• DISCOVERY
  • EXECUTION
  • MONITORING
  • HUMAN

How to trigger automated model retraining with your AI

Connect Dataiku DSS to your AI client to manage automation. Once linked, you can trigger specific scenarios to refresh models or rebuild data flows.

Ask AI about this page

Short answer

Can I trigger Dataiku scenarios using my AI?

Yes. You can list available scenarios to see what's ready and then tell your agent to run a specific one. This lets you refresh models or rebuild pipelines without opening the Dataiku interface.

The outcomes

What your AI handles

The AI manages the execution of your Dataiku workflows.

DISCOVERY

Find available scenarios

The AI scans your Dataiku instance to identify which automation scenarios are ready to go.

EXECUTION

Run specific scenarios

Your agent triggers the exact scenario needed to rebuild a pipeline or retrain a model.

MONITORING

Track job status

The AI monitors the progress of the scenario it just started so you know when the model is updated.

HUMAN

Manual intervention

You still need to manually handle any errors or logic changes within the Dataiku DSS interface.

The workflow

What your AI does when <the thing arrives>.

The AI acts as the bridge between your chat interface and your Dataiku environment.

  1. Identify scenarios

    The AI scans your Dataiku project to see which automation scenarios exist.

    list_scenarios

  2. Select target

    Based on your request, the AI picks the specific scenario meant for retraining or data updates.

    list_scenarios

  3. Trigger execution

    The AI sends the command to start the selected scenario in Dataiku.

    run_scenario

  4. Confirm completion

    The AI reports back once the scenario has finished running.

    run_scenario

Try it

Copy these to start.

Use these prompts to begin interacting with Dataiku.

Starting points

Replace the bracketed text with your actual Dataiku project or scenario names.

Dataiku Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_omB2MsN4Y1V0ZX0dD6ibopTA1n2aAb9aFGAtDQOY/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — Dataiku capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "dataiku-dss-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_omB2MsN4Y1V0ZX0dD6ibopTA1n2aAb9aFGAtDQOY/mcp"
    }
  }
}
Copy into chat04

  • List all available scenarios in my Dataiku project.

  • Run the 'model_retrain_v2' scenario now.

  • Find the scenario used for rebuilding the production pipeline.

  • Trigger the scenario named 'daily_data_refresh'.

  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Start here

Connect Dataiku DSS once, then ask.

One connection gives your AI access to your Dataiku scenarios. Your credentials stay encrypted and secure.

Connect Dataiku DSS to your AI

FAQ

How this task behaves

  • 01

    Can the AI create new scenarios in Dataiku?

    No. The AI can only list and run existing scenarios.

  • 02

    Can the AI change the logic inside a scenario?

    No. The AI cannot edit the code or the steps within a Dataiku scenario; it only triggers them.

  • 03

    How does the AI know which scenarios are available?

    It uses the list_scenarios tool to pull the current list from your Dataiku instance.

  • 04

    Will the AI automatically retrain my model if data changes?

    No. The AI only runs a scenario when you specifically ask it to via your AI client.

  • 05

    Can I see if a scenario failed?

    Yes. After the AI runs a scenario, it will report the outcome of that execution.

  • More questions about Dataiku DSS? The Connector page answers them. See everything the Dataiku DSS Connector can do

Connect Dataiku to Claude, Cursor, ChatGPT & more