Each data connector consists of an API call which you can configure behind the scenes. Fin will automatically choose when to use it and deliver a personalized answer to the customer.

You can connect any system which has an API; that might be your unique internal backend tool you have built for your business, or a third party app you're using like Shopify, Salesforce, Stripe, Jira, and more.

Learn more about how to design and use your APIs with data connectors.

Navigate to Settings > Integrations > data connectors and click New data connector.

If you have one of the supported apps installed, you’ll see a template for this app listed under Create data connector. We currently support templates for Shopify, Stripe, and Statuspage (more on that below).

data connector templates are available when the following apps are installed in your workspace:

If the app is not already installed, go to the App Store to install. Once the app is installed, data connector templates for each app will appear as an data connector ready to set live.

When you click on a template, you’ll see some information about what the data connector does and you can test it in the Messenger preview. If you’re happy with the data connector behavior, just select Set live for AI Agent.

The Messenger preview here uses example data. When setting the data connector live, Fin will use your real customer data.

If you want to configure the data connector you can click on Customize, which will take you to the data connector builder for advanced configuration.

If you don’t have one of our supported apps installed, the apps will appear here for you to install them on your workspace. After installation, the relevant data connector templates will appear in the section above.

To see AI recommended data connectors, go to Settings > Integrations > data connectors and click New data connector.

You’ll see your unique AI recommended data connectors under "Create data connector from template". These are generated based on your conversation history to help you identify potential data connectors, see what percentage of conversation volume they could resolve, and preview them in the Messenger, before setting anything up.

For AI recommendations to appear, Fin needs to be live on your workspace and you must have sufficient conversation volume.

When you click on an AI recommended data connector, you’ll find information about what the data connector does and you can preview it in the Messenger (using example data). AI recommended data connectors are merely suggestions based on your conversation volume, but they require an API to be connected manually in order to work.

To set the data connector live, click Set up to configure the API details.

Now all you need to do is connect the data connector to your API by adding the HTTPS URL.

To further customize this data connector, see the custom data connector section below. 👇

To set up your own custom data connector for Fin, navigate to Settings > Integrations > data connectors and click New data connector > Create data connector.

First, provide a short name to describe what this data connector does such as “Get unpaid account balance”. This will help Fin know when to use it.

Next, provide a detailed description explaining when Fin should use this data connector. Include examples of the data this data connector provides and customer queries it helps answer.

For example:

Use this data connector to retrieve recent transdata connectors for a customer. This data connector provides key information such as… Example customer queries include…

Then check the box to enable Fin to use this action directly without adding it to a workflow or task.

You can customize who this data connector is available for by clicking Add audience rule. This way, you can set up an data connector to be used when, for example, a logged in user with a verified email asks about their account balance.

If you want to test the data connector before enabling it for customers, use the audience rules to enable the data connector just for you or your teammates initially.

Click Next step when done which will bring you to the API connection section.

If you want, you can specify if Fin should collect any data before using this data connector. This can be helpful in cases where you need to make sure data exists before the data connector is run. For example, you might want to ask the customer for their account number if this is not stored on their user profile in Intercom.

To collect data inputs, click on + Add data input and pick the format of the data that should be collected (text, number, decimal number, or true/false) and give it a name and description so Fin knows how to collect it.

When available, Fin will gather the information from the conversation context.

Next, you must specify the HTTPS URL of your API along with the type of request to be made (GET, POST, etc).

You may want to use attributes available within your workspace, such as a customer’s user ID, to perform a lookup as part of the workflow.

Within a data connector, you can use people, company and more attributes in the path or body of the request.

You can pass dynamic attributes in the API endpoint URL like this:

This is also how you can ensure that Fin can use any collected data inputs configured in the data connector.

You also need to make sure to specify the correct authentication token and to specify correct headers (for example: Accept: application/json or Content-Type: application/json).

Once done, click on Next step to proceed to the next step where you can test your data connector.

You’ll need to test this data connector to make sure it’s fetching the right data from the API you’re connecting to. You can test your data connector using two methods:

If everything is looking good, click on Next step to set up your data access.

By default, Fin can access the full response data to generate replies. Select Manually restrict access if you wish to limit the data Fin can read. Then check the data fields you want to give Fin access to.

You can also edit the individual data items by clicking on the edit icon to give your response data a customer facing name as well as specify any transformations to the data.

For example, if the API response returns a balance of 0, instead of Fin stating the unpaid balance is 0, it can reply stating that there is currently no unpaid balance remaining.

With code blocks for data connectors, we're empowering you to directly transform and manipulate API responses using Python—right inside your connector setup.

Unstructured or overly large payloads from APIs can cause AI-based responses (like Fin or other AI agents) to hallucinate, misinterpret, or simply fail to deliver clear answers. Now, you can programmatically preprocess, filter, or massage API responses before they're sent to Fin or mapped to Intercom objects without needing backend changes or third-party integrations.

Go to Settings > Integrations > data connectors and select the data connector you'd like to use code blocks with.

Then click on Data transformation and select the "Use code to filter or transform the response" option.

To access the data returned by your API (the test response), use the inputs['data'] variable inside your code block. Typically, this gives you the entire response from your API, ready to transform however you like.

For example, at the start of your code block, you typically write:

This assigns the API response (a Python dictionary or list or string, depending on your API) to the variable api_response for further processing.

When you navigate to the Data transformation tab, your data connector response is automatically analyzed to identify suggestions that will improve Fin's performance.

This detects common issues like Unix timestamps and oversized payloads—unstructured or overly large data that can cause AI-based responses to hallucinate, misinterpret, or fail to deliver clear answers.

When a suggestion is found, you'll see a banner with a View suggestion button showing recommended Python code that will make your data cleaner and more reliable for Fin.

Select Test code to see the result it returns.

If you're happy with the return statement, select Accept suggestion to significantly improve the quality and accuracy of Fin's responses from your connector data.

When creating data connectors for Fin, there is no need to map response data to Intercom attributes or objects. Instead, Fin directly interprets the JSON response and can then use it to resolve questions. The response is generated based on the ‘Test response’ section. Each line item corresponds to a data point in the JSON response.

Click Set live and that’s it, Fin’s ready to use your data connector. 🎉

To use code blocks to optimize your data for Fin AI Agent, follow these steps:

We recommend using audience rules to roll out data connectors in phases to your customer base. This enables you to validate the performance of the data connector and make tweaks/changes where necessary.

To find existing data connectors, navigate to Settings > Integrations > data connectors. The data connectors enabled for Fin show a tick below "Usage" and you can see whether they're Live below the "Status" column.

Go to the Inbox conversation and select Show conversation events. Events will show if Fin has access to the data connector and if the data connector is successfully triggered.

Inbox views can be created with the attribute “Fin AI Agent: data connector used in reply”. This attribute is set if Fin calls an data connector and uses some or all of the response in an answer.

For troubleshooting purposes, all response data generated from data connectors triggered by Fin is recorded for up to 7 days. You can access these logs under the specific data connector in Logs.

You can view response data based on what kind of data Fin has access to.