Salesforce Launches Agentforce 2dx

Salesforce today introduced Agentforce 2dx, the newest version of Agentforce, its digital labor platform for bringing trusted, autonomous artificial intelligence agents into the flow of work.

In this release, Agentforce is enabling proactive AI agents to work behind the scenes, without constant human oversight, to unlock new customer and employee workflows. Organizations can now integrate autonomous agents into their data systems, business logic, and user interfaces, enabling agents to anticipate business needs and dynamically take action.

Agentforce 2dx also includes low-code and pro-code tools for Salesforce developers to configure, test, and deploy Agentforce paired with advanced analytics to help teams monitor, debug, and optimize agent performance with real-time data and guidance.

Salesforce also now offers the Agentforce Developer Edition, a completely free environment where developers can prototype agents using Agentforce and explore Data Cloud, Salesforce's hyperscale data engine.

"Companies today have more work than workers, and Agentforce is stepping in to fill the gap. By extending digital labor beyond CRM, we're making it easier than ever for businesses to embed agentic AI into any workflow or application to handle routine tasks, augment employees, and connect with customers. With deep integrations across Salesforce's digital labor platform, CIOs, IT leaders, and developers can seamlessly build agents and automate work wherever it happens, driving efficiency, fueling innovation, and unlocking new opportunities in the $6 trillion digital labor market," said Adam Evans, executive vice president and general manager of Salesforce's AI Platform, in a statement.

Among the new tools in this latest version of Agentforce are the following:

• Agentforce API, to integrate Agentforce in back-end processes, other systems, and applications.
• Agentforce Invocable Actions, allowing Agentforce to be embedded within Salesforce business logic, like Flow and Apex. This allows customers to blend classic workflow automation with agentic reasoning.
• MuleSoft integrations, including MuleSoft Topic Center, which allows developers to use natural language to create Agentforce topics and actions from MuleSoft APIs; The MuleSoft API Catalog, which simplifies AI agent development by centralizing access to APIs from MuleSoft, Salesforce, and Heroku within Agentforce and provideing a secure, governed hub for admins to expand agent capabilities with pre-built topics and actions; and The MuleSoft Agentforce connector, which allows developers to integrate Agentforce into existing workflows, enabling APIs and integrations to trigger agents for data enrichment and action execution across systems.
• Agentforce Steps in Slack Workflow Builder, which enables developers to embed Agentforce into no-code automations in Slack, trigger Agentforce from Slack events, and pass Slack conversational context back to Agentforce.
• Agentforce Employee Template, to deploy Agentforce for employee use cases across Slack and Salesforce and create multiple employee agents that can be configured and deployed across any line of business.
• Agentforce Surfaces, to deliver rich content within Agentforce across all digital engagement channels and add dynamic, interactive components and media that are channel- and device-specific to better customize how Agentforce shows up across channels.
• Agentforce Cards, to embed Lightning web components within the response of Agentforce actions and reuse Salesforce components to give more context, information, and functionality to Agentforce.
• Tableau Semantics, to create clear and organized data structures for Agentforce and enrich agents with real-time business context, so they can provide more accurate insights and answers.
• Agentforce Developer Edition, a free environment for accessing Agentforce and Data Cloud.
• AI assistance in Agent Builder, so teams can put Agentforce into production with AI-powered topic and instruction creation, troubleshoot answers that Agentforce provides, and give guidance on how to improve the underlying topic and instructions.
• Testing Center, so teams can test their Agentforce configurations at scale using AI and evaluate how well Agentforce configurations are adhering to guardrails.
• CLI and VS Code Support.
• DX Inspector, to explore and understand all of the metadata and data used by Agentforce, including agent topics and actions, inside the Salesforce Sandbox and make and track changes to the metadata while configuring agents in Agent Builder through the side panel.
• Agentforce Interaction Explorer, for detailed reporting and analytics about how Agentforce is performing, from general trends down to individual session tracing, each user request, the reasoning steps associated with the response, and the recommendations.