{"id":96104,"date":"2026-10-27T06:00:00","date_gmt":"2026-10-27T13:00:00","guid":{"rendered":"https:\/\/www.salesforce.com\/?p=96104"},"modified":"2026-10-26T17:32:39","modified_gmt":"2026-10-27T00:32:39","slug":"agent-fabric-catch-failures-control-ai-costs","status":"publish","type":"post","link":"https:\/\/www.salesforce.com\/news\/stories\/agent-fabric-catch-failures-control-ai-costs\/","title":{"rendered":"Salesforce Expands Agent Fabric to Automatically Stop Runaway Costs and AI Agent Failures Before They Impact Customers"},"content":{"rendered":"\n

Today, Salesforce announced Agent Evals, API Evals, and advanced cost controls for Agent Fabric<\/a>, its AI control plane for managing and governing agents across platforms. As enterprises scale AI, agents can fail silently, delivering wrong answers and racking up costs before anyone notices.\u00a0<\/p>\n\n\n\n

CIOs and AI leaders can now catch problems before they turn into customer complaints or runaway costs, with automated interventions when quality slips and hard spending limits that cap usage at budget. <\/p>\n\n\n\n

With over 1.2 billion requests handled daily, Agent Fabric brings proactive control to enterprise AI at scale.<\/p>\n\n\n\n

\u201cWhat excites us most about Agent Evals is that it doesn\u2019t stop at telling us something is wrong. When an agent\u2019s quality drops, Agent Fabric can step in automatically, alerting the right owner or pulling the agent offline before a small issue becomes a widespread customer problem. That\u2019s the missing piece for running agents at scale, and it will give us the confidence to keep expanding AI across our business. We are excited to partner with Salesforce and help shape Agent Evals Beta.\u201d \u2013 Poonam Deshpande, Director of Engineering, Digital Commerce at ASICS Digital<\/p>\n\n\n\n

As the models, APIs, costs and systems underneath agents evolve, issues can silently surface. Catching them proactively means building, maintaining, and evaluating performance continuously. Yet today fewer than half of organizations with agents evaluate them on live traffic<\/a>. Once issues are uncovered, resolution means tracking down the owner and getting approval to restrict the agent while it keeps producing harmful results and racking up token spend. With 96% of enterprises running agents on more than one platform<\/a> and out-of-the-box agents like Fin<\/a> on the rise, the need for oversight keeps growing.<\/p>\n\n\n\n

Moving from \u201ccross-your-fingers AI\u201d to continuous control<\/strong><\/h2>\n\n\n\n

To address these challenges, Salesforce is bringing continuous evaluation and automated intervention into the same control plane that enterprises already use to manage and govern their AI agents:<\/p>\n\n\n\n