AI + Workflows

Hi all, Assumption 1: an Admin created a Tagging Rule, which flags inbound messages containing a certain keyword as “urgent”. Assumption 2: a similar Topic leverages AI to identify “urgent” messages.  Assumption 3 : on the same mailbox, there is a Required Tagging rule, which forces the assignee resolving the message to tag it I’d be interested to see if it is possible to compare the Required Tagging final tag with the original tag and topic. This could help flag wrongly built tagging rules for instanceHas anyone ever created a custom report to do that?Or would you just export Tags/Topics Analysitcs report, feed them to Claude/Chat and ask it to compare with ticket ID? Thanks for your time! 

We're building a way for external AI agents to operate as real teammates inside Front — assigned conversations, their own identity, clean handoffs to humans, and @mention support. No more webhook workarounds or human accounts standing in as proxies. If you've already built an agent or are actively working on one, we want to hear from you. We're in early development and looking to understand real use cases before we build. Interested? Join our beta group to get started.

In regulated industries (lending, insurance, healthcare), who's allowed to handle a conversation often depends on something Front doesn't natively know - an active license, a coverage territory, a compliance certification - that lives in an external system of record. The pattern that's worked well for us: sync that external state into a Front custom field (e.g. an "Eligible" flag or region code) via API/webhook, then drive routing/assignment rules off the custom field instead of hardcoding teammate names or emails into rules. When the external system changes (someone's license lapses, territory shifts, roster changes), you update the sync/one field instead of touching a dozen rules. Curious how others are handling this: is anyone else routing based on data that lives outside Front, and if so, custom fields plus sync, or a different approach entirely (webhooks triggering direct API assignment, something else)?

Wondering how end users utilize the tagging function, in a group that manages a small-scale project for new retirement plan implementations to help manage outstanding tasks and timelines. Does it make the most sense to tag by client and use statuses? I was also thinking that tags for status or stage may be useful. What has worked for your team?

Has anyone connected Front to Planhat? If so, did you find that this connection was worth your time? 

Need to quickly check the status of a customer's flight without leaving Front? In this tutorial, we'll create a simple Sidebar Plugin that embeds a live flight tracking website directly inside Front, making it easy for support agents and travel teams to monitor flights while responding to customers.This example demonstrates one of the simplest ways to extend Front with custom tools. The same approach can be used to embed internal dashboards, booking systems, CRMs, status pages, and many other web applications.To get started, you'll need to be a Front admin (or ask your admin to follow this guide).Navigate to Developers and create a new app.Give your app a name, such as Flight Tracker, and upload an icon so it's easy to recognize later.Open the Features tab, click Add feature, and select Sidebar Plugin.In the Sidebar URL field, paste:https://www.flightradar24.comReplace this URL with the URL where you've deployed the plugin.For the component, select Clipboard.Click Create.That's it! 🎉O

Hi Front community, We successfully tested the MCP Server feature using OAuth and it works great. However, for our production use case we need this feature available for API Tokens as well.Our scenario: we are building a centralized MCP server hosted on our own infrastructure that acts as a proxy to Front's MCP, consumed by multiple support agents through AI assistants (Claude Code). The server needs to authenticate against Front without per-user OAuth flows.  The challenge with OAuth:  - The refresh token is tied to a specific user's identity  - If that person leaves the team or the token is invalidated, the integration breaks  - Managing token rotation in a server environment adds significant operational complexity  What we need:API Tokens with MCP Server feature enabled, so we can authenticate our server-side MCP proxy with a stable, long-lived credential that isn't tied to a specific user's session.This would be the ideal solution for teams building centralized MCP integrations on

Want to create word clouds from your Front conversations? This is a great way to quickly visualize the most frequently mentioned topics, pain points, issues, and positive feedback across your inboxes.To get started, you'll need to be a Front admin (or ask your admin to follow this guide). Navigate to Developers and create a new app:  Name your app and add a logo so its easily recognizable later: In the Features tab, click Add feature and select Sidebar Plugin: In the Sidebar URL field, paste the following url:https://dedarritchon.github.io/front-word-cloudand select the Clipboard component:Click create. We are all set. Go to your inbox, you should see your new Wordcloud app in the sidebar: Of course, the example was made with test data, but on real conversations it should show interesting facts about your customers.You can edit your resulting word cloud by tinkering with the settings.Hope this helps someone! If you tried it, Share your Wordclouds in the comments 😃 

 Now open: request access to the Amazon Connect beta (voice and SMS in Front) If your team is handling phone calls and texts in a different tool from the rest of your customer conversations, this one is for you. We just opened requests to join the beta for our Amazon Connect integration, which brings voice and SMS into Front alongside the email, chat, and everything else you already manage here. Once it is connected, you can place and receive calls, send and receive SMS, and pull up call recordings, transcripts, and AI summaries right in the inbox. The full history of a customer lives in one place instead of scattered across systems. This is a private beta and we are screening who joins, but if you are on the latest Professional plan or above and have a real voice or SMS use case, you are very likely a fit. You can preview the full setup steps in our Help Center. Want in? Request to join the beta group here.We will review and get back to you. Members get a dedicated space for updates a

Sharing a workflow in case it's useful. Our Client Services team supports clients across all US time zones, and we wanted to track SLAs on an 8 hour time frame. What we built:27 time zone inboxes across 12 teammate groups Custom fields (Time Zone Inbox, CSM Backup) to drive routing without hardcoding names into rules Mirror rules so conversations route to the right TZ inbox while staying visible in the team queueBiggest lesson: drive routing off custom fields, not teammate names in rules. When someone changes territory, you update one field instead of editing dozens of rules.

Hi everyone,I'm interested in hearing how other teams manage SLA tracking when supporting customers across multiple inboxes.Our team handles conversations from several channels, and one challenge we've been running into is maintaining consistent response times while balancing workload between team members. We've been exploring different approaches using rules, assignments, and tags, but we're still trying to find the most effective setup.A few questions for those who have already solved this: Do you track SLAs separately for different inboxes or use one standard across all customer communications? How are you handling reassignment when someone is unavailable or overloaded? Are there any Front automations you've found particularly useful for preventing conversations from falling through the cracks? I'd love to learn about any workflows, reporting setups, or best practices that have worked well for your team.Thanks in advance!

We have an automatic out-of-office reply switched on in Front for any inbound customer service enquiries. When a customer emails in, that auto-reply becomes the most recent message on the thread.When our AI agent then drafts a response, the Front connector replies to the latest message — which is our own out-of-office, not the customer's email. Because it's replying to our own outbound message, the draft has no recipient and no subject line, so it can't be sent.The fix we're asking for: have create_draft reply to the customer's last inbound message (not just the latest message of any kind) — or give us a way to point it at the customer's message directly. Any of those would let the draft inherit the right recipient and subject.

Hi everyone,We're reviewing our support workflow and have run into a common challenge: customers often reply to an old resolved email thread when they actually have a completely new request.Currently, when this happens, the conversation reopens in Front, but it can sometimes remain associated with the original owner or context, which makes triage more difficult and increases the risk of missing new work.We're considering a workflow that would:• Automatically detect replies to conversations that have been archived for a certain period of time.• Apply a tag such as "Reopened - Review Required."• Route the conversation back to an unassigned queue for triage.• Use analytics to track how often customers start new requests through old threads.For teams handling a high volume of customer support, logistics, or account management messages, how are you managing this scenario?Have you built rules or tagging structures that help distinguish a genuinely reopened issue from a completely new request

Hello everyone, My name is Jacob and I am about to take my test for admin certification!

Our CS org is about to transfer to Zoom phone, and it’s my understanding the Front <> Zoom integration focuses on video conferencing/scheduling vs. the phone app. Have any teams using both platforms come across recommendations on how to leverage the two systems together?

Hi everyone,I’m trying to figure out the best way to track performance for users who work across multiple shared inboxes.In our case, the user have access to analytics in more than one inbox, but reporting is still separated per inbox. I’m looking to understand if there’s a way to get a combined view of metrics like messages sent, reply time, and first response time across all inboxes user works in.Right now, it seems like the only option is to pull reports seperatly and combine them manually, which isn’t very efficient.Has anyone found a better way to handle this? Maybe through exports, integrations, or a specific workflow inside Front?Thanks in advance!

Hey folks,We started using the knowledgebase for internal tips and tricks about Front. I’m bringing in other team members to brainstorm how it can be used across our organization internally, and where it might also be useful externally. How are your teams using the knowledgebase? 

Hey all! Thinking through utilizing automation when possible while also giving the customer a positive experience. Where should teams draw the line between automation and personalized responses in Front, especially when dealing with sensitive logistics issues like lost or delayed shipments?

For those in logistics or similar high-volume environments:Are you routing by issue type, customer, or shipment status? Any best practices for avoiding overlap between ops and support teams?Would love to hear how others are structuring this.

Currently, Front lacks a native mechanism to "undo" a merge. Once two conversations are joined, whether manually by an agent or through automated threading logic, they are effectively locked together. In the fast-paced world of logistics, this creates a "Merged Entanglement" that poses four significant operational risks:• Mixed Shipment Data: If an email regarding Shipment A is merged into a thread for Shipment B, critical attachments or instructions can easily be overlooked. A single missed detail in our industry can lead to a stalled truck or a failed delivery.• Broken Analytics: Accuracy is the backbone of our operations. When two distinct business events are tracked as one, our "Time to Resolve" (TTR) and "Messages per Shipment" metrics become skewed, providing an inaccurate picture of team performance.We propose a native "Unmerge" feature that allows users to split conversations back into their original, distinct components. Key requirements include:1. Split by Message: A UI optio

Hi Front Community, Just a quick update for all Asana plugin users — we’ve added support for creating tasks using task templates 🎉 Task templates in Asana can be created by selecting “Convert to task template” from a task’s options (note: this feature is only available on paid plans).  Once your selected project includes templates, you’ll see a new field in the task creation flow. Choosing a template will automatically populate fields based on that template, helping you create tasks faster and keeping things consistent with your existing Asana workflows. This feature was requested here: https://front.aha.io/ideas/ideas/PRD-I-9755Let me know if you have any questions or run into any issues while using it.Best,Daniel

I am currently exploring options to connect external services not currently available in Front. We are aware of Front´s metric and analytic capabilities but will still need a bridge or integration. The application in question is Amplitude.Since there isn't a native integration or plugin, I’m curious how others are doing this. For those of you who have moved past Zapier/Make and into Custom Plugins, was it difficult to set up the connection? 

Currently, Front’s tagging system is proactive: it works perfectly for messages coming in after a rule is set. However, logistics is often about identifying patterns after the fact.We currently have to perform manual searches and use "Bulk Actions" to tag messages. This is time-consuming, prone to human error, and often misses archived or moved threads. As such our Front Analytics reports are incomplete for the first 14 days of any new issue, making it harder to provide our shippers with accurate historical data.We propose a feature that allows Admins to apply a Tag (or trigger a Rule) retroactively.1. Selection: Create a Tag or Rule (e.g., If body contains "Toll Increase" -> Add Tag "Finances").2. Backfill Option: A button that says "Apply to Historical Conversations".3. Time Parameters: A date-picker to define the look-back period (e.g., Last 30 days, Last quarter, or Custom Range).4. Background Processing: A status bar indicating the progress of the historical scan.Why this matte

You can now access 5 new templates in your workflows if you install the Asana and Salesforce integrations from our App Store. These integrations add rule and macro templates that let you take action in the Asana and Salesforce without having to build the Connectors yourself or start from scratch on the rules and macros. Simply load the rule or macro from the template library and customize from there! New rule templates Create lead in Salesforce Send task to Salesforce Send email to Salesforce New macro templates Create Salesforce opportunity Create Asana task To access these templates, go to your Settings, select a workspace or choose the Company level, and then click Rules and macros. From there, create a new rule or macro and look for the Connect section to find these templates.

Hey Team, Is there a way to setup domain based routing to multiple inboxes? Will each inbox receive a copy separately or is there a way to route a single copy to a inbox based on load balancing?