer using the updated information.Why this matters    •    Allows quick corrections when Fin is about to provide wrong or outdated information    •    Enables real-time steering of AI responses without agent replies    •    Especially useful for temporary changes (e.g. delivery delays, special cases, exceptions)This would make Fin far more flexible and safer to use in live support situations.

There’s a ‘Give Feedback’ button above and a ‘Feedback’ button to the right. Why 2? 

When we receive a new ticket by email it only shows the email and the status of this ticket, but not the title or description or any other attribute set, so it's hard to follow and reply to, unless you open the app. Is there any way we can set it up?We only receive this:Thanks in advance.

I’d like to see questions my teammates asked Copilot that it wasn’t able to find answers for. Why is this not available in reporting? Visibility on unanswered questions seems like a simple way to identify gaps in our knowledge and content.

I am trying to access the agents that are working in my organizations to replicate our reports in the reporting tab of intercom. We have created interesting reports with FRT, closed tickets, open tickets etc. However, instead of using the reports in intercom, I would like to get the same using the API.Now the problem I am facing is that I can only get myself and FIN rather than access to all the other agents working in the organization. Can you please guide me in what I might be doing wrong.HEADERS = {"Authorization": f"Bearer {BEARER_TOKEN}","Accept": "application/json","Intercom-Version": "2.14"} # -------------------------------# FETCH ALL ADMINS# -------------------------------url = "https://api.intercom.io/admins" response = requests.get(url, headers=HEADERS)response.raise_for_status() # Will raise an error if request fails admins_data = response.json() # -------------------------------# PRINT ADMINS# -------------------------------for admin in admins_data.get("admins", []):print(

Hi everyone,Our bot communicates in Hebrew. Because Hebrew is gendered, we’re seeing an inconsistency: Fin sometimes replies in masculine form and sometimes in feminine form.Both of the following Guidance rules are under Communication style: Bot self-reference is always masculine When responding in Hebrew, always refer to yourself in masculine grammatical form. This applies to self-descriptions, actions, and statements about your role or capabilities. Do not change your self-referential gender under any circumstances.What NOT to do: Do not adapt self-reference based on the user’s gender or language. Do not use feminine or neutral forms when referring to yourself.  AND:  Hebrew gendered language (pronoun-aware) When responding in Hebrew, adapt grammatical gender when addressing the user: If a <Pronoun> attribute exists, use it. If no <Pronoun> attribute exists, follow the gender implied by the user's Hebrew language. If gender is unclear, use neutral phrasing or defaul

I am pretty new to Intercom although I am pretty familiar with other CX tools that are similar - I have been struggling lately with our bot giving completely wrong and false information to our customers on topics that need to be answered with accuracy. It is drawing information from places outside of the articles and snippets we have supplied in our instance. I am struggling with understanding why it would pull in information that is seemingly just completely made up or not in line with things we have published for the site. What would be some suggestions for how to update and change this? Should we use guidance? How specific can we get? Any tips at all? Thanks!

Hey! I discovered that the Side conversations option allows to send messages to Slack—neat! However, it is not straight forward to later on find the conversations that have side conversations. Any ideas of how this could be done? In short, this is the workflow that we are aiming at: When we need to ping someone from the team for a quick question, start side conversation and set message to selected Slack channel (this part is covered) Then find a way to easily keep track of this conversation (or any conversation that as a side conversation) within Intercom, like using Views or something similar. (This is not done!)I figured it could be done using Views filters (like when we filter conversations that have tickets, etc.), but I failed to get it working. Any thoughts, tips or tricks?

Hi there, I am starting with a very simply implementation. We are only using Facebook through socials to start (no web or mobile implementation.) We have a workflow that I want to run whenever someone opens a new conversation with us. I don’t want it to run the workflow for that person again until we close the conversation. Our workflow asks some basic questions and then assigns the conversation to me. I want to them communicate manually with the lead and then once I am done I want to close the conversation, and the next time they message us they get the workflow again.Thank you!

I’ve seen a consensus online that it should be very clear for customers they can say “talk to person” at anytime during the conversation to get connect to a human. This builds trust with them, but I’m curious how folks have been doing this.  We used to put it at the very beginning of conversations, but its unclear if that was effective and customers saw it. How do ya’ll do this? Open to all and any suggestions. 

Hi! We just set up intercom/slack connection which is very awesome! We don’t yet want Fin replying, and I have turned off all Fin workflows.  But, I can’t stop Fin from posting response times in slack threads in our community.  I can’t work out how to turn this off.  Any ideas?  Thanks Matt  

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 would like to set FIN over the holidays so that it informs customers that the wait time for human support may be a little longer. Where can I set what FIN responds when asked for human support? 

I have spent some days trying to set up a product tour for our coursebuilder and it is working in very inconsistent ways. In our coursebuilder, the user is guided through a step-by-step process of specifying a target audience, uploading documents etc. If I use a single product tour for all the steps across pages, this does not work as elements are displayed too early, before the page in question is accessed. I found a workaround by setting up multiple product tours but they can disable each other, even when I specify a different start URL. Sometimes it works, sometimes not.Another problem is that essentially the product tour Preview function does not work with our coursebuilder, and neither does the link feature if I enable “use tour everywhere”. My only option to test the product tour is to assign it to my account and two other admin accounts. I then log into three different accounts once a day to have one runthrough each. If one part of the tour is not displayed, I have to wait to th