Tips from the Intercom Team

When using collapsible sections in your articles, consider repeating the core question of your FAQ (Frequently Asked Question) within the answer itself.  This significantly helps AI agents like Fin more accurately find and utilize the relevant content for their answers. It's a handy trick to optimize your FAQ sections for better AI performance!

Want to use conversation data attributes but you’re not sure how they can help stay organized and keep track of important information in your conversations?We got you covered! 🤝 In this video, we’ll walk you through how to create and use them using real examples and use cases.You’ll learn how to:1. Set up conversation data attributes from scratch.2. Apply them inside a conversation manually.3. Automate their use with Macros, Basics, and Workflows to capture key data points from customers upfront and route conversations based on your criteria.5. Organize these attributes with Views in your inbox.6. Report on them to gain valuable insights. If you found this helpful, let us know how you intend to use them to inspire us and others! 🚀

One of the easiest ways to improve how Fin handles conversations is to use if–then logic in your Guidance. It helps Fin understand exactly when to apply a response, and what that response should look like.Here’s a simple example:"If a customer asks how to change their password, tell them to click 'Forgot password?' on the login screen and follow the steps."That’s much clearer than:"Explain the password reset process."By adding a condition (“if a customer asks…”) and a specific action, you give Fin a clear playbook to follow. It also helps prevent Fin from jumping in with the wrong response in unrelated situations.To take it further, you can include a direct link to your help center or a relevant support article. This makes it even easier for Fin to guide customers to the right place, without needing to explain every detail.

On the surface, it can seem that Copilot is a simple yet powerful tool that helps your team answer customers questions. But, it’s so much more than that!We've been using Intercom’s Copilot across our team and it's been a game-changer for us. If you're not using it to its full potential yet, here’s a quick breakdown of some ways to use Copilot you may not have thought of that help streamline work and boost efficiency:Faster Onboarding for New AgentsNew joiners no longer need to ping senior teammates every five minutes. Copilot acts like a super-smart buddy, guiding them with internal resources and examples from previous chats. It’s drastically shortened our onboarding ramp time.Internal Process GuidanceWhenever someone has a “how do we do this again?” moment, Copilot jumps in with answers sourced from our internal articles and documentation. It’s perfect for navigating complex or frequently changing internal workflows.Major Time SavingsBy aggregating info from external knowledge bases (

Since it was in early beta we have been using the AI Summaries feature in our Intercom workspace and it’s proven to be a massive time-saver for our support team. Before this, whenever a teammate picked up a conversation after Fin handled it, they had to scroll through everything to understand what had already been covered. Now, Intercom generates a quick, clean summary at the point of handoff from Fin in an internal note.It’s a small change with big impact—no more duplicated steps, no more “Let me check what’s already been said,” and a much smoother handoff between Fin and our human teammates.🛠 How to enable it in your workspace: Go to your Workflows page Go to one of your existing triage workflows or create a new workflow In the path (or before) you are assigning to an inbox, add the “Add summary note” action Done! The summaries will automatically appear as internal notes at this point in the workflow so when a teammate picks up the conversation, they have all the context they ne

Here’s something that’s easy to overlook: Fin isn’t reading between the lines. It’s taking your guidance literally, so the simpler and more specific your language, the better the results.We’ve all written something like:"Be friendly and professional."It sounds good, but it’s open to interpretation.A clearer version might be:"Use a professional yet warm tone. Keep responses short and avoid jargon. When a customer is frustrated, acknowledge the issue and say something like, ‘I understand how that can be frustrating. Here's what we can do.’"This type of Guidance gives Fin a clear tone to follow and reduces guesswork. It also helps keep responses consistent across your support experience.Think of it like coaching a new team member. If you wouldn’t rely on vague tone tips when onboarding a new agent, don’t use them with Fin either.

A lot of us naturally default to vague guidance like,"Make sure Fin understands our product types."But Fin thrives on clarity. A stronger version might be:"If a customer asks about the 'search' feature, first ask which product they’re using. Then give product-specific instructions."See the difference? That second version gives Fin clear steps and a condition under which to act. It's specific, it's actionable, and it’s something Fin can consistently follow.When you're writing guidance, ask yourself: what should Fin say first? What should happen next? That simple shift in thinking can make your guidance 10x more effective.How do you typically plan out what Fin should do in different scenarios?

Tip: One of my new weekly rituals is using the AI-powered Suggestions feature to improve our knowledge base - and it's incredibly satisfying.Before this feature, most content improvements happened when a teammate noticed a problem, took the time to submit a Back-office ticket, and someone else followed up to make changes. That worked... when it happened. But it often didn’t.Now, Suggestions does the heavy lifting. It automatically looks at where Fin may have stumbled in a real conversation and recommends a fix (like editing an article or adding a snippet). I review them once a week while waking up with a coffee, and approve about 70% with just a few clicks.After you’ve deployed Fin, head to Fin AI Agent > Train > Suggestions. You’ll see AI-generated recommendations for improving your content, with links to the original conversations so you can double check the context. It’s honestly one of the fastest ways to boost Fin’s performance without chasing down feedback manually!

Currently when you add the “Notify Slack Channel” action to a Workflow step, it doesn’t allow you to customize the notification which isn’t to great when you want to send a specific message or include data pertinent to the user. Well... with the use a Data Connector, you can create your own custom Slack notification!  1. Set Up a Webhook in SlackFirst, create an incoming webhook in Slack:Go to your Slack workspace and click on your workspace name Select "Settings & administration" → "Manage apps" Search for "Incoming WebHooks" and click "Add to Slack" Select the channel where you want messages to appear Click "Add Incoming WebHooks integration" Copy the Webhook URL (you'll need this later) Optionally customize the name and icon for your webhook2. Create the Data Connector in IntercomNow set up the connector in Intercom:In Intercom, go to "Settings" → "Data Connectors" Click "Create new data connector" Choose "Custom" as the connector type Name your connector (e.g., "Slack Notificat

Tip: Product releases can significantly affect what Fin needs to know to respond accurately to customers. Here’s a simple process to keep your content aligned and Fin informed: Create a tag: Start by creating a tag like "[Feature name] content updates". Search & review: Search the Knowledge Hub for content related to the release. Open top results and assess if they need updates. Apply the tag to anything that does. Filter & collaborate: Filter by your tag to create a list of all impacted content. Share this view with teammates to divide and conquer updates. Prepare drafts: For public articles, save updates as drafts ahead of the release. Publish in one go: When it’s time to ship, filter by your tag + status “Published with pending draft”, then bulk publish to go live in one click ⚡️ Fin will instantly have the most accurate, up-to-date content to handle any inbound conversations confidently and correctly.

Tip: Use simple, specific language that mirrors the words your customers actually use. Avoid technical jargon or internal terms—Fin works best when articles match how users naturally phrase their questions. For example, say “log in” instead of “authenticate” to improve understanding and AI searchability.You can red more about it here.

Tip: Enhance the clarity of your help articles by restating user questions within the answers. Instead of a simple “Yes” or “No,” provide full-sentence responses that mirror the user’s query. This approach not only aids AI comprehension but also ensures users receive precise and context-rich information. For instance, if a user asks, “Do I need to use the original shipping box to return an item?” Rather than replying with just “No,” elaborate with, “You can use your own packaging when sending an item back for a return or exchange; there’s no need to save the original shipping box.”  By adopting this method, you make your support content more accessible and effective for both AI agents and human readers. You can read more about it here.

Hey there! Ebenezer here from Engineering Support👋.We get a lot of questions on how to “Pass a Company ID over in a Conversation”. While Company data doesn't get stored in the Conversation Object, there is a way to do this!☝😎First, you'll need to create a Conversation Data Attribute that stores the specific value that you're looking to access.Next, Your team will need to perform several calls to our REST API to get the ball rolling. Initially, they would Retrieve a conversation and then locate the value for  source.author.id. This value will contain the ID of the person who initiated the conversation.A little side note; You’ll want to verify that the source.author.type is "user" for those conversations. If it's "admin" then that ID will be for a team member on your workspace who started the conversation. In these situations, you will want to dig into the conversation_parts attribute to see who the actual customer is.Once you have the ID of the User, you will then want to make a call

Hey Community!  👋 It’s Noor here from the Customer Education team at Intercom.I wanted to share a helpful tip that’s made a big difference for our customers at Intercom, which is to"Prevent Customers Reopening Closed Conversations". It’s a simple setting that can really clean up your reporting and make your support process smoother. 🚀 This setting can be found in your Messenger settings, under the Control Inbound Volume section. By preventing customers, or visitors, from reopening closed conversations, you encourage them to start new ones for each new question.  Why is this important or how is it going to benefit your support workflows?It keeps separate customer queries from getting mixed up, making it easier to track how long it takes to resolve each problem. When different issues are combined into one conversation, it messes up your reporting and makes it hard to see how long each specific issue takes to handle.It saves your agents time. They don’t have to figure out if a new quest

Hi Intercom Community! We’re back with another Intercom Quick Win, and this one’s about managing SLAs. 🚀 Have you noticed your conversations going out of SLA before your agents even have a chance to catch up on the thread or greet the customer? This often happens because the time customers spend interacting with Fin AI Agent or going through a Workflow counts towards your SLA. Here’s a simple fix: set up a separate Bot Inbox in your Automation Settings. This way, any conversation that starts with Fin AI Agent or a Workflow will appear in a separate inbox. Your SLAs won’t start ticking until the conversation is assigned out of that inbox and into the right hands. By turning on this separate bot inbox, you can also exclude the time customers spend with Fin AI Agent or in a Workflow from your reporting. This gives you a clearer picture of how long it really takes for your agents to respond and follow up. Check out this 1-minute video to see how it works, or follow along with our help gui

Hey Support Leaders 👋 I’m Michelle, and I’m a Support Manager here at Intercom.  I wanted to share some insight into something we’ve been working on within our Support team over the last few months that I think might be useful to others across the industry. With customers all over re-evaluating their tech stacks and looking to minimise costs where possible, it’s more important than ever to ensure that they are getting the most out of your product, and really getting to see the value it has, to help inform their decision making.  At Intercom, we spotted an opportunity to utilise our own Support team (who are speaking with hundreds of customers every day), to proactively flag with customers when they are not using features within their subscription (that they’re paying for!), so that they can see the full power of what they can do with Intercom.  The problem we faced, like most Support teams, is that we did not have a tonne of capacity to spare for our team to take on the additional wor

Hey, I’m B, a Customer Support Engineer with Intercom 👋🐝 An issue we often see users face when building Product Tours & Tooltips is that their selector cannot be found on the page the Tour is being built on.A guaranteed way of making your Product Tour display as expected is editing your CSS selectors to the Intercom specific ones provided -[data-intercom-target="Specific element name"]You’ll find more on this method in this article from our Help Center 📌 

When managing conversation history, it’s not uncommon for Intercom customers to need to export the full contents of a Conversation from Intercom into a third party tool. Depending on the information needed there are a few different approaches to take.  If you don’t need the full text of the Conversation, rather you only need to export the data around the text (ex. which customer you’re speaking to, which admin handled the conversation, etc) then there are 2 different ways to get this data.Option 1: Via the Data Export option in our Reports 1). In the Reports section of your Intercom workspace click on the Data Export option, click on the Conversations or the Tickets tab (depending on which you want to export), and choose your timeframe and any filters that you want to use.2). Choose which fields you want to include in the export from the 4 dropdown menus under the Select Fields to Export section.3). Click on the Export CSV button. An email with a CSV file of those Conversations will be

Hey there 👋Femi here from the Technical Support Engineering  team! We get some questions about using Custom Actions with Custom Objects and Workflows, here’s how to do that. Let’s start by taking a look at what my custom API response to the /products endpoint of my test API looks like 👇 This is important as the request and response type will determine how you structure the Custom Action request.  Now that we know what the response looks like, let’s go ahead and set up our Custom Action. First, navigate to Settings and go to Apps & Integrations where you’ll find “Custom Actions”: This is where you'll set up all the different connections you have to external data (e.g. Shopify, Salesforce, etc.) depending on your use case. In this post, I’ll be making use of my custom online store that sells football boots.Click “Create action” to set up your first Custom Action: Give your Custom Action a clear description 👇  Configure the Request details: This is where you’ll need to enter the AP

Hey, I’m Larissa, a Customer Support Specialist with Intercom. 👋We often get asked what is the difference between conversation tags and attributes. Whist they can easily be confused, they can be used in different ways.Conversation Tags are tags that are applied to individual responses in a conversation. Tags can be applied by teammates, bots, and/or rules. These tags are helpful to flag and categorize information. You can apply multiple tags to the same conversation and they can be completely different. Let’s say that on the same conversation a customer asked for a feature, complimented another one and was really happy with the support given. This conversation could have three tags: ‘feature request’, ‘positive feedback’ and ‘good interaction’.Conversation Data Attributes are more structured than tags. You define specific information that you would like retrieved from a conversation, like specific numbers, text, true/false responses, priority, etc., and then it becomes categorized to

Hi, I’m Brian, a Customer Support Engineer in Chicago 👋A common question: “Is it possible to create two Product tours where the second tour shows immediately after the first one finishes?” The answer is yes! There are a few ways to achieve this.   Note: #2 and #3 will require the help of your dev team 1) Using SeriesPerhaps the simplest way to do this would be to create a Series which sends out the Tours. Then, you can configure it so when the User has completed the first Tour, the second one will be sent automatically.2) Utilize the Intercom(‘update’) methodAn alternative to using a Series would be to refresh the Intercom page after the first Tour is displayed. When you call the Intercom('update') method using some new user data, Intercom will look for new messages that should be shown to the user and will display the second Product Tour. 3) Use the Intercom(‘startTour’) methodAn alternative method would be to display the second tour when a button or a link is clicked on your s

To locate the access tokens for your workspace, go to the Developer Hub and then navigate to Your Apps.Here you'll find a list of all the apps you've built, including the workspace the app is installed on and the production workspace's access token. To find the access token, you'll need to locate the private app with the same name as your workspace's name. If this was migrated over during the update, it will have the phrase "Access Token App" at the end of its name.For example, my production workspace was called CSMappe and the access token would be this private app in my developer hub:  Once you've located this, you'll want to click on the app's name. This will take you to the app's basic information view, like this 👇​Next, you'll want to locate your access-token details by clicking the Authentication link in the navigation bar. Along with details regarding the scope of the token. (i.e. what data it can access and what it can do), you can also make updates to change the scope of your

In Workflows, it is possible to share a ticket form with customers for them to fill out, but it is not directly possible to create a ticket automatically.To create the ticket automatically, you can use Custom Actions to make an API call to create a ticket. The API endpoint you will need to use is here. Here is an example,1- Firstly, you can create your custom action using the example below, which you will insert into your Workflow later. You can adjust the content of the ticket based on your use-case. 2- Now it's time to incorporate this into our workflow:In my example, I’d like to automatically create a ticket whenever a conversation is rated negatively. (See here for more details on how to ask CSAT via Workflows)For this, I am using branches to check if the conversation is rated negatively. If so, it will trigger the Custom Action we created.  3- Result:When the customer rates the conversation negatively, the custom action is automatically triggered by the Workflow above, creating a

Hi I’m Jennifer 👋I am part of the Support Team here at Intercom 👍We often see confusion between creating new Workspaces live in production, creating Test Workspaces and creating Developer Workspaces. There are 3 different types of Workspaces that can be created.Intercom Apps (instances) are called Workspaces, whereas Integrations are called Apps. We've made this change to avoid confusion for developers who are building apps on our Framework.   However, we have not renamed the "app_ID", as changing the name of that to "workspace_id"would have been a breaking change for integrations with Intercom across web apps and websites.To create a new Workspace, you can click on your avatar in the lower left-hand corner. You then hover over your current workspace's name and a pop-out should appear. At the bottom of the "Search for a workspace" pop-out, click "Add a new workspace..." 👍​If you are trying to create a Test Workspace, you should go to your general settings. You'll then be directed to

Using our JS API, it is not possible to update the email field of a visitor type contact with the standard Intercom('update', {"email": "rk.test@testing.com"}); Doing so will result in a 403 error. However, using a parameter in the JS API called anonymous_email will allow you to convert a visitor to a lead via the JS API without running into any issues. Use the update method to pass through the email of the visitor without needing to set up REST API calls to achieve the same result. Intercom('update', {"anonymous_email": "test@example.com"});