Execute the Code Extension Workflow by Using Agentforce Vibes

Author, debug, and deploy Data 360 code extensions by using natural-language prompts in Agentforce Vibes IDE. You can also use local IDEs, such as VS Code, Windsurf, and Cursor, where the Agentforce Vibes extension is enabled.

Prompts work best when you follow the natural workflow sequence—each step builds on context from the previous one. The exact wording of your prompt is flexible. Agentforce Vibes uses the built-in Data 360 skill context to interpret your intent and carry out the action.

• Make sure that you have access to a Data 360 sandbox and the Data Cloud Architect permission set. If you don’t have a sandbox, create one. See Create a Data 360 Sandbox.

• Enable code extension in Data 360 Setup by using Feature Manager. See Enable Data 360 Features in Feature Manager.

• Agentforce Vibes IDE: Set up Agentforce Vibes IDE from your org and enable it. See Set Up Agentforce Vibes IDE and Enable Agentforce Vibes IDE.

• Local IDE (For example, VS Code or Cursor):

  • Set up Salesforce CLI for Code Extension. See Set Up Salesforce CLI for Code Extension.

  • Set up Agentforce Vibes extension. See Set Up Agentforce Vibes Extension.

1. Enable skills for Agentforce Vibes if you haven’t already. See Enable Skills.

2. Update the Salesforce Skills version to the latest available version by enabling the Auto Update Skills setting. See Salesforce Skills in Agentforce Vibes.

3. Ensure that you have these Salesforce skills, which are enabled by default.

   Skill	Description
   developing-datacloud-code-extension	Guides end-to-end code extension development and deployment.
   getting-datacloud-schema	Retrieves DLO and DMO schema metadata so that you can validate object and field names before testing and deploying a code extension.

   The developing-datacloud-code-extension skill installs the Code Extension plugin for the Salesforce CLI and the Data Custom Code Python SDK automatically if they aren’t already present.

4. Before you start prompting, note these expected behaviors.

   • Agentforce Vibes can pause and ask you to review and approve certain commands before running them. For example, terminal commands or file operations that aren’t pre-approved. When prompted, review the proposed action and click Run Command to approve or Reject to cancel.
   • Agentforce Vibes can ask for your org alias during the workflow. For example, running local tests or deploying. Sometimes, it determines the org automatically by running sf org list. If prompted, provide your org alias to continue.

5. In Agentforce Vibes chat, describe each workflow action. For example, use these prompts.

   1. Initialize a code extension package.

      create new code extension script package named code_extension_pkg_1

   2. Author the script.

      Refer to @/code_extension_pkg_1/payload/entrypoint.py and modify that file to read Employee DLO and write to Employee_Hierarchy DLO. Make sure to compute values for all the fields of Employee_Hierarchy DLO.

      Agentforce Vibes uses the getting-datacloud-schema skill to retrieve schema context and the developing-datacloud-code-extension skill to update payload/entrypoint.py based on your prompt.

   3. Test locally.

      test it locally

   4. Deploy.

      deploy it

• Invoke Code Extension by Creating a Batch Data Transform

• Write and Validate Custom Scripts
• Deploy a Custom Script to Data 360 Sandbox by using CLI
• Quick Start