# Register workflows > Register workflows - After you've connected an agentic workflow custom model to an agentic > playground, compared and tested the workflow, and made any required modifications to the workflow, > you can register the production-ready agentic workflow for deployment to Console. This Markdown file sits beside the HTML page at the same path (with a `.md` suffix). It summarizes the topic and lists links for tools and LLM context. Companion generated at `2026-05-01T23:10:47.694281+00:00` (UTC). ## Primary page - [Register workflows](https://docs.datarobot.com/en/docs/agentic-ai/agentic-deploy/agentic-workflow-register.html): Full documentation for this topic (HTML). ## Sections on this page - [Register from an agentic playground](https://docs.datarobot.com/en/docs/agentic-ai/agentic-deploy/agentic-workflow-register.html#register-from-an-agentic-playground): In-page section heading. - [Register from Workshop](https://docs.datarobot.com/en/docs/agentic-ai/agentic-deploy/agentic-workflow-register.html#register-from-workshop): In-page section heading. - [Register from the Models page](https://docs.datarobot.com/en/docs/agentic-ai/agentic-deploy/agentic-workflow-register.html#register-from-the-registry-models-page): In-page section heading. - [Custom agentic workflow build troubleshooting](https://docs.datarobot.com/en/docs/agentic-ai/agentic-deploy/agentic-workflow-register.html#custom-agentic-workflow-build-troubleshooting): In-page section heading. ## Related documentation - [Agentic AI](https://docs.datarobot.com/en/docs/agentic-ai/index.html): Linked from this page. - [Deploy](https://docs.datarobot.com/en/docs/agentic-ai/agentic-deploy/index.html): Linked from this page. - [Environment,Dependencies, andFiles](https://docs.datarobot.com/en/docs/workbench/nxt-registry/nxt-model-workshop/nxt-create-custom-model.html#assemble-the-custom-model): Linked from this page. - [Evaluation and moderation](https://docs.datarobot.com/en/docs/agentic-ai/agentic-deploy/agentic-configure-evaluation-moderation.html): Linked from this page. - [LLM gateway](https://docs.datarobot.com/en/docs/agentic-ai/genai-code/dr-llm-gateway.html): Linked from this page. - [test the agentic workflow response through the chat and/or score hooks](https://docs.datarobot.com/en/docs/workbench/nxt-registry/nxt-model-workshop/nxt-test-custom-model.html): Linked from this page. - [workshop](https://docs.datarobot.com/en/docs/workbench/nxt-registry/nxt-model-workshop/index.html): Linked from this page. ## Documentation content # Register workflows After experimenting in the agentic playground to build a production-ready agentic workflow, register the custom agentic workflow in the Registry workshop, in preparation for deployment to Console. ## Register from an agentic playground To begin registering an agentic workflow from an agentic playground, find the register option in the comparison chat, or a single-agent chat: **Comparison chat:** Click the actions menu for the agentic workflow you want to register, then click Register agentic workflow. [https://docs.datarobot.com/en/docs/images/agentic-workflow-register-1.png](https://docs.datarobot.com/en/docs/images/agentic-workflow-register-1.png) > [!TIP] Actions menu locations > The actions menu is always available in the Workflows panel for connected agentic workflows. In addition, when a workflow is selected for comparison, the actions menu is available next to the agentic workflow name in the comparison chat area. **Single-agent chat:** Click Register agentic workflow in the upper-right corner of the single-agent chat window. [https://docs.datarobot.com/en/docs/images/agentic-workflow-register-2.png](https://docs.datarobot.com/en/docs/images/agentic-workflow-register-2.png) The agentic workflow opens in the Registry Workshop page. Proceed to [Register from Workshop](https://docs.datarobot.com/en/docs/agentic-ai/agentic-deploy/agentic-workflow-register.html#register-from-workshop). ## Register from Workshop On the Registry > Workshop page, in an open agentic workflow: 1. On theAssembletab, ensure the agentic workflow is fully assembled by reviewing the following sections: LLM gateway access runtime parameter requirementTo use theLLM gatewayfor an agentic workflow, theENABLE_LLM_GATEWAY_INFERENCEruntime parameter must be provided in themodel-metadata.yamlfile and set totrue. 2. (Optional) ClickTest workflowto provide a test dataset andtest the agentic workflow response through the chat and/or score hooks. 3. After the workflow is fully assembled, clickRegister a workflowto open theRegister a workflowpage. 4. UnderConfigure the workflow, theTargetis set based on the workflow you're registering and theTarget typeis set toAgentic Workflow. Select one of the following registration options: 5. ClickRegister a workflow. The agentic workflow version opens on theRegistry > Modelspage with aBuildingstatus. ## Register from the Models page On the Registry > Models page, to register a fully configured agentic workflow: 1. Click theAgentic workflowtab, to filter theModelspage on agentic workflows. 2. Click+ Register a workflow(or thebutton when the registered model or version info panel is open): TheRegister a modelpanel opens to theExternal modeltab. 3. Click theCustom modeltab and then, underConfigure the model, select one of the following options: Then, configure the following fields: FieldDescriptionCustom modelSelect the custom workflow you want to register from theworkshop.Custom model versionSelect the version of the custom workflow to register.Registered model name / Registered modelDo one of the following:Registered model name:When registering a new model, enter a unique and descriptive name for the new registered model. If you choose a name that exists anywhere within your organization, a warning appears.Registered model:When saving as a version of an existing model, select the existing registered model you want to add a new version to.Registered version nameAutomatically populated with the model name, date, and time. Change or modify the name as necessary.Registered model versionAssigned automatically. This displays the expected version number of the version (e.g., V1, V2, V3) you create. This is alwaysV1when you selectRegister as a new model.Optional settingsRegistered version descriptionEnter a description of the business problem this model package solves, or, more generally, describe the model represented by this version.TagsClick+ Add tagand enter aKeyand aValuefor each key-value pair you want to tag the modelversionwith. Tags added when registering a new model are applied toV1. NoteIf you clickCancelon this page to return to theRegistry, you lose the configuration progress on this page. 4. ClickRegister model. The agentic workflow version opens on theRegistry > Modelspage with aBuildingstatus. ## Custom agentic workflow build troubleshooting If the custom workflow build completes with a Build failed status, you can troubleshoot the failure using the model logs. To access the model logs, in the Insight computation failed warning, click Open the workshop: The Workshop opens to the Versions tab for the custom workflow you registered, with the version panel open to the Insights section. Next to Status, find Logs, then click Model logs to open the model logs console: In the Console Log: Model logs modal, review the timestamped log entries: | | Information | Description | | --- | --- | --- | | (1) | Date / time | The date and time the model log event was recorded. | | (2) | Status | The status the log entry reports: INFO: Reports a successful operation.ERROR: Reports an unsuccessful operation. | | (3) | Message | The description of the successful operation (INFO), or the reason for the failed operation (ERROR). This information can help you troubleshoot the root cause of the error. | > [!NOTE] Model logs consideration > In the Registry, a model package's Model logs only report the operations of the underlying model, not the model package operations (e.g., model package deployment time). If you can't locate the log entry for the error you need to fix, it may be an older log entry not shown in the current view. Click Load older logs to expand the Model logs view. > [!TIP] View older logs > Look for the older log entries at the top of the Model logs; they are added to the top of the existing log history.