Cursor has modified how builders write code. The agent mode is sweet: you describe what you need, it causes by way of the issue, picks the fitting instruments, and ships working code. For greenfield initiatives and normal libraries, it really works easily.
The place it will get more durable is while you’re constructing brokers on a specialised platform with its personal deployment patterns, SDK conventions, and infrastructure abstractions. Cursor is a quick learner, however it doesn’t ship understanding your platform’s pyproject.toml construction, which endpoints to make use of for various agent execution patterns, or the best way to wire up Pulumi for a primary manufacturing deployment. With out that context, you find yourself correcting hallucinated API calls and debugging configuration errors that don’t have anything to do along with your precise use case.
DataRobot solves this with agentic Expertise: modular context packages that give Cursor precisely what it must construct, deploy, and govern manufacturing AI brokers on the DataRobot platform. Set up them as soon as. Cursor handles the remaining. You’ll be able to go from empty repo to a ruled, manufacturing AI agent with out leaving Cursor.
This put up walks by way of what Expertise are, the best way to get them into Cursor in below two minutes, and the best way to construct and deploy a production-ready agent with them.
A DataRobot Talent is a self-contained folder containing a SKILL.md file with YAML frontmatter, plus any helper scripts the agent can run instantly. When Cursor masses a Talent, it positive factors particular, validated steering for that functionality space: mannequin coaching, deployment, predictions, monitoring, function engineering, or CI/CD setup for the app framework.
The design objective is intentional: slightly than dumping every thing right into a monolithic system immediate and overwhelming your agent’s context window, Expertise are modular. You load what you want for the duty at hand.
All DataRobot Expertise comply with the naming conference datarobot-. The total set at present obtainable:
| Talent | What It Covers |
|---|---|
datarobot-agent-assist |
Unified DataRobot agent workflow — design (agent_spec.md), non-obligatory dress-rehearsal simulation through built-in rehearsal engine, template-based coding, and deployment. |
datarobot-model-training |
AutoML mission creation, coaching configuration, mannequin administration |
datarobot-model-deployment |
Deploying fashions, configuring prediction environments |
datarobot-predictions |
Batch scoring, real-time predictions, prediction dataset templates |
datarobot-feature-engineering |
Characteristic discovery, significance evaluation, engineering steering |
datarobot-model-monitoring |
Knowledge drift monitoring, mannequin well being, efficiency monitoring |
datarobot-model-explainability |
SHAP values, prediction explanations, diagnostics |
datarobot-data-preparation |
Knowledge add, dataset administration, validation |
datarobot-app-framework-cicd |
CI/CD pipelines, Pulumi infrastructure-as-code for agent templates |
datarobot-external-agent-monitoring |
OpenTelemetry instrumentation to route traces and metrics to DataRobot |
Expertise are Agent Context Protocol (ACP) definitions, which implies they work past Cursor too. The identical repository is appropriate with Claude Code, OpenAI Codex, Gemini CLI, VS Code Copilot, and others.
Putting in DataRobot Expertise in Cursor
DataRobot Expertise can be found on the Cursor Market at cursor.com/market/datarobot.
Choice 1: One command from the Cursor command palette
Open Cursor’s command palette and run:
/add-plugin datarobot-agent-skills
This registers the complete DataRobot Expertise repository towards your Cursor set up. No configuration required. Cursor reads the AGENTS.md file routinely and makes all abilities obtainable on demand.
Choice 2: Common installer through npx
In case you choose to put in from the terminal and duplicate Expertise instantly into your mission repo:
# Set up all abilities
npx ai-agent-skills set up datarobot-oss/datarobot-agent-skills
# Set up a selected talent solely
npx ai-agent-skills set up datarobot-oss/datarobot-agent-skills/datarobot-predictions
# Set up for Cursor particularly
npx ai-agent-skills set up datarobot-oss/datarobot-agent-skills --agent cursor
Confirm set up
Open the Cursor AI chat panel (Cmd/Ctrl + L) and ask:
What DataRobot Expertise can be found?If Expertise are loaded, Cursor will checklist them. In case you get a clean response, verify that the repository is open as your workspace and that AGENTS.md is on the root.
Right here’s a concrete instance to point out how Expertise change the expertise in follow. We’ll construct and deploy a customer-facing help agent that makes use of the DataRobot LLM gateway, connects to an current mannequin deployment as a software, and ships as a manufacturing software through the DataRobot app framework.
Step 1: Scaffold the agent
Begin from an empty mission repo. Open Cursor Agent mode and provides it a transparent job immediate that references the Expertise you need it to make use of:
Use the DataRobot app framework CICD Talent to scaffold a brand new agent mission. The agent ought to reply buyer help questions by querying a DataRobot deployment for churn danger rating and returning a advisable subsequent motion. Use the DataRobot LLM gateway for all LLM calls. Deploy through Pulumi.With the datarobot-app-framework-cicd Talent loaded, Cursor generates a mission that follows the proper DataRobot template construction: the fitting pyproject.toml format, a correctly configured agent bundle, LLM gateway enabled by default, and Pulumi infrastructure-as-code for deployment. With out the Expertise that is the place brokers usually go sideways — unsuitable dependency declarations, lacking runtime parameter injections, or a template construction that silently breaks on first deploy.
Step 2: Wire in your DataRobot deployment as a software
Now add the prediction software that provides the agent one thing to motive over:
Use the DataRobot predictions Talent so as to add a software to this agent that calls deployment ID, passes customer_id and account_tenure as options, and returns the churn_probability rating.
The datarobot-predictions Talent provides Cursor the validated SDK patterns for real-time prediction calls, together with the best way to construction the function payload, deal with the response schema, and floor prediction explanations if you would like the agent to justify its suggestion. Cursor pulls within the related helper scripts from the Talent’s scripts/ listing slightly than writing its personal endpoint logic from scratch.
Step 3: Check domestically with job dev
Earlier than deploying, run the agent domestically utilizing DataRobot job dev tooling:
Run this agent domestically utilizing DR job dev and ensure the prediction software returns a legitimate response for a check customer_id.The Expertise embrace steering on the dr job CLI instructions and customary native testing patterns. In case you hit authentication points, reply Cursor’s follow-up:
Use DATAROBOT_API_TOKEN and DATAROBOT_ENDPOINT from setting variables.Step 4: Deploy to manufacturing
As soon as native testing passes, deploy:
Use the DataRobot app framework CICD Talent to deploy this agent to manufacturing utilizing Pulumi. Create a brand new stack named customer-support-agent.Cursor generates the proper pulumi up sequence, configures the deployment with the fitting server sort and credential dealing with, and wires the appliance to your DataRobot use case. First deploys usually take 10 to twenty minutes as Pulumi provisions the complete stack. Subsequent updates are sooner. When it completes, you’ll have a registered mannequin, an agent deployment, and a dwell software endpoint in your DataRobot workbench.
What Expertise don’t do (but)
Expertise present context. They don’t deal with OAuth flows for third-party integrations, auto-configure your Pulumi stack on first deploy, or assure {that a} complicated multi-integration agent will work end-to-end with out iteration. First deployments through Pulumi can take 10 to twenty minutes, and the OAuth wiring for Google Workspace or Salesforce information sources nonetheless requires guide setup in DataRobot.
The place Expertise are invaluable is in eliminating the category of errors that come from Cursor not understanding platform specifics: unsuitable API endpoints, lacking runtime parameter injections, incorrect dependency declarations in pyproject.toml, mixing job dev and job deploy patterns incorrectly. That class of error is the place most developer time is misplaced when constructing on a brand new platform.
Getting began
Set up the plugin in a single command:
/add-plugin datarobot-agent-skillsBrowse the complete talent set and supply at github.com/datarobot-oss/datarobot-agent-skills.
In case your workforce builds customized workflows that don’t map cleanly to the present Expertise, the repository accepts contributions. A customized talent is only a SKILL.md file with YAML frontmatter, a transparent description, and no matter helper scripts your workflow wants. Level Cursor at it and the conference handles the remaining.
The hole between “agent prototype” and “agent in manufacturing” is generally operational context. Expertise are how DataRobot solutions that hole.
