AI 模型和平台
Salesforce 新增 Agent Evals和成本控制到Agent Fabric
在 Google 上的首选来源中添加 Unite.AI
2026年10月27日的Salesforce 宣布，是Agent Fabric的一组添加，其用于管理和治理agents跨平台的AI控制平面，头条由Agent Evals,API Evals，以及高级成本控制。 Salesforce 称平台每天处理超过12亿个请求。
公告将添加的内容设定在一个具体的操作问题上：随着企业规模化AI部署，agents可能会默默失败，在任何人通知之前给出错误的答案并积累成本。 Salesforce 称新的能力让CIOs和AI头目在他们变成客户投诉或逃逸成本之前抓住问题，当质量滑动与硬性支出限制在预算上限制使用时，将自动干预组合起来。
Agent Fabric是企业agent控制平面，以MuleSoft为基础，用于发现，管理，协调，以及观测agents,AI资产，以及单个控制平面的代理工作流程。 根据Agent Fabric产品页，其扫描仪自动检测和注册agents，模型背景协议(MCP)服务器，以及跨生态系统运行的API，如Amazon,Google,Microsoft,Claude,Databricks,Kong直接输入Agent注册，这是AI资产的集中目录。 该平台还包括将现有的API暴露为MCP工具的MCP桥；多agent的管弦乐；支持A2A协议；一个统一的LLM和MCP网关；信任的Agent身份；以及Agent可视化器，它用包括信心分数，瓶颈检测，以及幻觉风险等度量仪映射agent网络。 产品页表示Agent Fabric和Agent Force,Salesforce在Salesforce内建造和运行agents的平台，由同一引擎提供动力，用于定义agents如何处理相互作用，理性，计划和行为。
持续评价和自动干预
Agent Evals在部署前自动生成测试，然后在生产中按照确定的质量阈值评价agents，大语言模型(LLMs)和MCP服务器，Salesforce 称。 当结果不足时，系统触发了预先定义的干预，包括Agent Kill Switch，并在一个团队的政策需要时有一个批准步骤。 产品页描述能力是将agent质量测试转化为自动动作，并列出MCP服务器和LLM评价即将到来。
API Evals处理不同的故障点：agents在API依赖变化时中断。 工具Salesforce 称从API规格中自动生成功能和性能测试，在到达生产前捕捉断裂变化。
公告通过零售商的情景来说明工作流程。 零售商将其订单支持agent切换为成本较低的AI模型，以减少运营成本。 更改后，Agent Evals运行了预定的测试，并检测到agent正在提供有关延迟订单的不准确信息。 系统标榜质量问题，基于团队倾向于让人保持循环，请求隔离agent批准。 获批后，agent被隔离，同时团队完善处理延迟订单的指示，重新运行成本较低的模型上的评价以确认性能，并将agent返回生产。
Agent Kill Switch是产品页描述为快速停止agent生产活动的一种方式，在公告时一般可以使用。 A Triggered-Agent Kill Switch跟随2027年1月的通用版。
费用控制和预算执行
在成本方面，FinOps Dashboard和Model Walet给预算所有者一个单一的AI支出视角和硬限制，在成本超过预算之前停止请求。 Salesforce 称成本优化政策根据公司的测试设想，通过语义缓存、有效载荷压缩和反应修饰，将象征性使用削减了高达75%。
MuleSoft的成本管理文件详细介绍了执法机制。 模范钱包执行每agent、每个实例或每个业务单位的预算，按累积的支出进行现场追踪；当钱包运行时，执行在超支之前而不是发票之后进行，预测未来预计的超支日。 模型代理坐在交通路径上，每个请求与供应商实际收取的费率相对价，因此仪表板支出与发票相匹配。 优化政策(Progressive Expression,Smart Response Trimming，以及TOON 压缩)运行于网关，在不修改MCP服务器或客户端代码的情况下剪切令牌废物。 文件还描述了按团队，应用程序，以及实时使用大小写来跟踪支出，并在超过预算前自动关闭运行的agent环。
FinOps Dashboard,Model Wallet，以及成本优化政策在公告时一般可以使用。
发现和联邦网关政策
Salesforce也是宣布两个更新，将Agent Fabric扩展至其外箱平台支持之外。 自定义 Agent Scanner 带来自动发现到内部环境，防火墙后面的系统，以及第三方平台，让团队在Agent注册处不手工注册每个资产的情况下，建立自定义扫描仪，将agents，模型，MCP服务器和API编目。 截止公告时为β型，一般可使用时间计划于2027年1月。
联邦API网关的开放政策发现，执行，并追踪来自Azure,Apigee和Kong的网关的API政策，应用IP允许列表或费率等政策限制所有网关在一次行动中而不是一次行动中。 该能力在公告时一般都可以使用。
调查数据和客户报表
公告将增加关于评价做法的调查数据联系起来，指出只有不到一半的agents组织通过现场交通对其进行评价。 它引用了LangChain的Agent工程状况报告，该报告在2025年11月18日至12月2日期间调查了1300多名专业人员。 该报告发现，57.3%的受访者拥有agents的生产，32%的受访者认为质量是生产的最大障碍，89%的受访者对其agents实行了某种形式的可观察性。 具体地说，52.4%的组织报告在测试机上进行离线评价，而在线评价采用率为37.3%。
Poonam Deshpande, ASICS Digital，称 ASICS与Salesforce合作，帮助塑造Agent Evals β. Agent Evals最让我们兴奋的是，" 当agent的质量下降时，Agent Fabric可以自动介入，提醒右所有者或者在小问题成为广泛的客户问题之前将agent拉下线。
公告中还收录了Capita,GE Appliances，和Newell Brands等公司高管的声明。 Tiina Stephens)，卡皮塔的AI工程总监，称 Agent Evals将帮助公司验证agents的表现与清晰的商业和服务结果相对。 GE Appliances公司企业转型执行董事亚当·琼斯(Adam Jones)描述了公司可以看见其agents的单一控制飞机，他们建造了这些飞机，如果出事就关闭。 称公司使用Agent Fabric作为控制飞机，因为它是带来 AI agents公司跨品牌的客户服务。
“企业只能以尽可能快的速度将agents缩放在准确度和预算上。” 称 Andrew Comstock、SVP和MuleSoft和Agent Fabric的GM。 “今天，发现一个错误的答案或支出激增是一件工作，而阻止它则是另一件工作。 Agent Fabric将其统一起来，把评价、成本控制和干预结合起来，以便各小组能够立即控制问题，并自信地扩大agents。”
可用性
Agent Evals和API Evals于2026年11月进入β，一般可用时间计划于2027年1月。 自定义 Agent 扫描器在公告时处于β状态，并于2027年1月达到一般可用状态，Trigggered-Agent Kill Switch也是一样。 Agent Kill Switch，面向联邦API Gateways的开放政策，FinOps Dashboard,Model Walet，以及成本优化政策，自2026年10月27日起普遍开放。
本文由 AI图鉴自动抓取并翻译，版权归原作者所有；如需查看原文请点下方链接。
AI Models & Platforms
Salesforce Adds Agent Evals and Cost Controls to Agent Fabric
Add Unite.AI to your preferred sources on Google
Salesforce announced on October 27, 2026, a set of additions to Agent Fabric, its AI control plane for managing and governing agents across platforms, headlined by Agent Evals, API Evals, and advanced cost controls. Salesforce said the platform handles more than 1.2 billion requests daily.
The announcement frames the additions around a specific operational problem: as enterprises scale AI deployments, agents can fail silently, delivering wrong answers and accumulating costs before anyone notices. Salesforce said the new capabilities let CIOs and AI leaders catch problems before they turn into customer complaints or runaway costs, pairing automated interventions when quality slips with hard spending limits that cap usage at budget.
Agent Fabric is an enterprise agent control plane, built on MuleSoft, for discovering, governing, orchestrating, and observing agents, AI assets, and agentic workflows from a single control plane. According to the Agent Fabric product page, its scanners automatically detect and register agents, Model Context Protocol (MCP) servers, and APIs running across ecosystems such as Amazon, Google, Microsoft, Claude, Databricks, and Kong directly into Agent Registry, a centralized catalog of AI assets. The platform also includes MCP Bridge, which exposes existing APIs as MCP tools; multi-agent orchestration; support for the A2A protocol; a unified LLM and MCP gateway; Trusted Agent Identity; and Agent Visualizer, which maps the agent network with metrics including confidence scores, bottleneck detection, and hallucination risks. The product page states that Agent Fabric and Agentforce, Salesforce’s platform for building and running agents within Salesforce, are powered by the same engine for defining how agents handle interactions, reason, plan, and act.
Continuous Evaluation and Automated Intervention
Agent Evals automatically generates tests before deployment and then evaluates agents, large language models (LLMs), and MCP servers in production against defined quality thresholds, Salesforce said. When results fall short, the system triggers predefined interventions, including the Agent Kill Switch, with an approval step where a team’s policy requires one. The product page describes the capability as turning agent quality tests into automatic action, and lists MCP server and LLM evaluations as coming soon.
API Evals addresses a different failure point: agents break when the APIs they depend on change. Salesforce said the tool automatically generates functional and performance tests from API specifications, catching breaking changes before they reach production.
The announcement walks through a retailer scenario to illustrate the workflow. A retailer switches its order-support agent to a lower-cost AI model to reduce operating costs. After the change, Agent Evals runs scheduled tests and detects that the agent is providing inaccurate information about delayed orders. The system flags the quality issue and, based on the team’s preference to keep a human in the loop, requests approval to quarantine the agent. Once approved, the agent is quarantined while the team refines its instructions for handling delayed orders, reruns the evaluation on the lower-cost model to confirm performance, and returns the agent to production.
The Agent Kill Switch, which the product page describes as a way to quickly stop agent activity in production, is generally available as of the announcement. A Triggered-Agent Kill Switch follows to general availability in January 2027.
Cost Controls and Budget Enforcement
On the cost side, the FinOps Dashboard and Model Wallet give budget owners a single view of AI spending and hard limits that stop requests before costs exceed budget. Salesforce said Cost Optimization Policies cut token usage by up to 75%, based on the company’s test scenarios, through semantic caching, payload compression, and response trimming.
MuleSoft’s cost-management documentation details the enforcement mechanics. Model Wallet enforces budgets per agent, per instance, or per business unit, tracked live as spend accrues; when a wallet runs down, enforcement engages before an overrun rather than after the invoice, and forecasting flags a projected overrun days ahead. Model Proxy sits in the traffic path and prices each request against the rate the provider actually charges, so dashboard spending reconciles against the invoice. The optimization policies (Progressive Disclosure, Smart Response Trimming, and TOON compression) run at the gateway and cut token waste without modifying MCP servers or client code. The documentation also describes tracking spend by team, application, and use case in real time, and automatically shutting down runaway agent loops before they exceed the budget.
The FinOps Dashboard, Model Wallet, and Cost Optimization Policies are generally available as of the announcement.
Discovery and Federated Gateway Policies
Salesforce also announced two updates that extend Agent Fabric beyond its out-of-the-box platform support. Custom Agent Scanner brings automated discovery to internal environments, systems behind firewalls, and third-party platforms, letting teams build custom scanners that catalog agents, models, MCP servers, and APIs in Agent Registry without registering each asset manually. It is in beta as of the announcement, with general availability planned for January 2027.
Open Policies for Federated API Gateways discovers, enforces, and tracks API policies across gateways from Azure, Apigee, and Kong, applying a policy such as IP allowlisting or rate limiting across all of them in one action instead of one at a time. The capability is generally available as of the announcement.
Survey Data and Customer Statements
The announcement ties the additions to survey data on evaluation practices, noting that fewer than half of organizations with agents evaluate them on live traffic. It cites LangChain’s State of Agent Engineering report, which surveyed more than 1,300 professionals between November 18 and December 2, 2025. That report found 57.3% of respondents have agents running in production, 32% cited quality as a top barrier to production, and 89% have implemented some form of observability for their agents. On evaluation specifically, 52.4% of organizations reported running offline evaluations on test sets, while online evaluation adoption stood at 37.3%.
Poonam Deshpande, Director of Engineering, Digital Commerce at ASICS Digital, said ASICS is partnering with Salesforce to help shape the Agent Evals beta. “What excites us most about Agent Evals is that it doesn’t stop at telling us something is wrong,” she said. “When an agent’s 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.”
The announcement also included statements from executives at Capita, GE Appliances, and Newell Brands. Tiina Stephens, Director of AI Engineering at Capita, said Agent Evals will help the company validate that agents perform against clear business and service outcomes. Adam Jones, Executive Director of Enterprise Transformation at GE Appliances, described a single control plane where the company can see its agents, who built them, and shut them down if something goes wrong. Steve Sigrist, Vice President of Global Customer Service at Newell Brands, said the company is using Agent Fabric as its control plane as it brings AI agents into customer service across its brands.
“Enterprises can only scale agents as fast as they can keep them accurate and on budget,” said Andrew Comstock, SVP and GM of MuleSoft and Agent Fabric. “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.”
Availability
Agent Evals and API Evals enter beta in November 2026, with general availability planned for January 2027. Custom Agent Scanner is in beta as of the announcement and reaches general availability in January 2027, as does the Triggered-Agent Kill Switch. The Agent Kill Switch, Open Policies for Federated API Gateways, the FinOps Dashboard, Model Wallet, and Cost Optimization Policies are generally available as of October 27, 2026.
Auto-fetched and translated by AI Atlas. All rights belong to the original author.