Devin AI
Devin AI is an autonomous AI software engineer from Cognition that handles end-to-end engineering workflows — planning, coding, testing, debugging, and deployment. It operates in a secure sandbox with a terminal, editor, and browser to complete complex multi-step tasks with minimal oversight. Teams use it to automate coding at scale through repeatable playbooks.

Power end-to-end data operations for your Devin AI API with Nexla. Our bi-directional Devin AI connector is purpose-built for Devin AI, making it simple to ingest data, sync it across systems, and deliver it anywhere — all with no coding required. Nexla turns API-sourced data into ready-to-use, reusable data products and makes it easy to send data to Devin AI or any other destination. With comprehensive monitoring, lineage tracking, and access controls, Nexla keeps your Devin AI workflows fast, secure, and fully governed.
Features
Type: API
- Seamless API Integration: Connect to any endpoint as source or destination without coding, with automatic data product creation
- Visual Composition & Chaining: Build complex integrations using visual templates, chain API calls, and compose workflows with data validation and filtering
- API Proxy: Expose curated slices of your data securely with a secure and customizable API proxy that validates and transforms data on the fly
- Request optimization with intelligent batching, retry, and caching to minimize API calls and costs
Prerequisites
To connect Nexla to your Devin AI organization, you will need a Devin AI API key (also called a Service User API key) and your Organization ID. Devin AI uses a service user model for programmatic API access — service users are separate identities from human users, appear independently in audit logs, and their permissions are controlled through role-based access control (RBAC).
Obtain Your Organization ID
Your Organization ID is required for all Devin AI v3 API endpoints. It identifies the specific organization whose data Nexla will access.
-
Sign in to your Devin AI account at app.devin.ai.
-
Navigate to Settings > Service Users in the left-hand navigation.
-
Your Organization ID is displayed on the Service Users page. Copy and save this value — you will need it when configuring the Nexla credential.
Create a Service User and Generate an API Key
Devin AI API keys are tied to service users — dedicated machine identities used for integrations and automated workflows. Creating a dedicated service user for Nexla ensures that API activity is clearly attributed and permissions can be precisely scoped.
-
From the Settings > Service Users page in the Devin AI web app, click Create Service User.
-
Enter a descriptive name for the service user (e.g.,
nexla-integration) to make it easy to identify in audit logs. -
Assign a role to the service user that includes the permissions required for your integration:
-
To read sessions, playbooks, secrets, and knowledge notes, the service user needs read permissions for those resource types.
-
To create or modify sessions, playbooks, secrets, or knowledge notes, the service user needs write permissions for those resource types.
Assign only the permissions your integration actually requires. Following the principle of least privilege reduces the risk of unintended changes to your Devin AI organization. Additional permissions can be granted later if needed.
-
-
After saving the service user, click Generate API Key on the service user's detail page.
-
Copy the generated API key immediately. The key begins with
cog_and is displayed only once — it cannot be retrieved after you leave the page. Store it securely in a password manager or secret management system.ImportantThe API key is shown only once at the time of creation. If you lose the key, you will need to generate a new one. Never share your API key or commit it to source control.
For complete details on service user setup and permission scopes, see the Devin AI API Authentication documentation and the API Overview.
Authenticate
Credentials required
Bearer token authentication. Provide your Devin AI API key for authorized access to sessions, playbooks, and knowledge management endpoints.
| Field | Required | Secret | Description |
|---|---|---|---|
| API Key | Yes | Yes | Your Devin AI API key for authentication. |
| Organization ID | Yes | No | Your Devin AI organization ID. Required for all v3 API endpoints (e.g. /v3/organizations/{organization_id}/sessions). Find it on the Settings → Service Users page in the Devin UI. |
Create a credential in Nexla
-
To create a new Devin AI credential, after selecting the data source/destination type, click the Add Credential tile to open the Add New Credential overlay.
-
Enter a name for the credential in the Credential Name field and a short, meaningful description in the Credential Description field.
-
Devin AI uses Bearer token authentication — Nexla sends your API key as an
Authorization: Bearerheader on every request to the Devin AI API. Enter your Devin AI API key (beginning withcog_) in the API Key field. This key authenticates Nexla as the service user and controls which Devin AI resources Nexla can access. -
Enter your Devin AI Organization ID in the Organization ID field. This value is used to construct the base URL for all v3 API calls (e.g.,
/v3/organizations/{organization_id}/sessions). You can find this ID on the Settings > Service Users page in the Devin AI web app.The Organization ID is not a secret and does not need to be stored securely, but it must be entered exactly as it appears in the Devin AI settings — typically a UUID-format string.
-
Click the Save button at the bottom of the overlay. The newly added credential will now appear in a tile on the Authenticate screen during data source/destination creation and can be selected for use with a new data source or destination.
Use as a data source
To create a new data flow, navigate to the Integrate section, and click the New Data Flow button. Select the Devin AI connector tile, 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.
Endpoint templates
Nexla provides pre-built templates that can be used to rapidly configure data sources to ingest data from common Devin AI endpoints. 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.
Once the selected endpoint template has been configured, click the Test button to the right of the endpoint selection menu to retrieve a sample of the data that will be fetched. Sample data will be displayed in the Endpoint Test Result panel on the right, allowing you to verify that the source is configured correctly before saving.
Manual configuration
Devin AI data sources can also be manually configured to ingest data from any valid Devin AI v3 API endpoint not covered by the pre-built templates, including sources that use chained API calls or custom request parameters. Select the Advanced tab at the top of the configuration screen, and follow the instructions in Connect to Any API to configure the API method, endpoint URL, date/time and lookup macros, path to data, metadata, and request headers.
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 — for example, .../sessions, .../playbooks, .../secrets, and .../knowledge/notes. List endpoints return records inside an items array with a next_cursor field for pagination, so set Path to Data in Response to $.items[*] to treat each item as an individual record. 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.
Once all of the relevant settings have been configured, 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.
Use as a destination
Click the + icon on the Nexset that will be sent to the Devin AI destination, and select the Send to Destination option from the menu. Select the Devin AI connector from the list of available destination 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.
Endpoint templates
Nexla provides pre-built templates that can be used to rapidly configure destinations to send data to common Devin AI endpoints. Select the endpoint to which data will be sent from the Endpoint pulldown menu. Then, click on the template in the list below to expand it, and follow the instructions to configure additional endpoint settings.
Manual configuration
Devin AI destinations can also be manually configured to send data to any valid Devin AI v3 API endpoint not covered by the pre-built templates. Select the Advanced tab at the top of the configuration screen, and follow the instructions in Connect to Any API to configure the API method, data format, endpoint URL, request headers, attribute exclusions, record batching, and response webhooks.
All Devin AI v3 organization-scoped endpoints follow the base URL pattern https://api.devin.ai/v3/organizations/{organization_id}/ — append the resource ID for operations on a specific resource (e.g., https://api.devin.ai/v3/organizations/{organization_id}/sessions/{session_id}). Devin AI API endpoints accept JSON format (application/json). Most endpoints accept a single resource per request, so record batching is appropriate only for custom or bulk endpoints that accept arrays — review the Devin AI API documentation to confirm whether your target endpoint supports batching before enabling it. Nexla can also send the API response after each call to a new Nexla webhook data source, which is useful for capturing the session ID returned when creating a session.
Save & activate
Once all endpoint settings have been configured, click the Done button in the upper right corner of the screen to save and create the destination. To begin sending data to the configured Devin AI endpoint, open the destination resource menu, and select Activate.
The Nexset data will not be sent to the Devin AI API until the destination is activated. Destinations can be activated immediately or at a later time, providing full control over data movement.