Use this article to set up Fin AI Agent over email — from verifying your email channel and training Fin on content, to testing responses, deploying to customers, and optimizing performance. It also covers multi-participant thread controls, spam filtering, and DMARC email security.

The following instructions have been created based on what we know provides accurate AI-powered email support within your customers’ inboxes.

In order to use Fin over email, you must first ensure you have the correct setup for your email channel. Check your setup in Settings > Channels > Email.

You'll need to identify the audience or support topics you want Fin to handle over email and set a success metric (e.g. resolution rate, customer satisfaction (CSAT)). For example, this could include specific high-volume topics or a sub-set of customers.

Go to Fin AI Agent > Train > Content and ensure you've enabled content which Fin can use to support email queries. Update your content to cover your frequently asked email queries. You can add public articles, PDFs, snippets, URLs, or content from previous conversations.

Go to Fin AI Agent > Train > Guidance and set up guidance to train Fin how to speak in your brand’s voice, follow your policies, and handle conversations the way you want—using simple, natural-language instructions. You can set clear rules for what Fin should say and do, from using the right terminology to handing sensitive topics over to your human support team.

Go to Fin AI Agent > Train > Attributes and set up Fin Attributes to automatically classify conversations by topic, sentiment, urgency, or any custom attribute you define. Fin sets these attributes during a conversation, and you can use them as conditions in workflows to automatically route or escalate conversations to the right team.

Go to Fin AI Agent > Train > Escalation and configure Escalation guidance to define when and how Fin should hand conversations over to your human support team. Use natural-language or rules to specify escalation conditions—for example, escalating when a customer asks the same question twice, mentions a specific keyword, or expresses frustration.

Go to Fin AI Agent > Train > Procedures and build Procedures to automate more complex processes. Often times, these processes may involve actions in your external systems that need to reliably follow your specific business rules (e.g. cancel an order, refund a subscription). Fin will trigger the procedure and be actively involved each step to resolve customer queries.

From Fin AI Agent > Test you can see if you're ready to deploy Fin by testing how Fin responds to actual customer queries.

Simply generate questions from previous conversations, bulk upload questions via a CSV (comma-separated values file), or manually add specific questions you want to test Fin on. Then review Fin's responses and mark them as "Good" or "Poor".

When marking a response as "Poor" you can leave a reason and dig into where Fin's answer came from (i.e. which content source, guidance, or personality settings were used). You'll also get recommendations on how to improve Fin's answer. Then you can export this as a report to share with your teammates.

It's a good idea to set Fin over email live to a small test or internal audience (e.g. yourself and teammates) and monitor Fin’s replies for quality and accuracy.

Expand the audience Fin is replying to, so that Fin is replying to some real customer conversations over email. Review the results from Fin AI Agent > Analyze then expand Fin to handle more of your volume or topics.

Go to Fin AI Agent > Deploy > Email. At the top of this page, you'll see "Simple deploy" where you can:

Decide which of your customers can interact with Fin AI Agent. You can allow Fin to provide answers to your users and/or leads.

Click + Add audience rule and use data attributes in Intercom to target your audience further. Then click Save.

Before enabling Fin over email, you need to:

Now configure Fin's introduction message to customers who reach out through email. This helps your customers better understand what Fin can do and how to interact with it. You only need to write Fin's introductory messages in your workspace's default language. When you click Save, these messages will be automatically translated into all of the supported languages you have enabled for Fin.

Review the content sources you've enabled for Fin.

Review the guidance you've configured for Fin. This is how you can tailor Fin's responses to follow your brand voice and policies. Since email behaves differently from chat, consider targeting relevant guidance rules to the email channel only — for example, to avoid suggesting real-time support options like chat or phone, or to shape how Fin structures its responses.

When Fin is deployed over email, you can control how it behaves on threads with multiple participants. Two settings are available in the Fin answers the customer section of Fin AI Agent > Deploy > Email:

CC behavior — controls whether Fin responds when it's only addressed in CC (not in the To field):

Reply scope — controls who receives Fin's replies when it does respond:

The table below shows how Fin AI Agent's CC behavior and reply scope settings combine on email threads:

Specify what action should be taken if Fin cannot resolve the conversation. You can choose how Fin hands over or escalates to a particular team or teammate. Then click Save and move to the next step.

At the end of a customer's interaction with Fin AI Agent you can ask them to give a conversation rating by toggling these settings on:

Customize how long Fin waits before sending a follow-up email to customers who go quiet mid-conversation. Set your preferred delay in the Follow up with inactive customers section:

Choose when to auto-close conversations by specifying a length of time Fin should wait before before marking a customer as inactive. If you've enabled a follow-up, it will be sent after the last customer message. Once the follow-up is sent, the auto-close timer you set below will begin.

Select if you want Fin to automatically close the conversation after customer becomes inactive:

You can also Customize what Fin says when closing the conversation to make sure the customer got what they needed and remind them they can still speak to your support team, even if the conversation is being closed. Then click Save and move to the next step.

The Email Preview lets you test Fin's email experience end-to-end before going live. It shows a threaded conversation view — just like a real email inbox — so you can see exactly how customers will receive and interact with Fin's replies, including multi-turn exchanges where Fin reads and responds to follow-up messages in the same thread.

To preview Fin over email as a specific user or brand, select the Preview user dropdown at the top of the preview and then select User or lead. This let's you impersonate real users/leads and see exactly how Fin will respond. You can simulate real scenarios using live or dummy data, test data connectors, and validate every answer.

Once you've finished configuring Fin's email experience, click Set Fin Live. Fin will immediately begin responding to new inbound emails that match your configured audience rules. You can pause or update the configuration at any time from Fin AI Agent > Deploy > Email.

If you want to add Fin to a workflow, or customize Fin in an existing workflow, go to Fin AI Agent > Deploy > Email and open Advanced setup through Workflows.

If you have an existing workflow set up specifically for email:

If you don't have a workflow set up specifically for email:

To customize Fin's behavior in an email workflow, click on the Let Fin handle step in the workflow path. Here, you can:

By using branching, you can create different Fin experiences for different audiences.

For example:

Add as many branches as you need to create different experiences for your different customers.

You can also use branching to create different Fin experiences and paths based on your different email topics.

For example, you can use a "Message Content" filter to escalate conversations which contain the keyword "billing" directly to your Billing team.

You can use workflows to automatically handle unwanted emails—such as newsletters, out-of-office auto-replies, or emails from known spam senders—before they reach your inbox or Fin.

If you want to test a Fin over email workflow, send an email to your support email address configured in Settings > Channels > Email > Domains & addresses.

After you've deployed Fin over email, go to Fin AI Agent > Analyze to get real-time metrics like Customer Experience (CX) score, automated conversation analysis at scale, and AI-powered suggestions for optimizing Fin.

Here, you'll find the following dashboards:

As you analyze Fin’s performance and identify opportunities for improvement, you’ll need to continuously train, test, and deploy Fin to achieve an increasing number of Outcomes.

Fin AI Agent can reply to your customers' questions over email just like it does in the Messenger. Every email response from Fin will:

You can choose how Fin follows up with customers over email. By default, Fin will ask a relevant question to encourage a natural conversation.

If the customer's message is not clear, Fin will send a message asking to clarify what they need assistance with.

When the customer responds, they have the following options:

Customers will receive a follow-up email confirming the action:

Intercom has a sophisticated built-in spam filtering system that automatically checks incoming emails for hidden links, malware, phishing attempts, and proper authentication of sender's address. We assign all inbound emails a spam score and filter messages that exceed our spam threshold. This is Intercom's infrastructure-level spam filter, which runs first on all inbound email.

Fin AI Agent uses an AI spam detection system that triggers very early in the inbound email processing pipeline, before a conversation is created. Emails flagged as spam by this system are automatically routed to the Spam folder. This prevents Fin from engaging with spam messages, leading to more accurate metrics for Fin’s Involvement Rate. Unlike the infrastructure-level spam filter, which uses a numeric score against a configurable threshold, the AI spam filter makes a binary yes/no decision — there is no score or threshold involved.

You can customize the behavior of the AI spam detection using Spam Guidance.

The Spam view shows all email conversations Fin has flagged. Each flagged conversation includes a brief reasoning note from Fin, so your team can quickly understand why it was flagged and decide what to do next.

If a genuine customer follows up on a spam-flagged conversation, Fin automatically re-evaluates and can clear the flag. Follow-ups from actual spam are re-evaluated and can be confirmed as spam.

By default, emails marked as auto responders go to your Spam folder but if you need these to appear in your inbox, you can turn off this setting so they are routed to the inbox from Settings > Channels > Email > Email settings.

You can add an important layer of security to your inbound email flow by preventing Fin from processing emails that fail DMARC authentication. This ensures Fin only engages with emails sent from legitimate, verified domains, reducing the risk of fraud.

DMARC (Domain-based Message Authentication, Reporting, and Conformance) is an email authentication protocol designed to protect your domain from spoofing and phishing. It allows you to specify how incoming messages should be handled if they fail authentication checks.

When the “Prevent Fin from processing emails that fail authentication (DMARC)” setting is enabled, any inbound email that fails this check will be blocked from reaching Fin and Fin will not respond.

To enable this: