Fin Attributes enable Fin to understand and classify what a conversation is about in real time. This allows Fin to apply structured attribute values - like issue type, sentiment, or urgency - that power smarter triage, routing, and reporting.

Key benefits

Custom attributes that reflect your business: Train Fin to detect attributes like issue type, urgency, sentiment, or spam status.
Real-time, adaptive detection: Fin continuously evaluates context and updates values as the conversation evolves.
Smart routing and escalation: Combine Fin Attributes with workflows and escalation rules to route conversations to the right team at the right time.
Reporting-ready structure: All detected attribute data flows into Fin reports for deep insight—no manual tagging required.
Full transparency and control: View, validate, and override Fin’s attribute logic at any time.

How Fin applies attributes

By default, when Fin is involved in a conversation, it will classify enabled attributes at key moments:

When handing off to a teammate.
When the customer expresses resolution (positive feedback).
When a customer becomes inactive.

If you set up Escalation Rules, Fin will re-evaluate the conversation after each message, enabling more dynamic, real-time classification.

Note: If you're already using AI Category Detection, learn how Fin Attributes compares and how to transition.

How to set up Fin Attributes

Step 1: Decide what to classify

Think about the types of structured information you want Fin to detect. Common examples include:

Issue type (e.g., Billing, Projects, Account Management)
Sentiment (Positive, Neutral, Negative)
Urgency (Urgent, High, Normal, Low)
Spam detection (Spam, Legitimate)

Step 2: Create a new attribute (or convert an existing attribute)

To create a new Fin Attribute:

Go to Train > Attributes.
Click New.
Fill in the Name and Description for your attribute
Add Values (with clear descriptions for each).

Tip: Learn how to create effective attribute names and descriptions to help Fin classify your support conversations with high accuracy

To convert an existing attribute:

Go to Settings > Conversation data, click edit on a list-type attribute, and then click Let Fin detect.
Once converted, the attribute will appear under Train > Attributes.

Note: Once converted to a Fin Attribute, an attribute can't be reverted - but you can leave it disabled if needed.

Step 3: Preview before enabling

Before enabling an attribute, use the built-in preview in Train > Attributes to:

Test attribute values against example customer messages
Check how accurately Fin applies the right value
Iterate on names and descriptions before enabling

[Optional] Step 4: Add Conditional Rules

Use Conditions to create rules that control precisely when Fin should detect a specific attribute. This allows for more accurate classification, which leads to cleaner routing and reporting.

Conditions work by linking attributes together, creating a parent/dependent relationship. Fin will only attempt to detect the dependent attribute after it has first identified the parent attribute and its value.

How it works

The logic for Conditions is a simple If/Then statement:

If Fin detects a specific value for a parent attribute, then it will attempt to detect the dependent attribute.

You can configure these rules in the attribute settings side drawer under the Conditions tab. For each rule, you’ll define:

Define the parent attribute value.
Choose the condition that should be triggered when that parent value is detected.
Specify which condition values are allowed.

Examples:

If Issue type = Refund request → then detect Refund request reason.
If Sentiment = Negative sentiment → then detect Urgency.

When this logic is in place, Fin will first detect the parent attribute. If the defined value matches, Fin will then attempt to detect the linked conditions.

Note: Conditions logic is respected in Escalation Rules. If a condition is referenced in an Escalation Rule, Fin will re-evaluate the conversation after each customer message to see if the parent and condition values match.

Monitoring and reviewing Fin Attributes

Once your attributes are enabled, Fin provides real-time stats to help you understand how attributes are being applied.

You’ll see:

Conversations → the number of conversations Fin has detected for each attribute and specific attribute value.
Resolved → the percentage of those conversations that Fin was able to fully resolve.
Routed → the percentage of conversations successfully routed using that attribute.

You can also drill down into individual conversations to review how Fin applied a attribute and validate accuracy. This enables you to monitor the accuracy of the applied attribute, review conversations where the attribute is incorrect and update attribute descriptions based on patterns.

Tip: Learn how to use Fin Attributes in workflows, reports, and when analyzing conversations.

Fin Attributes examples

Below are some examples of ways that customers are using Fin Attributes in conversations.

Issue Type attribute example:

Projects - Projects are a collection of related tasks and activities aimed at achieving a specific objective or deliverable which can involve teammate collaboration, time tracking, milestones or goals, and status.
Billing - Billing encompasses managing subscription plans, invoices, payment methods, discounts, plan features, trials, account restrictions, refunds, and more for a seamless billing experience.
Account Management - Account Management covers discussions related to user accounts, including account creation, deletion, updating personal and payment information, and more.

Sentiment attribute example:

Positive - A positive sentiment means the user who wrote the message seems generally happy or satisfied and is probably feeling a positive emotion.
Negative - A negative sentiment means the user who wrote the message seems generally unhappy or dissatisfied and is probably feeling a negative emotion.
Neutral - A neutral sentiment means the user who wrote the message seems to be neither happy nor unhappy and it is difficult to guess their emotion.

Spam Detection attribute example:

Spam - Automated spam that is sent to the customer support agents. This includes auto-responders, newsletters, guest posts, and other general spam messages that could be ignored by the CS analyst.
Legit - Legitimate conversations in which the user has an actual issue that should be handled by a customer support analyst.

FAQs

What does Fin use to detect attributes?

Fin uses the attribute name, its description, and the value names and descriptions when evaluating which attribute value to apply. Ensure that all of these fields are written in a human-readable way that is easy for Fin to interpret.

What if the applied attribute isn’t accurate?

We recommend checking that the naming and descriptions. Use our best practices and test with real customer messages in the preview tool.

Pro tip: To help review your attribute value labels and descriptions, you might like to try using an AI writing tool such as Chat GPT or Claude.

Example prompt:

You are an expert in customer-support AI. You are evaluating a taxonomy used by a LLM to classify customer support conversations. For each attribute (e.g., Topic, Sentiment), the LLM chooses the most appropriate attribute based on a combination of the attribute name and its description. This taxonomy will directly impact the LLM's ability to classify real customer support conversations. Your task is to assess the quality of this setup using the following best practices: Create clear, concise names - Choose short, descriptive names that immediately convey the attributes purpose. Write comprehensive descriptions - Take the time to write detailed descriptions and include all relevant information about what belongs in the attribute. Think about every type of conversation that should fall under this attribute and describe them in the description. Providing a detailed description will help Fin classify conversations correctly. You can include keywords and examples of customer questions. Make attributes distinct - Avoid creating attributes that overlap too much. Your attributes should be clearly different from each other, making it easy to determine which one best fits a given situation. This should be checked within each attribute only. It's fine for different attributes to apply to the same conversation. It shouldn't affect the score. Overlap with values in other attributes is allowed and does not affect this score. Ignore Archived Attributes - If a attribute is marked as archived, do not evaluate or score it. Add 5 Columns to the CSV Clarity/Conciseness (1–5), Description Comprehensiveness (1–5), Attribute Distinction (1–5), Final Score, Comment Assess each parameter for each attribute, and write a comment of why you applied this rating. Then calculate the overall score for this setup. After you've done this add one more column: Overlapping Attributes. If you think any given attribute overlaps with other attributes - list these attributes there.

What if Fin doesn’t detect a value?

Fin will return a null value if none of the attributes apply, which will leave the attribute empty. You can include an "Other" option to catch unclassified conversations if preferred.

I’m using AI Category Detection - should I switch to Fin Attributes?

Fin Attributes are the next generation of AI Category Detection. They run automatically, require less workflow maintenance, and work seamlessly with Escalation Rules, giving you full control over the conversations Fin hands to your team.

Your current setup won’t change, but we recommend learning more and switching to Fin Attributes for an improved product and experience.

What happens when I convert an existing AI Category Detection attribute to a Fin Attribute?

When you convert an existing AI Category Detection conversation attribute into a Fin Attribute, Fin simply uses the same underlying conversation attribute. That means:

The converted attribute will continue to work in your existing workflows and reports without interruption.
When enabled, Fin will start classifying attribute values at key moments, so you may see these attributes being updated twice at first (once by AI Category Detection, once by Fin).
To simplify, you can eventually remove your AI Category Detection workflow blocks once you’re happy with how Fin is applying attributes.
Conversion is a one-way action - attributes cannot be reverted back to AI Category Detection, but they can be disabled if needed.

Do I have to involve Fin in every conversation to use Fin Attributes?

Yes. Fin Attributes are applied by Fin when it is present in a conversation. This means Fin must be included in your workflows in order to classify conversations.

If you’d prefer Fin not to answer in certain cases, you can use Escalation Rules. This allows Fin to classify the conversation and then exit immediately, based on conversation or user attributes of your choice.

For example, you could:

Escalate all conversations where Channel = Email
Escalate all conversations where Attribute = Billing

This way, you get the benefits of consistent classification across all conversations, while maintaining full control over when Fin does or doesn’t respond.

How to create Fin Attributes