Salesforce Introduces Agentforce Testing Center: First-of-its-kind

Agentforce Testing Center enables teams to test Agentforce using synthetically generated data, ensuring accurate responses and actions – with complete monitoring of usage and feedback

New Data Cloud Sandboxes and Digital Wallet enhancements enable teams to test the entire AI and data lifecycle in secure test environments while transparently managing and optimizing costs

Salesforce, the world’s #1 AI CRM, announced a new suite of agentic lifecycle management tools to automate Agentforce testing, prototype agents in secure Sandbox environments, and transparently manage usage as you scale.

AI agents are a new paradigm in software – introducing intelligent systems that can reason and act on behalf of customers and employees. But to realize the full potential of this new category of software, agents need to be tested and configured without disrupting live production environments. This new toolchain – the first of its kind in the industry – will enable teams to test, deploy, and monitor AI agents with Agentforce at scale, with confidence, enabling every enterprise to become “agent-first”.

Innovation in action: Agentforce Testing Center – built on the Salesforce Platform and integrated with Data Cloud – enables every organization to easily test and monitor AI agents so that they can deploy with confidence. New capabilities include:

AI-generated tests for Agentforce: Teams building Agentforce agents want to ensure the agent selects the right topics and actions when engaging with a customer. In addition to Agent Builder, which features a Plan Tracer for investigating the reasoning process of an agent, the new Agentforce Testing Center enables teams to test topic and action selection at scale. Using natural language instructions, Testing Center can auto-generate hundreds of synthetic interactions – such as requests a customer may make when engaging with, for example, Agentforce Service Agent – then test them in parallel to see how frequently they result in the right outcome. Teams can then use the test data to refine instructions so the expected topic is more frequently selected, improving the end customer experience.

Read More: SalesTechStar Interview with Monica Lewis, VP of Product Management at LinkedIn

Sandboxes for Agentforce and Data Cloud: Teams looking to test Agentforce need to do so in safe, isolated environments. Generally available today, Salesforce Sandboxes – mirror images of your production org’s data and configurations – now support both Data Cloud and Agentforce. By replicating the org’s data and metadata into a risk-free environment, development teams can rapidly assemble their unstructured data foundation and rigorously prototype Agentforce without fear of disrupting the business. This means that teams can now perform UAT (User Acceptance Testing) with an initial set of users to ensure that Agentforce performs the tasks that it’s intended to accomplish, then migrate those changes to production using familiar tools such as Change Sets, DevOps Center, and the Salesforce CLI that now support Data Cloud and Agentforce.

Monitoring and observability for Agentforce: With the GA of Data Cloud Sandboxes, the full Einstein Trust Layer can be tested in a secure, pre-production environment – enabling rapid configuration of Agentforce agents and Prompt Templates. Once Agentforce is live in production, new capabilities for granular insights into adoption and accuracy are now available through Agentforce Analytics and Utterance Analysis – new observability solutions built natively on Data Cloud for iteration as you move through the Agentforce Lifecycle.

Transparent usage monitoring in Digital Wallet: Data Cloud Sandbox and Agentforce usage is metered in Digital Wallet, providing customers with complete visibility into their consumption across the AI development lifecycle. New enhancements provide granular insights into what features consume credits, so that teams can uncover new trends around usage as they scale. And because Digital Wallet is integrated into the Salesforce Platform, teams can create automations to alert admins if, for example, usage exceeds a particular threshold.

Salesforce helps organizations of any size reimagine their business for the world of AI. With Agentforce, Salesforce’s trusted platform, organizations can bring humans together with agents to drive customer success—powered by AI, data, and action.