# DataRobot AI integration on Definable

> DataRobot is a machine learning platform that automates model building, deployment, and monitoring, enabling organizations to derive predictive insights from large datasets

## What this connects

DataRobot is a machine learning platform that automates model building, deployment, and monitoring, enabling organizations to derive predictive insights from large datasets

Vendor: https://www.datarobot.com/

## Tools available

**836** tools available. First 12:

- `DATAROBOT_ADD_USERS_TO_GROUP` — Add Users to Group — Tool to add one or more users to a DataRobot user group by groupId. Use when you have a valid groupId and want to add existing usernames. Limit 100 users per request.
- `DATAROBOT_ADD_USER_TO_ORGANIZATION` — Add User to Organization — Tool to add a user to an existing organization. Use when you have an organizationId and wish to add or create a user within it.
- `DATAROBOT_ANALYZE_DATASET_DEFINITION` — Analyze Dataset Definition — Tool to analyze a dataset definition by ID. Use when you need to trigger an analysis job that retrieves dataset metadata, schema, and statistics.
- `DATAROBOT_ARCHIVE_MODEL_PACKAGE` — Archive Model Package — Tool to archive a DataRobot model package. Use when you need to archive a model package that is no longer actively used.
- `DATAROBOT_BUILD_SCORING_CODE_JAVA_PACKAGE` — Build Java Scoring Code Package — Initiates an asynchronous build of a Java JAR package containing DataRobot Scoring Code for a deployment. The JAR can be executed locally for predictions or used as a library in Java applications. Use after confirming the deployment is active and supports scoring code. Poll the returned statusId or location URL to track build progress.
- `DATAROBOT_CANCEL_NOTEBOOK_JOB` — Cancel Notebook Job — Tool to cancel a running or pending notebook job execution. Use when you need to stop a notebook job that is currently executing or queued. The cancellation is immediate and cannot be undone.
- `DATAROBOT_CANCEL_PROJECT_JOB` — Cancel Project Job — Tool to cancel a pending job for a project. Use when you need to stop a queued or running job after confirming its ID.
- `DATAROBOT_CHECK_PROJECT_STATUS` — Check Project Status — Tool to check the status of a DataRobot project. Use after creating or loading a project to monitor its stage and Autopilot completion.
- `DATAROBOT_CLONE_APPLICATION_TEMPLATE` — Clone Application Template — Tool to clone an application template into a codespace. Use when you need to create a new codespace from an existing template.
- `DATAROBOT_CLONE_FILES` — Clone Files Collection — Tool to create a duplicate files collection in DataRobot. Use when you need to clone an existing files catalog item, optionally excluding specific files. The cloning operation is asynchronous - poll the returned location URL to check status.
- `DATAROBOT_COPY_FILE` — Copy File or Folder — Tool to copy a file or folder within the same DataRobot catalog item. Use when you need to duplicate files or folders in the data registry with configurable overwrite strategies.
- `DATAROBOT_CREATE_ACCESS_ROLE` — Create Access Role — Create a custom Access Role for an organization. Use to define tailored permission sets controlling user access to DataRobot entities (projects, deployments, datasets, etc.). Requires an organization ID which can be obtained from the account info endpoint.

## Auth

Auth schemes: `API_KEY`.

## How agents use DataRobot

Inside a Definable workflow, DataRobot is one of the tools the **Distributor specialist** can call. Example coordination patterns:

- **Researcher → DataRobot** — the Researcher (GPT-5.5) pulls context from DataRobot (records, threads, documents), synthesises findings, and briefs the rest of the team.
- **Writer → Distributor → DataRobot** — the Writer (Claude Opus 4.7) drafts copy in brand voice, the Verifier passes it, then the Distributor writes the result into DataRobot (create record, post message, draft email).
- **Designer / Engineer → Distributor → DataRobot** — the Designer ships an asset or the Engineer ships a code change, the Distributor delivers it via DataRobot (attach file, open PR comment, post status).

The Verifier checks every DataRobot call. On rate limit, schema drift, or auth refresh it self-heals and retries — the workflow completes without manual intervention.

## Categories

- artificial intelligence — https://definable.ai/apps/category/artificial-intelligence/
- ai models — https://definable.ai/apps/category/ai-models/

## Related

- HTML page: https://definable.ai/apps/datarobot/
- Same category (artificial intelligence): https://definable.ai/apps/category/artificial-intelligence/
- All integrations: https://definable.ai/apps/
- Workflow (multi-agent loop): https://definable.ai/workflow/
- Apps llms.txt index: https://definable.ai/llms-apps.txt