Product Wishlist

Christian OsmundsenNew Participant

Calculate recontact rate after (assumed) AI resolutionSubmitted

Hello Fin team,It's easy to go a little blind on resolution rates, since what really matters is what the customer believes is the truth. Fin will calculate an assumed resolution if a customer stops replying to the thread and leaves. Although this is quite common in the SaaS industry, it is also not a very safe indicator that the issue was in fact resolved. Even for confirmed resolutions, it may be that the customer thought it was perfect and confirmed, but later found that this was actually not the resolution anyway. To get a better picture of this, please consider this feature request for reporting:Any lead or user who does not only reopen a previous conversation (this can already be done in reporting), but opens a new conversation within X time (a variable that we should be able to select), is considered a recontact. The combination of AI resolution together with low recontact rate is dynamite, and far stronger than just showing off with a high AI resolution alone. Thanks,Christian Osmundsen, Deliverect

Forum|Forum|1 day ago

Ismael Martinez MoralesNew Participant

FIN Accelerated “inactive customer follow-up” timerSubmitted

For VIP/Ent customer email emergencies, the key is to avoid relying on the “inactive customer follow-up” timer, since email follow-ups are only configurable in hours (1 hour to 7 days). [1] [2]Request: to have more flexibility with the follow up timer and use minutes instead of hours.Use case: we want to add Fin also to handle Ent emails and if there's an emergency we can't wait 1 hour for Fin to escalate/hand off to our inbox.

Forum|Forum|1 day ago

Ben H.New Participant

Alerts when a procedure or data connector is marked unhealthySubmitted

Currently, monitoring the health of Data Connectors and Procedures requires manual oversight within the Intercom dashboard. If a sync fails or a procedure becomes "unhealthy" due to credential expiration, API changes, or server errors, there is no immediate notification. This lead-time between a failure and its discovery results in outdated customer data, broken workflows, and delayed responses to end-users.I would like to request an Alerting System that proactively notifies admins when a Data Connector or Procedure changes status from "Healthy" to "Unhealthy" (or "Failed"). Ability to receive alerts via:Intercom In-app notifications. Email (sent to specific workspace admins). Slack/Webhook integration.Granular Alerting: The ability to toggle alerts on or off for specific connectors (e.g., alert me for Salesforce sync failures, but ignore minor sandbox procedure errors).Failure Context: Notifications should include a brief summary of the error (e.g., "401 Unauthorized" or "Schema Mismatch") to allow for faster troubleshooting.Auto-Recovery Alerts: (Optional) A follow-up notification when a connector returns to a "Healthy" state.

Forum|Forum|1 day ago

Belén De AngelisNew Participant

Version history & save notes for Escalation GuidanceSubmitted

Guidance sections support version history and save-time notes, but Escalation Guidance doesn't. Would be great to have parity — these features are useful for tracking changes and context.

Forum|Forum|2 days ago

Marie BaierNew Participant

Search bar in Recommendations tabSubmitted

Hey team :) Adding a keyword search feature in the Recommendations tab, similar to the one available in chats, would make it much easier to find relevant content. At the moment, recommendations can only be filtered by topics, so if a specific topic is not yet listed, we need to manually scroll through all recommendations to find what we are looking for.

Forum|Forum|2 days ago

ImmortalNew Participant

Global Behavioral Rules for FinSubmitted

We’ve noticed a limitation in how Fin handles instructions when support logic spans multiple categories or requires conditional behavior.Currently, instructions are expected to fit neatly into isolated sections/intents. However, some support scenarios require layered logic that combines:topic classification, policy enforcement, escalation restrictions, conditional responses, and fallback behavior.A good example is our “custom code” support flow.In this case, we need Fin to:recognize requests related to CSS, PHP, JS, SQL, regex, or custom code in general; clearly explain that these cases are outside standard support scope according to our policy; still attempt to help when possible; avoid suggesting escalation to a live agent if Fin cannot solve the issue, because the live support team follows the same policy and cannot provide custom coding assistance either; only address escalation if the customer explicitly requests a human agent; and in that case: remind the customer about the policy, explain that the live team has the same limitations, and suggest alternative resources such as community help or custom development services. Right now, Fin tends to:split such logic across multiple sections, recommend restructuring instructions into separate categories, or fall back to default escalation behavior.This makes it difficult to implement nuanced support policies where:the topic, escalation behavior, and communication strategy must stay connected within a single instruction flow.

Forum|Forum|3 days ago

Mor CohenNew Participant

Workflow trigger when a tag is addedSubmitted

It would be really nice to have a workflow trigger when a tag is added to a conversation

2

Forum|Forum|4 days ago

CoryNew Participant

SLASubmitted

Provide the ability to edit SLA’s instead of archiving and creating a new one.

Forum|Forum|6 days ago

E

Eva MowinNew Participant

making the floating text editable for Fin for Sales.Submitted

We are using Fin Sales Agent on our website, and the default floating text currently says “Need help?” (or the Swedish equivalent, as shown in the screenshot).Since Fin is being used in a sales role, we would like the wording to better match a more sales-oriented and conversational tone.It would be great if this text could either be customizable by us, or updated to something more suitable for sales interactions, for example:Have a question? Looking for something? Want to know more? Need help getting started?Right now, “Need help?” feels more support-oriented than sales-focused.

1

U

Forum|Forum|9 days ago

Clémence LiquoisNew Participant

Automatic Translation of Help Center ArticlesSubmitted

Today, it is possible to easily translate content within conversations. However, the translation of Help Center articles is still not automated.This limitation creates a significant workload, especially when managing multiple languages in the Help Center.In the age of AI and given the rapid evolution of your tools, it feels surprising that automatic translation of Help Center content is not yet available. Introducing this feature would provide major benefits in terms of time savings, consistency, and overall efficiency.

3

Forum|Forum|9 days ago

A

alexheidiNew Participant

A/B testing for proceduresSubmitted

We're rolling out Procedures gradually to protect quality, which means we need a way to measure the impact of a Procedure on resolution success before expanding its scope. Today the only way to control which conversations a Procedure runs against is to gate it on a customer attribute (e.g. user segment, plan type). That introduces cohort bias: the two groups experience the product differently to begin with, so we can't isolate the effect of the Procedure itself. The comparison isn't apples-to-apples.Request:A native A/B test mode on individual Procedures, where:- Fin randomly assigns eligible conversations to treatment (Procedure runs) or control (Procedure doesn't run) at a configurable split.- Eligibility is defined by the Procedure's existing trigger conditions, so randomisation happens *inside* the qualifying topic space rather than across unrelated cohorts.- Reporting shows a 1:1 comparison of outcomes between the two arms: resolution rate, CSAT, handover

A

Forum|Forum|10 days ago

Cody WebbNew Participant

Need ability to cancel a external website syncSubmitted

Under Train > Content, need ability to stop a sync. At present, must wait for it to finish, so if an error is noticed, sometimes you have to wait hours before you can make the correction and kick off the sync again.

Forum|Forum|10 days ago

Connie KruegerNew Participant

All for Custom Attributes to be set in Batch TestingSubmitted

I have an Escalation Rule that is built on Attributes but it’s causing issues with batch testing as attributes are not set. I can not use an Audience as that is already needed in my batch testing to control the KB. Ideally you allow us to set the attributes before triggering the batch testing as you allow in simulations.My escalation rule is Attribute is not [name] and Attribute2 is not [name2]. This allows me to use FinAi for new use cases and then escalate to an existing nonFinAi workflow for existing use cases. Over time we will move all to FinAi but that is not possible right now. This escalation rule is built on Attributes so why is there no solution for batch testing? I will try creating a test user with the attribute set as a workaround. That will then require everyone to use this test user and that is not ideal.

Forum|Forum|10 days ago

TrevorInnovator ✨

Fin Ai Agent Access to Tracker Tickets for SMART bug Categorization, handling, and communicationSubmitted

The Problem:We have bugs that arise, just like any other tech company. We’re constantly innovating and pushing updates, and therefore encounter unexpected issues. We typically fix widespread issues and outages very quickly. And we link all customers to a tracker ticket. Fin spends way too much time blindly leading a customer through troubleshooting steps, when there’s a deeper issue Fin is unaware of. How we solve today:It takes a lot of effort to create a snippet, and create guidance for the snippet, to quickly train Fin on a known issue. And then that guidance and snippet has to be manually deleted hours or days later when the issue is resolved. It’s constantly evolving, requiring multiple steps. We create tracker tickets to inform customers and human agents of the progress of issues like this. So I’m training my agents and Fin separately, in two different places. The Dream Scenario: Awareness: Fin is aware of all active Tracker Tickets logged by human agents. Mitigation: Fin automatically offers a workaround to the customer if one is documented. Proactive Subscription: Fin asks the customer if they would like to be notified of updates regarding the bug. Automation: Upon confirmation, Fin automatically links the conversation to the Tracker Ticket and converts the conversation into a customer ticket. Persistence: Fin remains the primary point of contact unless the issue requires human escalation. Resolution Loop: When the Tracker Ticket is marked "Resolved," Fin proactively follows up with the customer to confirm the fix is working for them. Proposed Implementation in IntercomTracker Ticket Settings Add a "Sync to Fin AI" toggle on Tracker Tickets (or enable this by default for specific Ticket Types). When enabled, provide specific AI-optimized fields: Symptoms: Describe what a customer would experience (to help Fin match the issue). Workarounds: Step-by-step instructions for Fin to provide. Target Audience: Specific conditions or user segments impacted. Auto-Link: Toggle option to allow Fin to automatically link users to a Tracker Ticket. Auto-Ticket Creation: Toggle option for Fin to generate a linked conversation ticket automatically upon bug identification.

1

S

Forum|Forum|11 days ago

BekaNew Participant

Custom VoicesSubmitted

I’d like to be able to customize the voice that is used to request a CSAT rating on phone calls. Right now it’s just a default voice and it isn’t even the voice you choose for FIN. At the least I’d hope for continuity between the voice you choose for FIN and all other voice automations throughout the product.

Forum|Forum|15 days ago

John BeynonNew Participant

Option to hide 'Fin Attribute' reasoning private commentsSubmitted

I’d love the option to be able to set Fin attribute reasoning to be hidden, or perhaps follow the “Show conversation events” flag, We have several attributes and it can be quite noisey.

1

Forum|Forum|15 days ago

Thomas HilsNew Participant

Additional configuration options for email codes on Data ConnectorsSubmitted

When using an email code for data connectors I’d like to be able to configure two options: Choose the time out window myself Automatically communicate the time out window (regardless of whether it’s custom or not) to the customer whenever the security code is invokedA 10 minute window is very short and customers are often stuck in a loop requesting new codes over and over. This could be off-set with a longer window, and better communication about these timeouts. It seems like an industry norm to communicate time out windows by default and it’s strange that this isn’t done.

Forum|Forum|16 days ago

Daniel FosterNew Participant

Ability to choose which knowledge folders the content team can editSubmitted

Ability to choose which knowledge folders the content team can edit. We need to decrease risk by giving content editors access to edit ALL knowledge articles in a workspace.

Forum|Forum|17 days ago

Daniel FosterNew Participant

Change publication defaultsSubmitted

Ability to make fin toggle disabled as default for newly published content.

Forum|Forum|17 days ago

Mads EgmoseNew Participant

Fin AI: draft email replies for human reviewSubmitted

ProblemFin handles chat well — short turns, fast iteration, low downside if a reply needs a follow-up. Email is a different beast. Threads are longer, context spans days or weeks, and the stakes are higher: customers expect a considered, accurate response, and a wrong reply is much harder to walk back than in a live chat.That makes full autonomy a poor fit for most email conversations. But it doesn't mean Fin can't help. Right now, the gap between "Fin resolves it autonomously" and "agent writes from scratch" is too wide for email — there's nothing in between.ProposalWhen a new email arrives, Fin generates a draft reply using:- The full thread context- Connected knowledge sources (help center, macros, past resolved threads)- Brand voice and tone settings already configured for FinThe draft sits in the conversation ready for an agent to review, edit, or send. A confidence indicator and visible source citations would let agents verify in seconds rather than re-researching the answer.Why this is valuable- Cuts response time without giving up the human-in-the-loop check that email genuinely needs.- Captures Fin's value on conversations that today are 100% manual.- Creates a feedback loop: agent edits become signal for improving future drafts, and eventually for moving simpler email categories toward autonomous resolution.Use caseWe run a marketplace where most supplier-side conversations happen over email. They're rarely fully automatable, but most of what we write is a variation of something we've written before. A Fin draft would save the majority of the writing time per reply while keeping us in control of what actually ships.

Forum|Forum|18 days ago

T

Tom JNew Participant

Please fix CSAT UXSubmitted

I was digging why only few of our conversations have actual CSAT rating and I believe the reason is the terrible UX.When the question is asked, only smileys appear which makes you think one click and that’s it. But no, once you click on the smiley the text input with additional arrow appear, but they are in the inactive state so user has no idea he needs to actually click on the arrow. The rating is submitted ONLY when the grey arrow is clicked.Can someone please improve this or allow us to customize this form? Thank you.

4

Forum|Forum|18 days ago

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

Forum|Forum|19 days ago

G

Gerald PradoConnector

Ability to fine tune when the Let Fin Handle block should send follow ups for inactive customers.Submitted

Currently within the Let Fin Handle boxes there is the option to Follow up with inactive email customers. But we don’t have a way to fine tune which interactions Fin should follow up with. As an example, if a customer has had a conversation with Fin where all the possible options have been exhausted and the customer has stopped replying, we want to give Fin guidance to not reply if there is a specific conversation topic (attribute) that has been detected. We want Fin to be able to send the follow up as needed, but want to be able to give Fin some instruction to NOT follow up based on a topic, or guidance. At the moment it is either on or off.

G

Forum|Forum|21 days ago

V

visharadNew Participant

Interncom X OpenUISubmitted

Hey everyone! I’m Visharad, one of the maintainers of openui. We are doing some really fun stuff with generative UI. Would love to connect and collaborate with folks here and contribute to the community!https://www.openui.com/

V

Forum|Forum|21 days ago

RoyTop Expert ✨

🚀 Feature Request: "Direct API Mapping" for FinSubmitted

The Problem: Currently, setting up Fin Data Connectors is a high-friction process. For every action we want Fin to take, we have to manually: Create a new Connector. Define the endpoint. Manually map and explain each data attribute so Fin understands it. This significantly increases the "Time to Value" for Fin. If I have a complex B2B API with 50 endpoints, it takes days to set up, rather than minutes. ⏳ The Solution: Introduce a "Bulk API Mapping" feature. Instead of manual entry, allow us to provide a URL to our API Documentation (or upload an OpenAPI/Swagger JSON/YAML file) and the Global Authorization headers.How it would work: Doc Ingestion: Fin "reads" the documentation and automatically maps the available endpoints. Semantic Understanding: Since modern API docs are well-designed, Fin can use its native LLM capabilities to understand what each endpoint does without us writing a manual "explanation" for every single one. Global Auth: Set authorization once at the root level rather than per-connector. Selective Enabling: A simple toggle list where we can "Turn On" specific endpoints for Fin to use as Tools. Why this is a game-changer: ⚡️ Drastically Reduce Start Time: We could go from "Zero to Integrated" in minutes, not days. 📈 Scale Automation: It encourages teams to give Fin more "powers" because the cost of adding a new capability is nearly zero. 🛠 Improved Accuracy: Professional API documentation is often clearer than a human's manual summary, leading to fewer hallucinations during tool calls. Let’s move Fin from a "manual data connector" model to a "plug-and-play architect" model! 🇬🇧💪#IntercomFin #ProductFeedback #FeatureRequest