Salesforce Releases Agent Evals and API Evals
Salesforce today unveiled Agent Evals and API Evals to help companies scale AI agents.
Agent Evals automatically generate tests before deployment, then evaluate agents, large language models, and Model Context Protocols servers in production against defined quality thresholds. When results fall short, they trigger predefined interventions, including the Agent Kill Switch, with approvals where required.
API Evals automatically generates functional and performance tests from API specifications, catching breaking changes before they reach production.
Together, evaluation and governance help teams assess whether agents complete tasks correctly, use the right tools, operate efficiently, and follow security policies.
"Enterprises can only scale agents as fast as they can keep them accurate and on budget. Today, spotting a wrong answer or a spending spike is one job, and stopping it is another. Agent Fabric unifies them, bringing evaluations, cost controls, and intervention together so teams can contain issues instantly and scale agents with confidence," said Andrew Comstock, senior vice president and general manager of MuleSoft and Agent Fabric, in a statement.
Salesforce also updated Agent Fabric, which automatically discovers and governs agents across major AI platforms. Two updates extend that further, to agents running in internal and third-party environments, and to APIs managed on gateways from other vendors.
Custom Agent Scanner extends Agent Fabric's automated discovery to internal environments, systems behind firewalls, and third-party platforms. Users can build custom scanners to discover and catalog agents, models, MCP servers, and APIs in the Agent Registry without registering each asset manually. With Open Policies for Federated API Gateways, users can discover, enforce, and track API policies across gateways from Azure, Apigee, and Kong, applying a policy such as IP allow listing or rate limiting across all of them in one action instead of one at a time.