Use this article to set up, configure, and manage Data connectors — the feature that lets Fin retrieve live data from your external systems and give customers personalized answers without waiting for a teammate. You'll learn how to create a connector from a template or from scratch, configure its API endpoint, shape the response, control who can trigger it, handle security, roll it out safely, and monitor its performance.

Each Data connector consists of an API (application programming interface) call that you configure. Fin automatically determines when to use it to deliver customer-specific answers. You can connect any system with an API, including:

Navigate to Settings > Integrations > Data connectors and click New.

If you have one of the supported apps installed, you’ll see a template for this app listed under Create Data connector. Templates are currently available for Shopify, Stripe, and Statuspage — see From a 3rd party template below for details.

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 From a custom Data connector section.

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

The API tab defines how Intercom communicates with your external system.

Give your connector a short, descriptive name — for example, "Get unpaid account balance." This helps Fin understand when to use it. Add an internal description for your team's reference.

Data inputs let you specify what information Fin needs to collect before the connector runs — for example, a customer's account number if it's not already stored in Intercom. When Fin needs to pass a search query or other value to the API based on what a customer asks, add a data input and set the source to Let Fin collect — Fin will gather the value automatically from the conversation.

Click + Data input and choose a format:

Give each input a name and description so Fin knows how to collect it. You can also set a fallback value for cases where the API returns a null or missing response.

For each input, choose where the data comes from:

Add the HTTPS (secure web) URL for your API endpoint and select the HTTP request method: GET (retrieve data), POST (submit data), PUT (replace data), DELETE (remove data), or PATCH (partially update data).

Use the Attribute Inserter to pass dynamic values — like a customer's user ID — directly in the URL path or request body.

Select an authentication token and add any custom key-value headers your API requires (for example, Content-Type: application/json).

Once the endpoint URL and authentication details are complete, click Test connection to validate your setup. A successful test returns a green confirmation and the raw API response. A failed test displays the HTTP error code and a description — resolve any errors before proceeding to Phase 2: Data.

The Data tab controls how the API response is filtered and transformed before Fin uses it to answer customers. You can restrict which fields Fin sees and reshape the data using a visual editor or Python code.

By default, Fin has access to the full API response. To limit what Fin can read, switch to Manually restrict access and select only the fields you want to expose.

Choose how you'd like to transform the response:

Object mapping lets you map API response fields directly to Intercom contact or company attributes, automatically syncing data from your external system to your Intercom workspace.

Click Test code to validate your Python transformation logic, and Test connection to confirm the full API call and response shape. Resolve any errors before proceeding to Phase 3: Fin.

The Fin tab controls whether Fin triggers the Data connector automatically or only when explicitly called from a workflow, procedure, or macro. Choose the trigger mode that matches how sensitive or write-active the connector is.

Fin triggers the connector automatically based on the customer's question — no workflow required. Best for read-only connectors like "Check order status" and high-volume, repeatable queries.

You can control who this Data connector is available to with reusable Fin audiences, or by creating a custom audience specifically for this connector. For example, you might make it available to customers in your "Enterprise plan" audience, or restrict it to a custom audience such as logged-in users with a verified email who ask about their account balance.

The connector won't run automatically. You'll need to add it manually to a Workflow, Procedure, or Macro. Best for sensitive or write-active connectors — like "Delete account" — where you want human or workflow oversight before anything runs.

Use Fin preview to see exactly how Fin will respond using this connector before setting it live.

The Security tab is the final step before going live. It controls whether customers must be authenticated before the Data connector can access or display their data.

Toggle this on to enforce your workspace's authentication rules before the connector can access or display sensitive information. Authentication rules are configured at Settings > Workspace > Security > Customer authentication.

Run a diagnostic to assess the health and security of your API setup. Any risks are surfaced with actionable recommendations — resolve them before setting the connector live.

Once all security checks pass, click Save and then Set live. The Data connector status changes to Live in Settings > Integrations > Data connectors. Fin will begin using it immediately for conversations that match the configured audience.

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 list shows the following details for each connector:

Click a connector row to open its health dashboard, where you can review usage, performance metrics, and execution logs, or open the configuration editor to make changes.

To see Data connector activity for a specific conversation, open the conversation in the Inbox and select Show conversation events. The events panel shows whether Fin had access to the Data connector and whether it was successfully triggered.

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

Data connectors use a draft/live versioning system so you can make edits safely without interrupting the running connector.

Two public APIs (application programming interfaces) give you programmatic access to Data connector configurations and execution results. Both use OAuth (Open Authorization) for authentication. Full reference documentation is available in the Intercom Developer Hub.

The Configuration API is a set of CRUD (create, read, update, delete) endpoints for programmatically managing Data connectors. Use it to create new connectors, keep connectors in sync with your internal systems, and automate connector management at scale. The table below lists the available endpoints and their purpose.

Authentication uses OAuth (Open Authorization). Read and write access requires the read_write_data_connectors scope. Read-only access requires the read_workflow_connector_execution_result scope.

The Results API gives you programmatic access to execution data for each Data connector. Use it to build custom dashboards, feed alerting systems, or perform deeper analysis than the in-product health dashboard provides.

Filtering options include success status, specific error types, and time ranges specified as Unix timestamps (seconds elapsed since 1 January 1970 UTC). Pagination uses a cursor-based model, returning up to 30 results per page. Authentication uses OAuth with the read_workflow_connector_execution_result scope.

The following limitations apply to Data connectors. Where a workaround is available, it is noted below.

All response data from Data connectors triggered by Fin is recorded and stored for up to 14 days. To access logs, navigate to Settings > Integrations > Data connectors, click the connector you want to investigate, and select Logs.

For real-time signals on Data connector success and failure rates, use the Data connector execution webhook. This lets you receive execution events from Intercom and use them to build real-time dashboards, alerts, and SLA (service level agreement) monitoring in your external services.