Answered

We want to export full extracts of our conversations from our workspace - how can I do this?

Hi,Is there a way to export all the tagged conversations?I wish to get a spreadsheet with the message that was tagged, so I need to check the content sent itself.Thanks in advance

Hi everyone! I'm exploring best practices around chatbot deflection and would love to hear from this community's experience. Even though you may be using Fin, the underlying strategies likely apply across platforms.We're currently using AI chatbot tools for customer support and are looking to improve our deflection strategy. A few questions I'd love your input on:What deflection rates are you seeing, and what's considered "good" in your industry? What types of content (articles, FAQs, flows) drive the most successful deflections? How do you measure true deflection success vs. a user who just gave up? What's the biggest mistake you made early on that others should avoid? How do you handle graceful handoff to a human agent when the bot can't resolve an issue?Appreciate any tips, benchmarks, or lessons learned, even if your setup looks different from ours!

We have a number of products with a lot of overlapping terminology, and a lot of audiences that overlap with other audiences. This has made it difficult to target the information Fin uses very specifically. We have been considering setting audiences up using conversation data instead of just user data, but I’m having a hard time understanding if/how that would work. We have a new conversation attribute that would be selected and help define the audience for that conversation. But is that effective? If the customer asked another question in the same conversation, or had chosen something incorrectly, could the audience for that conversation ever be changed? Open to any suggestions here on how this could work, or what better options might be. 

Fin AI will always give suggestions when a customer asks a question. Let’s say the customer asks about a device (we have physical products that require a little technical knowledge), Fin AI always responds something along the lines “What do you want to know? (for example: this thing, that thing, many other things) You might be able to do this or that”I would like to to answer the customer’s question and not give extra information unless absolutely relevant. However, no matter what guidance I give, it will not stop this behavior.

Hi all,We're a regulated fintech app (Junior Stocks & Shares ISA) and have two distinct user types who might need support:1. Our main customers — parents who hold a JISA account with us2. Gifters — friends and family who are gifting money to a child's account but don't have an account themselvesWe'd like to add a support button within our gifting flow so gifters can reach us when they get stuck. But we want to make sure gifter conversations are kept separate from our main customer support queue.A few questions:• Can we configure multiple Messenger launchers that route to different inboxes or teams depending on where in the product they're triggered?• Can conversations be automatically tagged or routed based on which screen or page the Messenger was opened from?• Is it possible to create a separate Messenger experience for users who aren't logged in or don't have an account?• Can we set up routing rules to ensure gifter conversations never land in the same inbox as customer queries?

Has anyone successfully managed to setup access for customers to the ticket portal without using JWT authentication? We’re not a SaaS business, and our customers run the software on premises, often behind firewalls without access to the internet, so integrating intercom into the platform is a non starter. I’m looking at launching with Email & Slack channels, but have hit a blocker with the ticket portal feature - ideally I do not want to have to build a customer interface to surface this to customers. 

I’ve been thinking about how customer support teams manage queries for content creation tools, especially those with a large non-technical user base. Free apps seem to generate a lot of repetitive questions like exporting issues, performance on different devices, or how to use certain editing features.From a support perspective, this raises a few questions:How much of these queries can realistically be handled through automation (chatbots, guided flows, etc.) without frustrating users? At what point does it make more sense to route users to a human agent instead of relying on automated responses? Has anyone here used Intercom to manage high-volume, feature-related queries like theseOpen to suggestions how others are balancing scalability with user experience in this kind of scenario.

We are using the trial version with Expert capabilities to assess if Intercom suits our needs. We want an AI agent to embed in our software products. This agent should provide level 1 support based on documentation content. If the agent cannot help, it should hand off to our Support and Product Team in Jira Service Desk by calling a data connector to create a new ticket via the Atlassian API.The challenge we face is that there seems to be no way to set a Title and Description or copy the conversation into attributes for the data connector.Is there a way to achieve this? We are not going to use Intercom Inbox, as our support team only will interact with our customers via Jira Service Desk.  using Message Body, just the first user´s message is returned, other attributes from Conversation category doesn´t seems to be working for a data connection. 

Hi Intercom team,I’m integrating @intercom/intercom-react-native into a React Native 0.81.4 + Expo (prebuild) Android app, and I’m seeing an issue where new messages are not delivered while the Intercom conversation screen is open. They only appear after I navigate away and come back.What I’m seeingI open the Intercom Messenger from my app (using Intercom.present()). I start a conversation and stay on that conversation screen. From the Intercom workspace, I send a reply to that user. Nothing appears in the conversation UI while I stay on this screen. If I: go back to the previous screen and reopen the Messenger, or sometimes background and foreground the app then I suddenly see the new messages. So it looks like the real-time updates / polling are not happening while the conversation screen is active.Setup detailsReact Native: 0.81.4 Expo: managed workflow with expo prebuild Library: @intercom/intercom-react-native 9.8.0 Platform: tested on Android (real device)Region: USapp.json plu

We are currently reviewing and updating Custom Ticket and Conversation attributes; however, have hit a roadblock when trying to archive unused attributes with inaccurate / outdated data as multiple custom attributes are linked to private reports that individual users have created over time.Unnecessary gatekeeping has resulted in me having to chase over a dozen individuals to either update or provide me with access to their private reports before I can archive these attributes.This poses a great risk as during the time it takes to reach out and wait for colleagues across a global org to assist, we have old, outdated data live in reports, and my hands are completely tied as I cannot access or update these reports myself.Feedback from the Intercom Support Team: “… to make changes to that attribute, your teammates who own the Custom Reports will need to either update the attribute used in their reports or give you permission to access their reports. Once all related reports are updated, yo

It appears new features are regularly deployed without testing against multilingual use cases, we now have Procedures, and Recommendations incompatible with our workspace, seemingly due to multilingual articles.Great example of "garbage in - garbage out"If your database isn't ready for AI, funny things will happen, and I suspect the Articles database has some poor architecture in the relation to parent pages against their multilingual pages.Fin AI poorly executes against multilingual, time and time again. I am losing confidence that Intercom's multilingual articles are being considered in the new deployments of products.Recommendations breaks with multilingual, Procedures break with multilingual. Hoping this is fixed soon!

I have successfully been able to integrate Product Tour for most of the platform. However,  have a section within my platform where a workflow needs to be completed by the users.The workflow comprises of 4 steps and it’s a wizard style experience. all the 4 steps have the same URL and just the content on the page changes upon completing a step but the URL remains same.Issue: The pointers which are meant to appear on the step 2 of the workflow appears on the Step 1 itself. The CSS elements are not visible on the Step 1 but still the pointers appear.I have tried attributing the HTML with intercom <div> as well, the buttons are even highlighted in Pink within the tour editor after the attribution. It means the attribution worked, Despite this, the pointers appear on Step 1 instead of Step 2.  

Turns out a “Company” filter doesn’t work in any of the SLA reports. Leaving you with no way to see the team’s performance for any of your clients. Or any other company related info, such as attributes.I’m surprised a basic report is missing and was wondering if anyone has figured out a way to solve this.

We are B2B so it's really challenging to set appropriate wait times without being able to do business days only. Does anyone have any rules of thumb or ways to calculate so that timing makes sense?

We have two Help Centers, one for México and one for Chile:https://ayuda.fintual.mx/es/https://ayuda.fintual.cl/es/The problem is that articles from Chile rank in Google in México and vice versa. How can we make sure the correct article ranks in the corresponding country? From what I´ve read, there is no possibility to implement hreflang tags neither inject code through Google Tag Manager. We still want them indexed in Google so we can also not restrict them to a certain audience. 

Hey, I am looking to create an internal process for one of our teams based on when a user reaches a point in an outbound messaging series and have hit a wall. In the series I have a message encouraging a customer to book a call, when they get this message, if they haven’t booked I want to trigger an internal process where a member of our team proactively calls the customer. I have added a tag to this message, however I don’t know how to assign a task to my team to do the follow-up action.  Not sure if this can be done via a workflow eg. Person Tagged “X” > Assign To “X Team” > Add Note Can anyone help? 

I am trying to integrate JIRA for Cloud with my Intercom Inbox. However, once a JIRA ticket is created, it is not getting linked to the Inbox panel. I manually added the link as well and it says in the note that the linking was successful - still do not see anything here.Am I missing anything? 

Hi All, How do you all work around the guidance limitation of 100 pieces of total guidance? We have the opportunity to consolidate some guidance, but because the bot is used across multiple teams with different workflows and channels, this limitation will hamper us. Is there a way to increase the limit?  What alternatives do y’all use to guidance to achieve the same outcome?  How many pieces of guidance do y’all have? Thanks!Afton

We are a SaaS company, and have deployed Fin to only half of our user base (which has been very successful to date). We have yet to deploy to the other half (mostly enterprise users) because they each have very unique account settings/configurations. The general content on our help center that supports Fin does not account for each of these unique instances, and would provide incorrect/misleading answers for these users.It would not be scalable/manageable to generate unique content/tagging for each account with their unique settings, so we were excited about the possibility to connect Fin to our custom MCP server to gather contextualized information for users on common queries and answer accordingly. (Discussed here: https://www.intercom.com/help/en/articles/11461635-powering-fin-with-your-external-tools-using-mcp-connectors)However, we can’t find a ton of information on connecting to a custom MCP server rather than using one of the templated options (Stripe, Shopify, Linear). The abov

I have a very simple use case. I want Fin to ask for the Project and the Organization before it escalates. For some reason, Fin continues to frame it like this:“Would you like me to connect you with a human agent to assist further? Or if you provide more details about your project and organization, I can continue to help you.”No amount of escalation guidance refining is working. Fin should be able to handle this, no?   

I have one other question about attribute data and existing reports.Namely: Why are not all attributes available to add in the reports? In some cases we would like to export the drill down of both conversations and tickets, in this drilldown it's possible to add certain attributes as extra columns, but not all attributes are available. Why is that?Is there a work around possible? Or a setting you can change to make this possible? 

Hi everyone,I’m unable to send any WhatsApp message to one specific client. No matter what I try to send, I get the error: “Something went wrong, please try again later.”The client has been waiting for a reply since yesterday, and they also just sent another message a few minutes ago, which I still cannot respond to.I also tried starting a completely new conversation and sending an already approved template, but the same issue still happens.Has anyone experienced this or knows how to fix it urgently?

Hopefully I can describe this as simply as possible to see if this is expected or if anyone has run into this.I have an escalation rule set and live for audience A. I have batch testing setup in the test section and for each batch I set an audience B-H, one at a time or a single one (doesn’t matter). But batch testing is never tested as audience A. For any batch test that I run for any audience B-H, the escalation rule is triggered, meaning that it automatically escalates so that I cannot test my content or other guidance. I must turn off escalation rule for Audience A, test in the batch section as Audience B to get my answers, and then turn on escalation rule for Audience A. This does not seem like desired behavior.If I just skip the batch testing and test directly in my product via the messenger, the Escalation Rule is not triggered and works properly.Does anyone know what could be causing this? Is there another setting I am not aware of?  An example of escalation rule being turned o

Title: How to get our redirect URI allowlisted for MCP DCR?Body:Hi team,We're integrating Intercom's MCP server into our platform, which lets customers connect their own Intercom accounts to AI agents they build with us. When attempting Dynamic Client Registration, we get:POST https://mcp.intercom.com/register{ "error": "invalid_redirect_uri", "error_description": "Redirect URI https://app.integry.io/auth/redirect/ is not in the allowlist, reach out to Intercom Customer Support if you believe we should support it"}A few questions:What's the process to request a production redirect URI be added to the allowlist? Is this handled through Customer Support, developer hub, or a partner channel? Are there review criteria or a security questionnaire we should prepare for? Can we allowlist a staging URI alongside production in the same request? As an alternative — does the MCP server accept access tokens issued by a standard Intercom OAuth app (via app.intercom.com/oauth) as bearer tokens? If