{"version":1,"type":"story","url":"https://digestai.news/story/salesforce-adds-agent-evals-and-cost-controls-to-agent-fabric-for-ente","json":"https://digestai.news/story/salesforce-adds-agent-evals-and-cost-controls-to-agent-fabric-for-ente.json","markdown":"https://digestai.news/story/salesforce-adds-agent-evals-and-cost-controls-to-agent-fabric-for-ente.md","slug":"salesforce-adds-agent-evals-and-cost-controls-to-agent-fabric-for-ente","headline":"Salesforce adds Agent Evals and cost controls to Agent Fabric for enterprise AI","summary":"Salesforce announced new features for Agent Fabric on October 27, 2026, targeting enterprise AI governance. The platform, which handles over 1.2 billion daily requests, now includes **Agent Evals** to automatically test agents and models in production, triggering interventions like the **Agent Kill Switch** when quality drops. **API Evals** detects breaking API changes before they reach production, while **Cost Controls** enforce budget limits via the **FinOps Dashboard** and **Model Wallet**, cutting token usage by up to 75% through caching and compression. These tools aim to prevent silent failures, cost overruns, and customer complaints by unifying evaluation, monitoring, and spending controls in one system.\n\nThe updates follow survey data from LangChain’s 2025 report, which found only 37.3% of organizations evaluate agents on live traffic. Salesforce cites customer feedback, including from ASICS Digital, Capita, and GE Appliances, highlighting demand for automated quality checks and budget enforcement. Most features are now generally available, with **Agent Evals** and **Custom Agent Scanner** entering beta in November 2026 and full release in January 2027.","keyPoints":["Agent Fabric now auto-tests agents and models in production, triggering interventions if quality falls below thresholds","Cost Controls enforce budget limits, cutting token usage by up to 75% via semantic caching and response trimming","API Evals detects API changes before they break agent workflows, with general availability in January 2027"],"whyItMatters":"For enterprises scaling AI agents, these tools address critical pain points: silent failures, unchecked costs, and lack of observability. By unifying governance, monitoring, and spending controls, Salesforce reduces operational risks and accelerates trustworthy AI deployment at scale.","category":{"slug":"enterprise","name":"Enterprise & Industry","url":"https://digestai.news/category/enterprise"},"entities":{"companies":["Salesforce","LangChain","ASICS Digital","Capita","GE Appliances","Newell Brands"],"models":[],"people":["Poonam Deshpande","Tiina Stephens","Adam Jones","Steve Sigrist","Andrew Comstock"]},"firstPublishedAt":"2026-10-27T13:29:18Z","updatedAt":"2026-10-27T13:29:18Z","sourceCount":1,"hasPrimarySource":false,"sources":[{"outlet":"Unite.AI","title":"Salesforce Adds Agent Evals and Cost Controls to Agent Fabric","url":"https://unite.ai/salesforce-adds-agent-evals-and-cost-controls-to-agent-fabric","publishedAt":"2026-10-27T13:29:18Z","type":"press","primary":false,"lead":true}],"sourceNotes":null,"discussions":[],"thread":null,"cite":{"text":"Digest AI, \"Salesforce adds Agent Evals and cost controls to Agent Fabric for enterprise AI\", 27 October 2026, https://digestai.news/story/salesforce-adds-agent-evals-and-cost-controls-to-agent-fabric-for-ente","publisher":"Digest AI","title":"Salesforce adds Agent Evals and cost controls to Agent Fabric for enterprise AI","datePublished":"2026-10-27T13:29:18Z","url":"https://digestai.news/story/salesforce-adds-agent-evals-and-cost-controls-to-agent-fabric-for-ente"},"generatedBy":"Written by Digest AI's editorial model from the linked sources; the sources are the record.","license":"Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse"}