Share product ideas and upvotes with our product team
Right now, when Fin pauses for a teammate approval in the loop, the teammate’s decision or response helps Fin finish that conversation, but it doesn’t appear to improve Fin’s future answers.It would be very valuable if Fin could learn from those approvals over time, in two ways:Approvals as confidence: when a teammate approves a draft as-is, that should raise Fin’s confidence on similar questions, so it pauses less often as the evidence builds. Corrections as learning: when a teammate edits a draft or provides the correct information, Fin should use that to improve similar responses in the future.For example, if the same question has been approved several times, Fin could eventually answer it without pausing. That means fewer interruptions for the team and faster responses for customers.This would make the loop not just a safety step, but also a real training signal for Fin.
Ku Coin is an exchange company built by HusainiCompany
I’d love to share a product suggestion regarding reporting and exports for Outbound Messages (including Chats, News, etc).Current Experience:When I click into an individual outbound message, the performance overview and engagement chart are super helpful for tracking how the message is landing. However, there isn't a way to cleanly export this view. Currently, I have to manually take screenshots of the page to share performance updates with my team and stakeholders. What I’d Love to See:The ability to export an individual outbound message’s performance report directly from the message view. Ideally, this would include:A visual export (PDF or PNG): Capturing the engagement chart alongside the top-level summary metrics (Sent, Opened, Clicked, Replied, Goal completion) in a clean, presentation-ready format. A data export (CSV): Allowing us to pull the underlying time-series data from that chart (e.g., daily opens, clicks, and replies over time) rather than just raw user-level CSV exports.Why This Matters:Having a one-click export for individual message performance would save a lot of manual effort when putting together weekly/monthly stakeholder reports, comparing campaign performance across time, and archiving results without relying on cropped screenshots.
Summary:Manual reviewer notes added to conversations within a Monitor should be exportable, either via the Dataset Export (CSV) or surfaced in the Reporting API, alongside scorecard scores.The problem:When manually reviewing conversations in a Monitor, reviewers can add qualitative notes to explain their scoring decisions. These notes are currently only visible within the Monitor UI, one conversation at a time, and can't be exported via CSV, the Reporting API, or S3 export.This creates a noticeable gap: the qualitative insight that gives context to scores, the why behind a pass or fail, is trapped behind individual conversation views. To extract patterns, a reviewer has to manually open and copy notes from each conversation, which isn't realistic at scale.What I'd expect instead:Reviewer notes should be included in the Dataset Export (scorecard_evaluation or scorecard_attribute_evaluation datasets) as an additional column, and ideally also surfaced via the Reporting API so teams can build dashboards or send data to external tools.Even a basic bulk export, such as a CSV of conversation ID, attribute, score, and note, would make a meaningful difference for teams using Monitors for structured QA workflows.Impact:Without exportable notes, qualitative QA analysis at scale just isn't practical. It limits Monitors to surface-level pass/fail tracking, rather than the richer insight tool they're designed to be.
Problem: Operator drafts content that doesn’t fit the content type. In snippets, it writes “the customer” instead of “you,” so the copy isn’t customer-facing. It drafts escalations into snippets, which can’t escalate. It puts guidance in the wrong category. It merges guidance that should be two separate items into one. Request: Make Operator aware of the purpose and constraints of each content type (snippets, guidance, procedures) so its drafts need less correcting.
We need Fin audiences for the Macros so Fin can use macros as source of knowledge by Audience.
Building a reliable Fin AI agent and Outcomes means testing more than the happy path. We need to know whether Fin follows the right procedure, asks for missing information, handles exceptions, and hands off when it should. We also need to know whether a change that fixes one workflow breaks another.Today, Preview is useful for debugging a single conversation, but running tests one by one takes too much time. Evals help with batch testing, but their scope and run limits make it hard to test several workflows together, give each workflow its own success criteria, and rerun the full set after every change.I’d like Intercom to add a built-in sandbox enviornment where teams can:Test safely. Run draft configurations against simulated conversations without contacting customers or triggering live actions. Simulate tool responses, failures, and handoffs. Batch test across workflows. Run refunds, onboarding, and escalations in the same batch, with separate success criteria for each scenario. For example, a refund test should pass only if Fin verifies eligibility before attempting the refund. Run QA automatically and without limits. Generate test cases from Procedures, save them as reusable suites, and rerun them on demand, on a schedule, or whenever the configuration changes. Sandbox runs should be free and unlimited, with no monthly quota on simulations or evaluations. See what passed, what failed, and why. Show success rates by workflow and criterion, compare results with the published configuration, and link each failure to the conversation and the step where Fin went off track.The goal is to make QA part of building rather than another feature that has a financial barrier. Before publishing a change, I want to run the full regression suite and see whether Fin follows our protocols and achieves the intended outcomes. We should be able to do that after every meaningful change, as often as we need without limits.
Fin Releases are amazing. We’re using them for app updates and large releases. Two big requests that would help us out a lot:Scheduling a release to automatically publish on a specific date and time. Articles within a release, accessible via the existing Articles API or content API or CL tools. Context: We’ve staged 15+ article changes into a Fin release. The articles now have unpublished drafts that are in the release environment. My teams and tools used to translate these articles into all languages, can’t currently pull the article HTML for these staged drafts. So it means using an external AI tool to publish and manage our html files on our end, and push them to intercom. Instead of using operator to help update articles and keep things in alignment. Because when we have local copies of the HTML and edits we’ve made, we can easily share that internally, and get translations for all done very quickly.
I would like the follower notifications be shown as a mention, with the red dot, not only via email. Thanks!
We currently have users requesting video tutorials. We’ve added a tutorials section to the Intercom help area, but right now it either just mentions the video or gives a number for the article. It would be a lot cleaner if Fin could also just show the video in the chat, or even link directly to the video itself without showing a number pointing to an overall article.
We would love to analyze and update workflows and Fin training setup through API, but this does not seem possible currently.Could you include this, or create a separate API for broader setup access? Or let me know, if I just missed it, if this is already possible.
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.
Customers are looking for more control over how their support requests are identified and described. Currently, the Title and Description fields are either generic or populated using AI-generated content from the conversation. They would prefer the ability to manually provide and update these fields after the ticket has been created.
Right now the Intercom API and MCP connector can create, read, and search Help Center articles, but there's no way to work with Knowledge Hub internal articles. We'd love to see internal articles supported the same way.When trying to build a skill that creates Internal Articles for team use only, Claude tells me that The Intercom connector has no way to make internal articles, only public ones.
The customer propose an UI change for the very first lead message inside Fin chat to the intercom team? Now for leads the e-mail can be required, which is good, but it is not telling WHY the lead cannot send the message when the e-mail is not typed in. Adding some red asterix to the form for e-mail address might solve this confusion.
Problem to Solve:We still have people that are AI-adverse, so there are some instances that we’d like to be able to send a form for the customer to fill out since it has drop down options and other things that work better for people that don’t want to go back and forth with AI. Right now it doesn’t look like we’re able to have Fin send a form using procedures, it looks like it has to be built as a workflow and then the procedure fires off that workflow. Seems counterintuitive instead of it just being able to send a ticket the same way it’s able to handoff to ticket.Request:Add the ability for Procedures to be able to send a black ticket for customers to fill out.
We would like to request the ability to configure role-based knowledge visibility within Intercom Copilot, allowing administrators to control which knowledge articles and guidance are accessible to agents based on their support tier, team, or role.Business ContextOur support organization operates within a tiered escalation workflow. Tier 1 agents handle initial troubleshooting and workflow steps before escalating to Tier 2 agents, who continue the process and follow additional guidance.As we scale our knowledge base and AI-assisted support workflows, we need to ensure that Copilot surfaces the appropriate guidance based on the agent’s role and responsibilities.We would like to understand whether Copilot can distinguish between agent tiers and restrict the retrieval or display of content accordingly.Requested FunctionalityWe would like the ability to: Configure knowledge articles or content sources to be accessible only to designated agent roles, teams, or support tiers. Restrict Copilot from surfacing Tier 2-specific guidance to Tier 1 agents. Dynamically tailor Copilot responses based on the agent’s role and escalation stage. Maintain a centralized knowledge base while supporting different levels of guidance and access. Expected Benefits Ensure agents receive guidance appropriate to their responsibilities and workflow stage. Reduce the risk of agents receiving instructions intended for higher-tier specialists. Improve the accuracy and relevance of Copilot responses. Support scalable knowledge management and AI adoption without duplicating content across multiple knowledge bases. Strengthen governance and control over AI-generated guidance. Example Use CaseA Tier 1 agent is working through an escalation workflow and asks Copilot for the next step.Copilot should surface only the guidance relevant to Tier 1 responsibilities and the initial troubleshooting process.Once the conversation is escalated to a Tier 2 agent, Copilot should be able to surface the additional guidance required to continue the workflow.
When Fin is deployed over E-mail there is a DMARC security (setting) before Fin will answer to the e-mail. In my case; like 20-30% of the incomming e-mails aren’t getting answered because of this problem: "Fin did not try to answer because the sender could not be authenticated"Fin escalates the conversation immediately, even when Fin could answer the e-mail so easily. Right now, there aren’t any options to troubleshoot this problem or any triggers to solve it automatically. So my question is: Can you guys find a way to automate the process what fixes the error and so can Fin the e-mail that was sent in the first place?
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.