Devin AI Data Source

The Devin AI connector enables you to ingest data from your organization's Devin AI sessions, playbooks, secrets, and knowledge base into Nexla data flows. Use this connector to monitor engineering activity, audit session outputs, synchronize playbook content, and feed Devin's knowledge and session data into downstream analytics, reporting, or automation pipelines. Follow the instructions below to create a new data flow that ingests data from a Devin AI source in Nexla.

Devin AI

Create a New Data Flow

1. To create a new data flow, navigate to the Integrate section, and click the New Data Flow button. Then, select the desired flow type from the list, and click the Create button.

2. Select the Devin AI connector tile from the list of available connectors. Then, select the credential that will be used to connect to the Devin AI organization, and click Next; or, create a new Devin AI credential for use in this flow.

3. In Nexla, Devin AI data sources can be created using pre-built endpoint templates, which expedite source setup for common Devin AI endpoints. Each template is designed specifically for the corresponding Devin AI endpoint, making source configuration easy and efficient.
   • To configure this source using a template, follow the instructions in Configure Using a Template.

   Devin AI sources can also be configured manually, allowing you to ingest data from Devin AI endpoints not included in the pre-built templates or apply further customizations to exactly suit your needs.
   • To configure this source manually, follow the instructions in Configure Manually.

Configure Using a Template

Nexla provides pre-built templates that can be used to rapidly configure data sources to ingest data from common Devin AI endpoints. Each template is designed specifically for the corresponding Devin AI endpoint, making data source setup easy and efficient.

Endpoint Settings

• Select the endpoint from which this source will fetch data from the Endpoint pulldown menu. Available endpoint templates are listed in the expandable boxes below. Click on an endpoint to see more information about it and how to configure your data source for this endpoint.

List Sessions

Returns a paginated list of all sessions in your Devin AI organization. Use this endpoint to retrieve an inventory of engineering sessions, monitor session activity at scale, or feed session metadata into dashboards and reporting pipelines.

• No additional parameters are required for this endpoint. Nexla will automatically paginate through all available sessions using Devin AI's cursor-based pagination, fetching up to 200 sessions per page until all sessions have been retrieved.
• Each session record includes session metadata such as status, timestamps, and identifiers. Use the Get Session endpoint to retrieve full details — including structured outputs — for a specific session.

This endpoint returns organization-scoped sessions only. Enterprise-scoped endpoints are not covered by this connector. For complete details on the response schema, see the Devin AI API reference for List Sessions.

Get Session

Retrieves full details for a specific Devin AI session by its unique ID, including the session's status, outputs, and structured results. Use this endpoint when you need the complete record for a known session — for example, to audit a completed engineering task or pull structured output data into a downstream system.

• Enter the unique identifier of the session you want to retrieve in the Session ID field. Session IDs can be found by running the List Sessions endpoint first, or by copying the session ID from the Devin AI web app.

  • The Session ID is a required field. The source will not fetch any data if this field is left empty.
  • Each execution of this source will return the details for the single session identified by the provided ID.

For complete details on the response schema, see the Devin AI API reference for Get Session.

Get Session Insights

Returns detailed insights and analytics for a specific Devin AI session. Use this endpoint to analyze session performance, review task completion metrics, and understand how Devin approached and resolved an engineering task.

• Enter the unique identifier of the session whose insights you want to retrieve in the Session ID field.

  • The Session ID is a required field. Session IDs can be obtained from the List Sessions endpoint or from the Devin AI web app.

For complete details on the insights response schema, see the Devin AI API reference for Get Session Insights.

List Session Messages

Returns all messages exchanged within a specific Devin AI session. Use this endpoint to retrieve the full conversation thread between Devin and the user for a given session — useful for auditing interactions, reviewing instructions given to Devin, and analyzing how tasks were steered.

• Enter the unique identifier of the session whose messages you want to retrieve in the Session ID field.

  • The Session ID is a required field. Session IDs can be obtained from the List Sessions endpoint or from the Devin AI web app.
  • This endpoint returns all messages for the session in a single response — it is not paginated.

For complete details on the message response schema, see the Devin AI API reference for List Session Messages.

List Playbooks

Returns a paginated list of all playbooks defined in your Devin AI organization. Playbooks are reusable workflow templates that define repeatable instructions and processes for Devin. Use this endpoint to inventory your organization's playbooks, synchronize playbook metadata to external systems, or audit playbook usage over time.

• No additional parameters are required. Nexla will automatically paginate through all available playbooks using Devin AI's cursor-based pagination, fetching up to 200 playbooks per page.
• Each record in the response includes playbook identifiers and metadata. Use the Get Playbook endpoint to retrieve the full instructions and content for a specific playbook.

For complete details on the response schema, see the Devin AI API reference for List Playbooks.

Get Playbook

Retrieves a single playbook's full content — including its instructions and metadata — by its unique ID. Use this endpoint to extract the complete definition of a specific playbook for auditing, versioning, or synchronizing playbook content with external documentation systems.

• Enter the unique identifier of the playbook you want to retrieve in the Playbook ID field.

  • The Playbook ID is a required field. Playbook IDs can be obtained from the List Playbooks endpoint or from the Devin AI web app.

For complete details on the playbook response schema, see the Devin AI API reference for Get Playbook.

List Secrets

Returns a paginated list of all secrets stored in your Devin AI organization. Secrets are organization-level credentials and API keys that Devin sessions can access at runtime. Use this endpoint to audit which secrets exist in your organization, verify secret configurations, or synchronize secret metadata to a secrets inventory system.

• No additional parameters are required. Nexla will automatically paginate through all available secrets using Devin AI's cursor-based pagination, fetching up to 200 secrets per page.
• The Devin AI API returns only secret metadata (such as names and identifiers) — secret values are never exposed through the API.

For complete details on the response schema, see the Devin AI API reference for List Secrets.

List Knowledge Notes

Returns a paginated list of all knowledge notes in your Devin AI organization's knowledge base. Knowledge notes are tips, instructions, and organizational context that Devin automatically recalls as relevant when working on tasks. Use this endpoint to export and back up your organization's Devin knowledge base, synchronize knowledge notes to external documentation systems, or audit knowledge content.

• No additional parameters are required. Nexla will automatically paginate through all available knowledge notes using Devin AI's cursor-based pagination, fetching up to 200 notes per page.
• Use the Get Knowledge Note endpoint to retrieve the full body and metadata for a specific note.

For complete details on the response schema, see the Devin AI API reference for List Knowledge Notes.

Get Knowledge Note

Retrieves a single knowledge note by its unique ID, including its full body text and metadata. Use this endpoint to extract the complete content of a specific knowledge note for review, versioning, or synchronizing to an external documentation or knowledge management system.

• Enter the unique identifier of the knowledge note you want to retrieve in the Note ID field.

  • The Note ID is a required field. Note IDs can be obtained from the List Knowledge Notes endpoint.

For complete details on the knowledge note response schema, see the Devin AI API reference for Get Knowledge Note.

Endpoint Testing

Once the selected endpoint template has been configured, Nexla can retrieve a sample of the data that will be fetched according to the current settings. This allows users to verify that the source is configured correctly before saving.

• To test the current endpoint configuration, click the Test button to the right of the endpoint selection menu. Sample data will be fetched & displayed in the Endpoint Test Result panel on the right.

• If the sample data is not as expected, review the selected endpoint and associated settings, and make any necessary adjustments. Then, click the Test button again, and check the sample data to ensure that the correct information is displayed.

Configure Manually

Devin AI data sources can be manually configured to ingest data from any valid Devin AI v3 API endpoint. Manual configuration provides maximum flexibility for accessing endpoints not covered by pre-built templates or when you need custom API configurations.

With manual configuration, you can also create more complex Devin AI sources, such as sources that use chained API calls to fetch data from multiple endpoints or sources that require custom request parameters.

API Method

1. To manually configure this source, select the Advanced tab at the top of the configuration screen.

2. Select the API method that will be used for calls to the Devin AI API from the Method pulldown menu. The most common method for Devin AI data sources is:

   • GET: For retrieving sessions, playbooks, secrets, and knowledge notes from the Devin AI API

API Endpoint URL

3. Enter the URL of the Devin AI API endpoint from which this source will fetch data in the Set API URL field. All Devin AI v3 organization-scoped endpoints follow the base URL pattern https://api.devin.ai/v3/organizations/{organization_id}/, where {organization_id} is replaced by your actual Organization ID.

   Common endpoint URL patterns include:

   • List Sessions: https://api.devin.ai/v3/organizations/{organization_id}/sessions
   • List Playbooks: https://api.devin.ai/v3/organizations/{organization_id}/playbooks
   • List Secrets: https://api.devin.ai/v3/organizations/{organization_id}/secrets
   • List Knowledge Notes: https://api.devin.ai/v3/organizations/{organization_id}/knowledge/notes

Ensure the API endpoint URL is correct and accessible with your current credentials. You can test the endpoint using the Test button after configuring the URL.

Date/Time Macros (API URL)

Optional

Optionally, the API URL can be customized using macros—all macros added to the API URL will be converted into values when Nexla executes the API call. Macros are dynamic placeholders that allow you to create flexible API endpoints that can adapt to different time periods or data requirements.

Macros are particularly useful when filtering Devin AI sessions or other resources by date range, or when constructing dynamic API queries that depend on the current time.

1. To add a macro, type { at the appropriate position in the API URL (within the Set API URL field), and select the desired macro from the dropdown list.

   • {now} – The current datetime
   • {now-1} – The datetime one time unit before the current datetime
   • {now+1} – The datetime one time unit after the current datetime
   • custom – Datetime macros can reference any number of time units before or after the current datetime—for example, enter (now-4) to indicate the datetime four time units before the current datetime

2. Select the format that will be applied to datetime macros from the Date Format for Date/Time Macro pulldown menu. This format will be applied to the base datetime value of the macro—i.e., the value of {now} in {now-1}.

3. Select the datetime unit that will be used to perform mathematical operations in the included macro(s) from the Time Unit for Operations pulldown menu—for example, for the macro {now-1}, when Day is selected, {now-1} will be converted to the datetime one day before the current datetime.

Lookup-Based Macros (API URL)

Optional

Column values from existing lookups can also be included as macros in the API URL. Lookup-based macros allow you to reference data from previously configured data sources or lookups, enabling dynamic API endpoints that adapt based on existing data.

Lookup-based macros are useful when constructing Devin AI API URLs that reference specific session IDs, playbook IDs, or other identifiers sourced from another Nexla data flow or lookup table.

1. To include a lookup column value macro, select the relevant lookup from the Add Lookups to Supported Macros pulldown menu.

2. Type { at the appropriate position in the API URL, and select the lookup column-based macro from the dropdown list. Lookup-based macros are automatically populated into the macro list when a lookup is selected in the Add Lookups to Supported Macros pulldown menu.

Path to Data

Optional

If only a subset of the data returned by the Devin AI API endpoint is needed, you can designate the relevant part of the response by specifying the path to that data. This is particularly useful when API responses contain metadata, pagination cursors, or other data you don't need in your Nexset.

For example, Devin AI list endpoints typically return a response with an items array containing the actual records and a next_cursor field for pagination. By entering the path $.items[*], you can configure Nexla to treat each element of the items array as an individual record.

Path to Data is essential when working with Devin AI list endpoints. Without specifying the correct path (e.g., $.items[*]), Nexla may treat the entire response object — including pagination metadata — as a single record rather than extracting individual items.

• To specify which data should be treated as relevant in responses from this source, enter the path to the relevant data in the Set Path to Data in Response field.

  • For responses in JSON format, enter the JSON path that points to the object or array that should be treated as relevant data. JSON paths use dot notation (e.g., $.items[*] to access the items array in a Devin AI list response).
  Path to Data Example:

  For a Devin AI List Sessions response, the sessions are returned inside an items array. Enter $.items[*] to configure Nexla to treat each session as an individual record.

Autogenerate Path Suggestions

Nexla can also autogenerate data path suggestions based on the response from the API endpoint. These suggested paths can be used as-is or modified to exactly suit your needs.

• To use this feature, click the Test button next to the Set API URL field to fetch a sample response from the API endpoint. Suggested data paths generated based on the content & format of the response will be displayed in the Suggestions box below the Set Path to Data in Response field.

• Click on a suggestion to automatically populate the Set Path to Data in Response field with the corresponding path. The populated path can be modified directly within the field if further customization is needed.

  

Metadata

If metadata is included in the response but is located outside of the defined path to relevant data, you can configure Nexla to include this data as common metadata in each record. This is useful when you want to preserve important contextual information that applies to all records but isn't part of the main data array.

For example, Devin AI list responses include a next_cursor field alongside the items array. If you have specified $.items[*] as your path to data but want to preserve the next_cursor or other top-level fields as metadata, you can specify the path to that metadata here.

Metadata paths are particularly useful for preserving pagination tokens, request timestamps, or other contextual fields from Devin AI API responses that apply to all records in the response.

• To specify the location of metadata that should be included with each record, enter the path to the relevant metadata in the Path to Metadata in Response field.

  • For responses in JSON format, enter the JSON path to the object or array that contains the metadata.

Request Headers

Optional

• If Nexla should include any additional request headers in API calls to this source, enter the headers & corresponding values as comma-separated pairs in the Request Headers field (e.g., header1:value1,header2:value2).

  You do not need to include the Authorization header — it is automatically injected by Nexla using the API key configured in your Devin AI credential. Common headers like Authorization and Content-Type are handled automatically based on your credential configuration.

Endpoint Testing

After configuring all settings for the selected endpoint, Nexla can retrieve a sample of the data that will be fetched according to the current configuration. This allows users to verify that the source is configured correctly before saving.

• To test the current endpoint configuration, click the Test button to the right of the endpoint selection menu. Sample data will be fetched & displayed in the Endpoint Test Result panel on the right.

• If the sample data is not as expected, review the selected endpoint and associated settings, and make any necessary adjustments. Then, click the Test button again, and check the sample data to ensure that the correct information is displayed.

Save & Activate the Source

1. Once all of the relevant steps in the above sections have been completed, click the Create button in the upper right corner of the screen to save and create the new Devin AI data source. Nexla will now begin ingesting data from the configured endpoint and will organize any data that it finds into one or more Nexsets.