Product Wishlist | Community

Help Center
Academy
Developer Hub
Partner Hub
Hire an Expert

Create New Topic
Login

How Nuuly turned AI savings into higher pay for its support team

7 days ago

Home
Ideas

Product Wishlist

Share product ideas and upvotes with our product team

Your Guide to Joining the Beta Group & Navigating the Product Wishlist

Join the Beta Group 🎉 You can now join the Beta Group and get exclusive early access to product betas, share feedback and contribute to shaping the In...

Forum|Forum|2 years ago

35128

Idea Pipeline

Filter by idea status

Browse by category

452 Ideas

Most replies

Most votes

Newest first

E

Ed MorrellNew Participant

Preserve and restore conversation ownership after Fin AI Agent involvementSubmitted

When a human agent takes ownership of a case, particularly for complex, multi-step issues like repair bookings or courier collections, and Fin subsequently handles part of that conversation (e.g. answering a status update, running a procedure), there is currently no native way to automatically return the conversation to the original owning agent once Fin's involvement ends or escalates. Our agents handle cases that span multiple touchpoints. An agent may book a scooter collection or repair, making them the case owner with full context. If the customer later contacts us again, Fin may handle the interaction but when Fin escalates or the conversation needs human attention again, it lands in an unassigned team queue. The original agent loses the case unless they find it or it gets manually reassigned to them. The only current workarounds I can think of:Agent name tags + a workflow branch per agent (brittle, requires maintenance as the team changes) Creating a new custom attribute (however, we've exhausted our attribute allowance on reporting-critical fields)None of these are clean solutions, they all require ongoing manual maintenance or sacrifice something else.The ask: A native "Case Owner" concept at the conversation level, separate from the current assignee, that: Can be set by an agent when they take ownership of a case Is preserved throughout Fin's involvement in the conversation Automatically reassigns the conversation back to the case owner when Fin escalates, hands off, or the conversation leaves the bot inbox Alternatively, a workflow trigger condition of "previous human assignee" that can be used to route conversations back to whoever held the conversation before Fin took over. As teams adopt Fin more deeply particularly on email channels where conversations reopen and span days or weeks, case continuity becomes critical. Fin is excellent at triaging and answering, but the handoff back to a human needs to be intelligent, not just "drop it in the team queue." This feature would allow teams to confidently expand Fin's scope without sacrificing the accountability and context that comes with named case ownership. This would affect any teams using Fin on email or async channels with multi-touchpoint cases, repairs, logistics, complaints, or anything requiring follow-up over time. ThanksEd

0

E

Forum|Forum|1 day ago

L

LouiseKleinConnector

Category Detection Feedback LoopSubmitted

We’d love a way to provide direct feedback on Fin’s category detection, particularly for attributes and list-based categorization. For example, when Fin assigns the wrong category, it would be useful to mark the selection as incorrect and specify the correct category.In cases like this one, the category itself is well defined, but Fin’s reasoning led it to the wrong selection. Having a feedback mechanism for “selected category vs. correct category” that could be used to improve future categorization would be extremely valuable and could significantly improve accuracy over time.

0

L

Forum|Forum|1 day ago

M

Marco BernardNew Participant

Enhance Claude (Anthropic) with full access to Intercom WorkspaceSubmitted

Currently, the only way to use Claude is to connect the Intercom MCP and perform in-article updates or fetch articles, etc., but it feels half-baked and lacks many useful features. For example, Claude can’t edit multiple languages, only the main language can be added. For me, that’s German, so I can’t edit the English version.We also need an HTML/CSS editor within Intercom. When Claude generates an hc article structure and I don’t want to push it via the MCP, I should be able to copy the HTML and paste it into Intercom so everything is interpreted correctly and formatting issues don’t occur. Also editing Snippets is important, which he cannot access.More broadly, give Claude more access to the workspace so he can reference resources and assemble content. Right now, using him beyond fetching articles is painful. This is the functionality I rely on most, but other capabilities are lacking because he doesn’t have full Intercom access.

1

A

Forum|Forum|1 day ago

G

Gavin LawrensonNew Participant

Reference Macros for Pre-Defined Bot GuidanceSubmitted

I would like it if we could have the chat bot view/reference all of the Macros we have set up to use as pre-defined guidance on what to say and do in a given scenario.

0

G

Forum|Forum|1 day ago

P

Paula AcabadoNew Participant

Allow the AI scorecard for monitors to be trained by the manual reviews submittedSubmitted

It would be nice to use manual reviews submitted by teammates to help train the AI reviewer for similar scorecards

0

P

Forum|Forum|1 day ago

T

Thales LopesNew Participant

Improvement Suggestion — Adding Sector as a Criterion for Audience RulesSubmitted

I’d like to report a potential improvement regarding the Audience configuration.Recently, we expanded the operation to other products. Given this scenario, managing the materials now requires more robust audience rules to prevent content related to other products from being incorrectly used in ERP support interactions, and vice versa.After reviewing the current Audience configuration, I noticed that it is not yet possible to use the Sector attributes we created for chat classification as a rule criterion. These attributes are currently essential for correctly routing each interaction to the appropriate Fin configuration and, consequently, to the support team responsible for the respective product.If we could use Sector as a condition in Audience rules, we would be able to segment customers and materials more precisely according to each product. In addition, this configuration would make future maintenance and adjustments much easier, as we could focus corrections and improvements on each sector's specific prompt, without having to revise broader audience rules.Given this need, we would like to request the addition of Sector as an available criterion when creating Audience rules. We believe this improvement would help ensure more accurate material segmentation, prevent inappropriate content from being used across different products, and make it easier to manage and continuously improve Fin.

0

T

Forum|Forum|2 days ago

A

Amy DeFineNew Participant

Smart Replies - option to turn offSubmitted

I’d like to see the ability to turn off smart replies (at the admin level) to ensure an entire team is / is not using them as preferred by the org.

3

Forum|Forum|2 days ago

L

LiveLongAndPatrickNew Participant

Support Procedures on Slack ConversationsSubmitted

Our team uses tons of slack channels for communication with customers, so it would be excellent if Procedures triggered on Slack conversations. They have been really impactful to help with troubleshooting and resolution rate, but since they aren’t supported on slack convos, we are hitting a plateau.

0

L

Forum|Forum|5 days ago

B

BryanNew Participant

Let fin use previous conversations with the same customerSubmitted

I would like it when fin can use the previous conversations with the same customer and can continue with that same topic if needed. So the customer can ask follow up questions and Fin “remembers” that conversation with that customer.

2

Forum|Forum|6 days ago

M

Michael StrebNew Participant

If an email arrives as spam, then unmarked as spam, them email should follow the workflows instead of Fin replying.Submitted

If an email comes in and is automatically marked spam that isn’t spam, we mark it not spam. From there, it should follow the workflows that we have setup, but doesn’t. We have emails that are sent to a specific email address that just need routed to that team inbox (things like notifications from a tax agency that a return was processed), Fin never is to get involved. But, if one of those emails arrives marked spam, and is manually unmarked as spam, Fin replies to it and there are no workarounds to prevent that. It either needs to follow the workflows or do nothing so it can manually be handled.

0

M

Forum|Forum|6 days ago

Bruno FerraraNew Participant

Fin improvement tracking — something like Linear, but inside IntercomSubmitted

One thing we’ve been exploring recently is using Linear to manage the issues we identify with Fin.Assigning an owner, tracking actions and status, and keeping a record of how each issue was resolved. Given that Intercom is increasingly bringing other tools and workflows into the platform, such as Releases, I think it would be really useful to have something similar natively for Fin.For example, being able to flag an issue, create a card for it, with an owner, notes/actions and a status. It could then be moved through different stages as it’s being worked on, and ideally linked back to the conversations affected.If something like this existed within Intercom, it would be perfect and would keep the whole identify → fix → measure feedback loop in one place.

1

Forum|Forum|7 days ago

I

ImmortalNew Participant

Support GitHub repositories as a knowledge source for AI syncSubmitted

Currently, AI content sync works well with websites and hosted documentation pages, but it does not support pulling structured content directly from GitHub (e.g. public or private repositories containing developer documentation).In our case, we maintain part of our developer documentation in a GitHub repository (e.g. https://github.com/Crocoblock/plugins-documentation), and it would be extremely valuable if the AI could use this source when generating responses for users. It will allow to keep developer documentation in GitHub as the single source of truth and ensure AI can answer technical questions using up-to-date GitHub docs

2

I

Forum|Forum|8 days ago

S

Support FourwavesNew Participant

Sync content from Github - Multilingual supportSubmitted

This synchronization looks very neat: https://www.intercom.com/help/en/articles/15943800-sync-content-from-githubUnfortunately, it lacks support for multilingual content, which is a significant drawback.

0

S

Forum|Forum|8 days ago

J

Judy CorreiaNew Participant

Recommendation Audit or CategorisationSubmitted

Currently Fin Recommendations (content gaps, data gaps and action gaps) only have two options - reject or mark as done/approve. Rejecting removes the recommentation and stops Fin from suggesting it again in the future. In our case this is limiting as a recommendation (in particular or data and action gaps) may not be technically possible today, but as technology changes the recommendation may make sense at some future time. It would be amazing if recommendations had a option for a “soft rejection” where it may be rejected now but we’d like Fin to make the recommendation again (if warranted) at some future time, someting like “remind me again in X months”It would also be great if: there were an audit trail, where we could see what recommendations were accepted and rejected. In addition to an audit, being able to specify reason for rejection, this would help with identifying the recommendations that may not make sense today but could in the future. Currently to overcome this limitation in auditability and tracking we need to keep a running list of recommendations in a spreadsheet, noting the recommendation, when it was suggested and the reason for rejection and review it regularly to see what might be feasbile today that perhpas wasn’t a few months ago. This adds extra overhead to our process and means having to bounce between applications vs having one source of truth within Fin.

0

J

Forum|Forum|8 days ago

I

ImmortalNew Participant

Give permissions for Monitors without access to FINSubmitted

Right now in order to review conversations in Monitors we need to give full permission for FIN. It would be great if we can give access specifically for Monitors excluding FIN.

0

I

Forum|Forum|10 days ago

Matej BosnjakConnector

Feature Request: Folder / Collection Structure for Intercom Audiences (Segments)Submitted

Hi everyone! SummaryWe are building a structured segmentation system covering 8 countries × 6 license tiers × up to 7 roles per tier, plus driver, EMS, and product-specific sub-segments. This will result in 150–200+ audience segments in Intercom.At this scale, the flat list view of the Segments section becomes unmanageable. We are requesting a folder or collection structure for audience segments to enable organised navigation and team usability.Problem Intercom Segments currently exist in a single flat list with no grouping or hierarchy. With 150–200+ segments, finding the right audience requires scrolling or searching every time. There is no way to visually distinguish between segment types (e.g. country-based CPO segments vs. driver segments vs. product segments). This makes it difficult for support agents, Fin AI configuration owners, and CS managers to confidently navigate, audit, or update the correct segment. Onboarding new team members to the segmentation system becomes significantly harder without clear visual structure. Requested FeatureIntroduce folders or collections for the Segments section, allowing users to: Create named folders (e.g. 🇩🇪 Germany, 🇧🇪 Belgium, Business, Pro, Enterprise) Assign segments to folders — either at creation or via drag-and-drop / bulk assignment Expand / collapse folders in the sidebar or segment list view Nest segments logically without changing their underlying rules or behaviour Example StructureCopy📁 Germany (DEU) ├── DEU — Pro — Fleet Admin ├── DEU — Pro — Fleet Manager ├── DEU — Business — Finance Manager └── ...📁 Belgium (BEL) ├── BEL — Pro — Fleet Admin └── ...📁 Drivers ├── CC@home — Driver — Manual ├── CC@home — Driver — Automatic └── Reg. driver — no platform access📁 EMS ├── EMS — Dynamic (System Users) └── EMS — Static (Drivers)📁 Legacy (Wind-down) ├── All — Basic └── All — CompactImpact Area Current With Folders Segment navigation Scroll through 150+ flat entries Expand relevant folder, find segment instantly Fin AI configuration Error-prone — easy to select wrong segment Clear grouping reduces misconfiguration risk Team onboarding Requires tribal knowledge Self-explanatory structure Segment auditing Manual scan of full list Folder-level review Priority / Urgency We are actively building this segmentation system now and will reach 150+ segments within the next quarter. Without folder support, we may need to delay segment creation or work around the limitation with inconsistent naming conventions alone. This feature would benefit any Intercom customer operating at scale across multiple regions, products, or customer types. Workaround Currently UsedStrict naming conventions ({COUNTRY} — {Plan} — {Role}) allow alphabetical sorting to group segments loosely by country. However, this does not solve the navigation problem for cross-cutting segment types (drivers, EMS, product-specific) and is not intuitive for new team members.Additional Notes We would also welcome a search/filter bar within the Segments list as a lighter alternative or complement. A tagging system for segments (similar to Intercom tags on conversations) could achieve a similar result and may be simpler to implement.

1

S

Forum|Forum|12 days ago

L

Laura CelentanoNew Participant

Fin on Messenger - customise the answer Fin gives (currently unable to)Submitted

I would love to be able to chose if and what Fin says once it's given an answer to a customer. It seems to default to 'was this helpful’ or ‘was this what you were looking for'. If you could ask your product team to make this a setting/personalised please.

0

L

Forum|Forum|14 days ago

J

Jeff CastonNew Participant

Fin learningSubmitted

The idea here is to allow Fin to “learn” from converstations that teammates have to take over on. The teammates answers should either automatically or perhaps with an option to “add to Fin’s knowledge” to allow Fin to learn from teammates answers. I know we can add snippets or add to existing knowledge articles, but this would really streamline the process. Maybe an option when you go to update the status of the ticket, you can “add to Fin’s knowledge.”

0

J

Forum|Forum|14 days ago

Justin DeanNew Participant

Store Temporary Attributes in Fin’s Conversation MemorySubmitted

Today, temporary attributes in Intercom are limited to the lifecycle of a single procedure. This creates friction in conversations that involve multiple procedures or handoffs, since any intermediate state is lost when switching contexts. To work around this, we currently promote short-lived data to permanent attributes, which introduces latency, adds complexity, and clutters our data model.We’re requesting a way to make temporary attributes persist for the duration of a conversation (i.e., session-scoped), so they can be shared across procedures without needing to be written to permanent storage. This would allow us to pass state more efficiently between workflows, reduce unnecessary read/write cycles, and improve responsiveness.A conversation-scoped attribute layer—automatically cleared when the conversation ends—would make it much easier to build fast, reliable, multi-step conversational experiences without compromising performance or data hygiene.

1

B

Forum|Forum|15 days ago

L

Luis AugustoNew Participant

Esperar a que el usuario termine de escribir antes de responderSubmitted

Actualmente Fin responde en cuanto detecta un mensaje, incluso si el usuario todavía está escribiendo varios mensajes seguidos. Esto puede causar respuestas incompletas o confusas cuando el usuario aún no ha terminado su pregunta. Sería útil que Fin detecte cuando el usuario sigue escribiendo y espere unos segundos (por ejemplo 30–60 segundos) antes de responder. Esto mejoraría la experiencia en conversaciones donde los usuarios envían mensajes en varias partes.

0

L

Forum|Forum|17 days ago

I

IlaydaNew Participant

Feature Request: Fin AI replies to everyone when multiple emails are in the "To" field (Huge Privacy Risk)Submitted

Current Behavior & Problem:We have configured Fin AI Agent so that it should only reply to the original sender of an incoming email. However, when an incoming email contains multiple recipients in either the "CC" or "To" fields, Fin AI ignores this setting and executes a "Reply All", automatically sending bot responses to every single recipient included in the thread.This behavior poses a severe data privacy risk for us. Fin AI might share account-specific data, resolution steps, or internal context with external third parties who were included in the "To" line of an incoming email, without explicit authorization to receive that specific response.Requested Feature / Fix:Fix the "reply only to sender" setting so that Fin AI strictly addresses only the single primary sender (From / Reply-To address).Ensure Fin AI completely ignores additional recipients in both the "CC" AND "To" fields during automated responses.This is critical for teams handling sensitive customer data over email. A fix or strict control for this would be greatly appreciated!

0

I

Forum|Forum|17 days ago

S

Sophie_TeamwhaleNew Participant

Add Telugu as a supported languageSubmitted

Hi Intercom team!We would like to request the addition of Telugu to Intercom’s supported languages, similarly to the existing support for Tamil.We serve a significant number of Telugu-speaking customers, and having Telugu available would help us provide localized support, configure the relevant language settings, and create a more accessible customer experience.Thank you for considering it!

0

S

Forum|Forum|17 days ago

C

CS AdminNew Participant

Optimize Idea submission with FinSubmitted

Whenever we contact Fin for support and there is no solution to what we are suggesting, why not make it so Fin searches this Ideas section automatically to help streamline submission and upvotes? Having customers leave the conversation with all the context to do this manually seems like a miss, especially for a company pushing AI first.

0

C

Forum|Forum|18 days ago

D

David CruzNew Participant

Speed in completing tasksSubmitted

Hello team,We were using the Operator to improve some FAQ articles, and it was able to identify some unique English-language articles that contained the word “participant.” Each of these articles has a Spanish-language equivalent, and all of them will need to be updated, but for some reason, updating this with the Operator takes way too long compared to doing it manually, so speeding up some processes would be required to save us some time and be more competitive.Thanks!

0

D

Forum|Forum|20 days ago

M

Meghan BeckerNew Participant

Have better data changelogs on Custom AnswersSubmitted

Currently we have no way of seeing a “last updated on” and “last updated by” or a historical change log on any custom answers and that is reporting we need access into.

0

M

Forum|Forum|20 days ago