Salesforce by OneDCX

Maintain Your Agentforce Specialist Certification for Summer ’26 Learning Objectives After completing this unit, you’ll be able to: Describe how Agent Script improves control and governance in Agentforce Builder. Explain how Agentforce Grid supports designing, testing, and managing AI workflows. Identify key metrics and troubleshooting tools in Agentforce Observability. Explain how organizations monitor and improve AI agent performance after deployment. Build More Reliable Agents with New Agentforce Builder The new Agentforce Builder changes how teams build and manage AI agents. Instead of relying only on natural language prompts, builders can now use Agent Script—a structured language that combines deterministic logic with large language model (LLM) reasoning. Deterministic logic follows defined paths and rules, such as conditions and transitions, while LLM reasoning adds flexibility when interpreting and responding to requests. With Agent Script, teams can create more reliable and co...

  Agentforce Specialist Certification Maintenance (Summer '25) Control Agent Access to Topics and Actions with Filters As of March 2025,   you can now create filters for topics and actions in Agentforce, ensuring agents can access them only when specific conditions are met. Previously, agents had access to all added topics and actions without restriction. Now, agents’ access to topics and actions can be controlled using filter and context variables. Filters help you securely manage agent access to sensitive or conditional workflows. This is especially useful for Service agents on customer channels. Once you’ve configured and customized the Customer Verification topic to align with your security requirements, you can create filters to control access to topics and actions that perform tasks on a user’s behalf. For example, you might unlock a Case Management topic only when the user’s case status is Escalated, or allow an agent to initiate a return only if the user’s order w...

  Give Users Read-Only Access to Recipes Improve data transparency for your team while maintaining control over data processes. By granting users read-only access to recipes, you allow users to view the details of recipes and understand dataset content without the risk of accidental modifications. Assign colleagues the permission: Recipes View Only. With this permission, when users visit Data Manager, they see only the Recipes option. They can open recipes and view their content but can’t edit, run, or delete them. From Setup, in the Quick Find box, search for and select  Permission Sets . Select or create a permission set. Click  System Permissions , and select  Recipes View Only . When users visit Data Manager and click a recipe name, they can view the recipe’s details in the recipe editor. Use Version Control When Saving Dashboard Component Changes Enhance your ability to manage and track changes in dashboard components by implementing version control. Users can n...

  Learn What’s New in Data Cloud Setup and Administration for Winter ’25 Do More with New Data Types in Data Cloud To enhance flexibility, you can now use the email, URL, phone, percent, and Boolean data types in Data Cloud. These data types expand data compatibility and interoperability with external systems that interface with Data Cloud. Data Type Description Email Stores email addresses. The email data type is modeled on the text data type. You can use any valid text value for ingestion into an email data type field. Data Cloud doesn’t validate the format. URL Stores URL values. Data Cloud doesn’t parse or interpret the ingested URL value. It also doesn’t validate the value for correctness. Data Cloud doesn’t store any metadata related to the URL. Phone Stores phone numbers. Data Cloud doesn’t validate the format of the phone number. The phone data type is modeled on the text data type. Any valid text value is accepted for ingestion into a phone data type field. Percent Holds p...