Share product ideas and upvotes with our product team
It would be awesome if when you go to reply Fin has already had a go and then you can either accept it and tweak/send or start typing to override.
I love the monitor function for ticket QA, however, it is currently very focused on leveraging AI for ticket selection. While I appreciate that feature for investigative QA, when it comes to release QA, it would be nice to have the ability to have increasing filter options, so you can model ticket selection to your reports.f.e. I would like to filter monitor ticket selection to pick up tickets with specific Fin AI attributes.
Currently, Fin's content recommendation feature analyzes conversations of any age when suggesting article edits, including conversations that are a year or more old. For fast-moving products where features and functionality change frequently, this leads to outdated and incorrect recommendations.Request:Add a setting to limit the age of conversations that Fin reviews when generating content recommendations. Ideally, this would allow us to restrict recommendations to conversations from the past 6 months (or a custom timeframe).Why this matters:Recommendations based on year-old conversations suggest edits that no longer reflect current product functionality This creates extra work reviewing and dismissing irrelevant suggestions For products with frequent updates, only recent conversations provide actionable insightsExample:I recently received a recommendation to edit a help article based entirely on conversations from approximately one year ago. The suggested changes were completely incorrect because our product has evolved significantly since then.
Currently, when a ticket is in Waiting on customer, any reply from the customer automatically changes the ticket state back to In progress. In many cases the reply doesn’t actually unblock the ticket. For example, a customer might say “Perfect, I’ll send the file tomorrow” or “I’ll book the meeting later today.” Even though the required information hasn’t been provided yet, the ticket still moves to In progress automatically. It would be very helpful to have an option to disable this automatic state change, so the ticket can remain in Waiting on customer until a teammate updates it manually. This would make ticket workflows clearer and prevent tickets from returning to active queues before the needed information is actually received. We use Intercom in our app to onboard customers and guide them through a process with our team, and ticket statuses are an important way for both sides to understand where we are in that process.
It is increasingly common for websites to not just have a sticky chat bubble, but to embed fin on a specific location on a web page.Features: Insert Fin by URL targeting on a page Ability to adjust prompt based on attributes or URL Some customization around UXExamples Include: Amazon Product Pages “ask a question” SimpliSafe “ask about this product Walmart/Target are testing out similar features Expedia
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.
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.
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.
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.
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.
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.
Ability to make fin toggle disabled as default for newly published content.
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.
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.
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
Already have an account? Login
No account yet? Create an account
Enter your E-mail address. We'll send you an e-mail with instructions to reset your password.