Product Wishlist

Sofia MaconiNew Participant

Monitors + Scorecards feature requestsSubmitted

Ability to re-evaluate conversations when re-opened and re-closed. When a conversation is re-opened, it should be removed from the monitor and re-added when closed again. Making rating reasons available in reporting so we can filter on them. In addition to this, making rating reasons attached to specific rating options. For example, if I have a “Resolved” rating option, I can then attach specific reasons for the “Resolved” option like “Explicit Confirmation” and “Procedure completed” that would only be selected if the AI Scorer selected Resolved. Different rating options per scorecard on a shared criteria so we can tailor rating options to Fin or human agents accordingly. Ability to score both Fin + human agents using a single monitor + scorecard. Being able to display or filter on more attribute columns in the monitor view. Being able to see scoring details in the drill-in views from reports (instead of only from the monitors page)

Forum|Forum|55 minutes ago

david lyonsNew Participant

Add a response delay setting for Fin on all plans, including BasicSubmitted

On the Basic plan there is no way to delay Fin's replies. No Workflows, no wait timer. It's instant response or off entirely. Simple automations offer a 2-minute delay, but only on the first Messenger message during office hours. There is no delay option for email or for ongoing conversations, which is where the clash actually happens.The problem: I'm on the phone with a customer, they email support during the call, and Fin replies before I can even start typing, sometimes contradicting what I've just agreed with them verbally. Two conflicting answers from one company. The "send a message first to claim the conversation" workaround doesn't work, Fin is always faster.This makes Basic self-defeating. With no control over when Fin engages, the rational move is to switch it off. And a customer who has turned Fin off never upgrades to Advanced for Workflows. You lose the upgrade path.The ask: a simple "wait X minutes before Fin responds" setting on all plans. If a teammate replies in that window, Fin stands down. One timer field would make Fin usable for exactly the small teams Basic is aimed at.

Forum|Forum|5 hours ago

Sam ScherNew Participant

Don't automatically reopen resolved tickets on customer replySubmitted

When a ticket is marked Resolved, it should remain resolved unless an agent decides it needs to be reopened. A customer replying doesn't automatically mean the original issue is unresolved. They may simply say thank you, ask where the fix was made, or ask how to use the solution. The previous behavior, where only Waiting on Customer tickets automatically returned to In Progress, more accurately reflected the status of the issue. Automatically reopening resolved tickets makes the ticket status less accurate and creates unnecessary work. This behavior should be configurable so each workspace can choose the workflow that best fits its support process.

1

O

Forum|Forum|17 hours ago

E

Evie LynchNew Participant

Feature request: let Fin add a colleague into a conversation and continue it over emailSubmitted

When Fin identifies that a conversation needs a specific person, I want it to be able to add that person into the conversation directly, with the thread continuing over email outside of Intercom. Fin makes the introduction, the customer and my colleague are both on the thread, and they carry on together from there.Think of it as Fin brokering a warm handoff: "I've looped in Hannah from our team, she'll take it from here" and from that point it's a normal email thread between the lead and Hannah, with the conversation history attached.Our use caseNew business leads come through Fin on our help centre. We've set up a procedure so Fin collects the lead's name, email and company. The person who follows up is a BDR who works out of email, not Intercom.What we want is simple: Fin finishes qualifying, adds the BDR into the conversation, and the whole thing continues as an email thread between the lead and the BDR. No copy-pasting details, no relay through another team, no dead end where the lead is told "someone will be in touch."Today that handoff isn't possible. Conversations can only be assigned or mentioned inside Intercom, and notifications only reach Slack channels or Intercom users. The conversation can't leave the platform with a new human participant on it.What we're not asking forNot Fin for Sales. Our account manager has already advised our inbound lead volume doesn't justify setting it up, and we agree. This isn't a qualification or playbook problem, it's a handoff problem, and it applies beyond sales: finance, legal, and partner contacts all sit outside Intercom too. Not a notification. An FYI email about the conversation still leaves the lead sitting in a closed chat. We want the person added into the conversation so it continues with them on it.

E

Forum|Forum|1 day ago

Nicolaj Bjørn Busk JensenNew Participant

AI Inbox Translations only inboundSubmitted

Hi team,We recently started evaluating the AI Inbox Translations feature, and we're very interested in using the inbound translation functionality. It has the potential to save our support team a significant amount of time that is currently spent translating incoming messages.However, we're not entirely satisfied with the quality of the outbound translations. We'd love to be able to enable inbound translations only, while keeping outbound translations disabled.The reason is that errors in inbound translations generally don't affect our business, as we can still understand the customer's intent. On the other hand, outbound translations are not shown to us before the message is sent, so we have no way of verifying whether the translation has altered the meaning or context—which unfortunately happens from time to time.Would it be possible to support this kind of setup, where only inbound translations are enabled?Thank you.

Forum|Forum|2 days ago

B

Brandon MosesNew Participant

select folder for snippet when creating through the improve answer workflowSubmitted

When improving an answer provided by fin, creating a new snippet, it just puts it into a content folder. Adding an option to select a folder right in that workflow would prevent from having to go to the knowledge tab to modify the snippet created.

B

Forum|Forum|2 days ago

Matthew SharpNew Participant

Add option to limit the amount of time rating of Fin via CSAT is availableSubmitted

Hi,For agent CSAT ratings, there is currently an option to prevent customers from submitting a rating after a configurable period of time, see below:Could the same "Prevent customers from rating after a given period of time" option be added to Fin AI CSAT options?During a recent review of our Fin AI CSAT data, we identified several negative ratings that were submitted days, weeks and, in some cases, months after the original AI conversation. These ratings all reflected subsequent interactions or dissatisfaction with business outcomes rather than the AI response itself. Simply leaving a negative CSAT may not also encourage getting back in contact with us to resolve the new issue.CSAT is intended to measure satisfaction with a specific interaction, allowing ratings indefinitely reduces the reliability of the metric and makes it harder to evaluate Fin AI performance or identify genuine areas for improvement.Since this configuration already exists for agent CSAT, having feature parity for Fin AI would provide more reliable reporting while still allowing customers a reasonable opportunity to submit feedback. Thanks!

Forum|Forum|3 days ago

Henrik RActive User

Make replies in phone conversations visible to customers in MessengerSubmitted

We would like to request an improvement to how phone conversations work in Intercom.Today, replies sent within a phone conversation are not visible in the Messenger conversation history. If the customer has an email address, the reply is only delivered by email. If they do not have an email address, the customer never sees the reply at all.This creates several challenges:Support agents can mistakenly believe they have replied to the customer when, in reality, the customer has no way of seeing the message. Customers without an email address receive no response, which leads to confusion and unnecessary follow-up contacts. Agents often have to start a brand-new Messenger conversation instead of continuing the existing one, resulting in fragmented conversation history.We would like the option to make replies sent in phone conversations also appear in the customer's Messenger inbox. Ideally, this could be:The default behavior, or A workspace setting that administrators can enable or disable.This would provide a much more consistent omnichannel experience, reduce confusion for both customers and support teams, and ensure that conversation history remains complete regardless of how the interaction started.

1

Forum|Forum|3 days ago

V

Val BrookNew Participant

Product Tour with AISubmitted

We are adding a product tour to our software using Intercom.We watched demo from a software company that use AI to help develop a product tour. That was the only differentiator between Intercom’s Product Tour vs them.It would be great to have an ability to use Fin help guide the product tour during onboarding. For example, he can ask - do you work for X or Y industry - are you a regular user or an admin and then deliver product tour/onboarding based on what client has selected and then getting better with time - noticing what people are doing more of - settings, training or something else and adjust product tour according to that data.

V

Forum|Forum|5 days ago

SaikaNew Participant

Option to generate AI summaries using only customer messagesSubmitted

Currently, AI summaries include both customer messages and Fin (bot) messages in the conversation. This makes it difficult to create summaries that focus only on what the customer said.It would be very helpful if there were an option to generate summaries based only on customer messages, excluding bot responses. This would make summaries more useful for internal review and QA workflows.Thank you for considering this improvement.

Forum|Forum|6 days ago

SaikaNew Participant

Increase the limit of AI‑scored criteria per workspaceSubmitted

Currently, each workspace has a limit of 20 AI‑scored criteria across all scorecards. For teams running more detailed QA reviews, this limit can feel restrictive.It would be very helpful if this limit could be increased or made configurable, so teams can create more AI‑scored evaluation criteria without needing to split them across multiple scorecards.Thank you for considering this improvement.

Forum|Forum|6 days ago

Ryan MaddenNew Participant

Auto-add Spanish triggers to procedures (Feature Request)Submitted

Summary: Requesting a way to automatically generate/add Spanish-language trigger phrases to Fin procedures, instead of manually creating a duplicate Spanish trigger for every English one.Use case: Reduces manual maintenance work on bilingual procedures and improves Fin's coverage for Spanish-speaking customers, which supports our CX goals.

Forum|Forum|6 days ago

Ryan MaddenNew Participant

Adding Markdown support to file uploadSubmitted

Document parser breaks formatting on upload Summary: When uploading PDFs and DOCX files (e.g. into procedures/content for Fin), the document parser ruins formatting and messes up the document's organization, making the parsed content a mess.Details:Affected file types: PDF and DOCX Issue: parsing strips or scrambles formatting and structure, so the resulting content is disorganized and hard to use Impact: degrades quality of Fin's knowledge/procedures content, which hurts customer-facing answers and our CX scoreRequested fix: Preserve document formatting/structure during parsing. As an alternative or additional fix, native Markdown (.md) upload support would likely resolve this since it avoids the PDF/DOCX conversion step entirely.

Forum|Forum|7 days ago

JHarloweConnector

More Granular Permissions Set For ProceduresSubmitted

Summary: We'd like the ability to grant teammates access to create and edit Fin Procedures without also giving them visibility into or access to Workflows, automation settings and other sensitive operational areas of our Intercom workspace. Current Behavior: Today, Procedures live within the Fin AI Agent tab, which is accessed via the "Can view Fin and Automation settings" permission. This same permission also exposes Workflows and Simple Automations. There is no way to grant procedure-building access in isolation, any teammate who can work on procedures can also see workflows. To prevent teammates from editing workflows, we can withhold the "Can manage Automation settings and inbound Workflows" and "Can manage outbound Workflows" permissions, but those teammates will still have full visibility into workflow configurations, which is not ideal from an access control and operational security standpoint. Requested Change: Introduce a dedicated permission (e.g., "Can manage Fin Procedures") that:Allows teammates to create, edit, and manage Fin Procedures Does not expose Workflows, Simple Automations, other automation settings or operationally sensitive areas of the workspace Can be granted independently of any workflow-related or data / security related permissionsUse Case: We want to involve subject matter experts and content contributors in building and refining Fin Procedures, teammates who understand our processes deeply but should not have access to the broader automation and workflow configuration of our workspace. Today, there's no clean way to enable this without overexposing sensitive operational settings. Desired Outcome:A permission model that lets us confidently delegate procedure authorship to a wider group of teammates, with clear boundaries that protect workflow integrity.

Forum|Forum|7 days ago

Michele BossartNew Participant

Let us pick certain reps for Fin training, or exclude rep answers.Submitted

We have a lot of new customer support reps that are coming in and have given some incomplete or inaccurate answers. We would love the ability to tell Fin to use our stars for learning and answers, and ignore some who are training. Case in point, one of our new reps gave a wrong answer a few weeks ago (that was from Copilot while when we were just getting started and training both CoPilot and Fin) assuming it was correct. Fin still references this answer, even though it is wrong.We can avoid this by just having Fin only learn from our more experienced reps.

Forum|Forum|7 days ago

David BrownNew Participant

Bulk control of Fin access to synced website pages after a full crawlSubmitted

When syncing a website for Fin, the crawl often imports a large number of pages. Currently, restricting Fin’s access to specific pages requires manually disabling them in the UI, which does not scale for large sites.It would be valuable to add API support for bulk updating External Pages after a full website crawl, allowing teams to programmatically limit Fin’s availability for selected pages (for example via a bulk update endpoint). This would enable automated pruning of redundant or unwanted pages without manual UI changes.I attempted to set fin_availability = FALSE via PUT /ai/external_pages/{page_id}, but the request failed because the page belongs to an automatic website sync source. Intercom returned:Content Import Source must have API sync behaviour.The current API workflow requires creating an API-based Content Import Source and POSTing pages to the External Pages endpoint to create or update them. Because of this, teams must either:determine the preferred pages before importing via the API, or manually disable pages in the UI after a full crawl.Allowing teams to sync the site first and then programmatically restrict pages afterward would make the process significantly easier.

Forum|Forum|9 days ago

AmyCNew Participant

Emoji-only spam detectionSubmitted

Message Content conditions are only built for text matching, and there's no built-in support for detecting emoji-only messages as spam. This seems to be a real gap for social channels specifically. Having this as an additional feature would be extremely helpful when filtering out spam communications.

Forum|Forum|9 days ago

Support Escalate OpsNew Participant

Can FIN AI send emails from different inboxes by brand?Submitted

Hi ! I’m running into a limitation with Fin AI and multi-brand setups.I have two brands, each with its own inbox, but currently Fin replies from a single inbox… Regardless of the brand the customer is contacting.This causes issues with context, audience targeting, and consistency.It would be great if Fin could reply using the correct inbox per brand.Hope this feature is considered!

1

Forum|Forum|9 days ago

Daniel RönnbergActive User

Add a disclaimer that the message has been automatically translated when using AI Inbox TranslationsSubmitted

Hi,We've enabled AI Inbox Translations for our support, allowing us to assist more users in their native language. I think this is a great feature that will enhance the user experience. However, transparency is important to us, and we want users to always be aware when AI is involved.It would be really helpful if there were an indicator showing that a message has been automatically translated into their preferred language, along with an option to view the original message in English.

6

Forum|Forum|13 days ago

J

Juan MorenoNew Participant

Use Review Scores and Comments (Monitors) to Train AI AgentSubmitted

We'd like reviewed conversations (in Monitors) actually feed back into the AI agent's training.Right now review scores and reviewer comments just sit in the record with no way to use them to improve the AI agent's future responses other than updating our content (which is a manual process).The review data, the score AND the comments should be used as a training signal so the AI agent gets better based on real feedback from our team instead of having us manually update our content and snippets, which is very time-consuming. Comments are an important part because they could tell the model what’s wrong. Most of Fin’s mistakes are small but impacful nuances that don’t require an article or snippet update of its own.There should be a way to directly tell the model what it got wrong and what should have said instead during the review process rather than having our team update our content.

J

Forum|Forum|14 days ago

ArmandNew Participant

Prevent users from reaching human supportSubmitted

In FIN, "always offer human support" is currently a default setting that cannot be disabled or preventend.However, for certain customer segments (audiences), we have agreements in place where these users should be directed to their own administrator first, rather than to our human support team, if FIN can't resolve their issue.We'd like to request a feature to support this flow. Ideally, it would work like this:FIN attempts to answer the customer's question using our knowledge base, snippets, and past conversations. If the customer indicates the answer isn't helpful, they're given the chance to rephrase their question. If FIN still can't provide a satisfactory answer, instead of offering human support, the customer should be directed to their own administrator.

Forum|Forum|14 days ago

Maria GardetteNew Participant

Add a “next step / action” field at the end of Monitors QA reviews.Submitted

Description:During QA reviews in Monitors, reviewers often identify improvements needed after evaluating a conversation. Today there’s no structured way to capture follow‑up actions.Request: introduce a dedicated action / to‑do step at the end of the QA review where reviewers can define the next step (e.g., coaching, training, process update, content change). This would help teams track improvement tasks directly from the QA workflow instead of relying on notes or external tools.

Forum|Forum|15 days ago

G

GlendaNew Participant

Conversation tracking details - 'closed by'Submitted

What you want: a “closed by” field (workflow vs teammate) Why it matters: to track abandoned workflows vs manual closes Where you’d use it: reporting, filtering, and monitoring Example: “Report on conversations closed by workflows vs teammates”

G

Forum|Forum|16 days ago

Daniel RönnbergActive User

Hide unused Fin roles in content settingsSubmitted

We only use Fin for Service, but when managing which roles content should be used for, Sales, Service, and Ecommerce are all shown as options. I can turn Sales off, but Service and Ecommerce appear to be linked, meaning Ecommerce cannot be turned off without also turning off Service. Likewise, turning Service on also turns Ecommerce on.From a user perspective, this is confusing because it looks like these roles can be managed independently, even though they cannot. Since we don’t use Fin for Sales or Ecommerce, I’d ideally like the option to hide or disable those roles entirely from our workspace, or at least have clearer UI messaging explaining that Service and Ecommerce are linked.The current setup creates unnecessary friction when managing content because I have to keep seeing and accounting for roles that are not relevant to our use case. It also makes the settings feel more complex than they need to be for teams that only use Fin for support/service.Suggested improvements: Allow admins to hide or disable unused Fin roles at workspace level. Allow Service and Ecommerce content settings to be managed independently. If they must remain linked, make this explicit in the UI before users try to toggle them. Consider simplifying the content management experience for teams that only use Fin for Service. This is not blocking us from using Fin, but it adds avoidable confusion and makes content governance harder than it needs to be.

Forum|Forum|16 days ago

SiobhanNew Participant

View or audit what’s stored in Operator’s workspace memorySubmitted

Workspace members should be able to view and edit the shared memory that Operator uses (e.g. tone of voice, style guides). At the moment, this context isn't visible or editable by the team, which makes it harder to keep it accurate and up to date, and leads to duplicated effort when different team members try to recreate or adjust the same guidance.Giving teams visibility into this shared memory, and the ability to update it, would reduce repetitive work and give everyone clearer insight into how Operator's output is shaped, supporting better collaboration across team members who share responsibility for its performance.