Enterprises with AI context layers report agent failures at more than twice the rate of those without one拥有AI上下文层的企业报告代理故障的频率是未拥有该层的企业的两倍以上。

A company builds a governed context layer specifically to stop its AI agents from confidently giving wrong answers. Once that layer is live, the company is more than twice as likely to report the failure happening — not less.一家公司构建了一个受控的上下文层，专门用于防止其AI代理自信地给出错误答案。一旦该层投入使用，该公司报告此类故障发生的可能性反而增加了一倍多，而非减少。

In the past six months, 68% of enterprises have traced a confident but wrong AI agent answer to missing or inconsistent business context. Thirty-seven percent say it happened more than once, ahead of the 32% who saw it happen only once. The figures come from a VB Pulse July 2026 survey of 101 qualified enterprises with more than 100 employees. That's up from 57% in a VB Pulse survey conducted in June. Recurring failures climbed too, from 31% then to 37% now.在过去六个月中，68%的企业将AI代理自信但错误的回答追溯到业务上下文缺失或不一致。37%的企业表示这种情况发生过不止一次，超过了仅发生过一次的32%。这些数据来自VB Pulse 2026年7月对101家拥有100多名员工的合格企业进行的调查。这一比例高于6月份VB Pulse调查中的57%。重复性故障的比例也从当时的31%上升至现在的37%。

This is the second time VB Pulse has asked enterprises this exact question, once in June and now in July. The failure rate is climbing, not falling, even as more enterprises report a governed layer in production, up from 25% in June to 32% now.这是VB Pulse第二次向企业提出这一确切问题，分别在6月和7月。尽管报告生产环境中拥有受控层的企业比例从6月的25%上升至现在的32%，但故障率仍在上升，而非下降。

How agents get context determines whether they're wrong代理获取上下文的方式决定了它们是否会出错

Every AI agent needs some way to know what the business actually means, whether a metric is defined consistently, whether a document is current. That's the operation. The challenge is that enterprises hand agents that context in very different ways, and those ways are not equally reliable.每个AI代理都需要某种方式来了解业务的实际含义，无论是指标定义是否一致，还是文档是否为最新版本。这就是操作过程。挑战在于，企业向代理提供上下文的方式各不相同，且这些方式的可靠性并不均衡。

Retrieval over documents remains the most common approach, the primary source for 31% of enterprises. But a real share of enterprises skip a structured approach altogether. Thirteen percent run agents primarily on long-context loading, feeding documents directly into the model's context window rather than retrieving them. Five percent give agents no structured context at all, just the model's general knowledge. Between them, nearly one in five enterprises are feeding agents business context by brute force or not feeding it at all.基于文档的检索仍然是最常见的方法，是31%企业的首选来源。但相当一部分企业完全跳过了结构化方法。13%的企业主要通过长上下文加载来运行代理，直接将文档输入模型的上下文窗口，而不是进行检索。5%的企业根本不为代理提供结构化上下文，仅依赖模型的通用知识。在这两者之间，近五分之一的企业要么通过暴力方式向代理输入业务上下文，要么根本不输入。

Even the leading approach can still produce a confidently wrong answer. Retrieval works by matching a question to text that looks similar in meaning. Similar wording doesn't guarantee the same meaning. Srijith Rajamohan, an AI research leader at Redis, described exactly this gap in an interview with VentureBeat earlier this year. 即使是领先的方法也可能产生自信但错误的答案。检索的工作原理是将问题与语义相似的文本进行匹配。相似的措辞并不能保证含义相同。Redis的AI研究负责人Srijith Rajamohan今年早些时候在接受VentureBeat采访时准确描述了这一差距。

"If you have a sentence like 'Rome is closer than Paris' and another that says 'Paris is closer than Rome,' and you do an embedding retrieval followed by a text search, you're not going to be able to tell the difference," Rajamohan said. "The same words exist in both sentences."“如果你有一个句子说‘罗马比巴黎近’，另一个句子说‘巴黎比罗马近’，而你进行嵌入检索后进行文本搜索，你将无法分辨其中的区别，”Rajamohan说。“两个句子中存在相同的词汇。”

Buying shifted to access control. Grading didn't follow.采购重心转向了访问控制，但评估标准并未跟进。

The way enterprises choose a retrieval system doesn't help close the gap. Access control and permissions now tie ease of data ingestion as the top selection criteria, at 24% each. It's the first time in this survey series that a governance property has led to the buying decision. Retrieval accuracy trails at 15%. The property most directly tied to a confident wrong answer isn't the property most enterprises are buying for.企业选择检索系统的方式无助于缩小这一差距。访问控制和权限设置现在与数据摄取的便捷性并列为首要选择标准，各占24%。这是该系列调查中首次出现治理属性主导采购决策的情况。检索准确性位居其后，占15%。与“自信但错误”的答案最直接相关的属性，却并非大多数企业采购时关注的重点。

Once a system is running, correctness is still how enterprises judge it. Response correctness is the primary success metric for 38% of enterprises, twice the next closest answer, security and access control at 19%. Enterprises are shifting how they buy toward governance. They're still grading success on whether the answer is right.系统运行后，正确性仍然是企业衡量其成功与否的标准。38%的企业将响应正确性作为首要成功指标，是第二名（安全和访问控制，19%）的两倍。企业在采购时正转向治理，但在衡量成功时，依然看重答案是否正确。

The companies fixing this are the ones reporting it worst那些正在解决问题的公司，反而报告了最严重的故障情况

A governed context layer is meant to fix this. It's one shared, agreed-on model of what the business's data means, that every agent and BI tool references instead of guessing on its own. Adoption is far from settled.受控上下文层旨在解决这一问题。它是一个共享且达成共识的业务数据含义模型，每个代理和BI工具都参考它，而不是自行猜测。目前其普及程度远未定型。

Thirty-two percent of enterprises run one in production. Thirty-one percent are piloting or building one right now. Twenty percent are evaluating one. Fourteen percent have no plans to, and 4% don't know.32%的企业在生产环境中运行该层。31%的企业目前正在试点或构建中。20%的企业正在评估。14%的企业没有计划，4%的企业表示不清楚。

Compare that adoption data against who's actually had the failure, and the picture inverts. Among the 91 enterprises able to say whether they'd experienced the failure at all, those running or building a governed layer report it recurring at 50%. Those without one report it at 21%.将该采用率数据与实际发生故障的情况进行对比，情况恰恰相反。在91家能够确认是否经历过此类故障的企业中，正在运行或构建受控层的企业报告故障重复发生的比例为50%。而没有该层的企业报告比例仅为21%。

A governed layer doesn't cause the failure — it's what makes the failure visible in the first place. Tracing a bad answer to a broken definition or a stale table requires a shared, governed reference point. A context layer provides that. Without one, the same wrong answer still happens — it just gets chalked up to the model, or never gets traced at all.受控层并不会导致故障，它只是让故障变得显而易见。将错误的答案追溯到错误的定义或陈旧的表格，需要一个共享的、受控的参考点，而上下文层恰好提供了这一点。没有它，同样的错误答案依然会发生，只不过要么归咎于模型，要么根本无法追溯。

The pain point predates AI by decades. Kyle Nesbit, founder of the semantic layer startup Credible Data, described it to VentureBeat last month. "It's the same pain point people have had for 30 years, the lack of governed data analysis," Nesbit said. "Now with AI, it's the same problem, but orders of magnitude more chaos and pain."这一痛点在AI出现前几十年前就已存在。语义层初创公司Credible Data的创始人Kyle Nesbit上个月向VentureBeat描述道：“这是人们30年来一直面临的痛点，即缺乏受控的数据分析。现在有了AI，问题依旧，只是混乱和痛苦程度增加了几个数量级。”

Company size sharpens the same point. Enterprises with more than 1,000 employees report recurring failures at 55%, against 30% for those between 101 and 1,000 employees. That's despite the bigger companies being less likely to have a layer already in production, 24% against 37%. More instrumentation and more people asking why a number was wrong turns up more failures, not fewer. A clean record is not evidence of a healthy context layer. It's at least as likely to be evidence that nobody's checking.公司规模进一步突显了这一点。拥有1000多名员工的企业报告重复性故障的比例为55%，而101至1000名员工的企业为30%。尽管大型企业在生产环境中拥有该层的可能性更低（24%对37%）。更多的监测和更多人去追问数字错误的原因，反而发现了更多故障，而非更少。记录清白并不代表上下文层健康，更有可能是因为根本没人去检查。

What this means for enterprises这对企业意味着什么

Here's what this adds up to for enterprises building on this layer.对于正在构建此层的企业，以下是总结。

Retrieval alone will not close the context gap. RAG remains the default context source, and nearly one in five enterprises are running agents on long-context loading or no structured context layer at all. More documents or a bigger index doesn't fix a definition that means two different things in two different systems.仅靠检索无法弥补上下文差距。RAG仍然是默认的上下文来源，近五分之一的企业通过长上下文加载或根本没有结构化上下文层来运行代理。更多的文档或更大的索引无法解决同一个定义在两个系统中含义不同的问题。

The budget is moving faster than the infrastructure is shipping. Sixty-three percent of enterprises are already building or running a governed context layer. Only 32% have actually gotten one into production. That gap is where the spend is going, not where the problem has been solved.预算的投入速度快于基础设施的交付速度。63%的企业已经在构建或运行受控上下文层，但只有32%的企业真正将其投入生产。这一差距正是资金流向的地方，而非问题已解决的地方。

A clean failure record is a red flag, not a green one. The 22% of enterprises reporting no context failure at all are not the best-governed group. They're the group least likely to be checking. The size data backs this up directly. Larger enterprises report recurring failures at nearly twice the rate of mid-market peers, despite being less likely to have a governed layer in production, not more.清白的故障记录是一个危险信号，而非良好信号。22%报告没有上下文故障的企业并非治理做得最好，而是最不可能进行检查的群体。规模数据直接印证了这一点。大型企业报告重复性故障的频率是中型企业的近两倍，尽管它们在生产环境中拥有受控层的可能性更低。

No one is planning to hand the layer to a single provider. Seventy-nine percent of enterprises intend to keep at least part of the context layer outside any one vendor's stack, split between best-of-breed tools and an explicit mix. Just 12% plan to consolidate onto a single provider's native context stack.没有人计划将该层完全交给单一供应商。79%的企业打算将上下文层的至少一部分保留在任何单一供应商的堆栈之外，通过最佳工具组合或明确的混合方式来实现。只有12%的企业计划整合到单一供应商的原生上下文堆栈中。

The finding that organizations aren't likely to hand over control to a single provider is a theme that VentureBeat has reported on consistently this year. Michael Ni, an analyst at Constellation Research, put it bluntly earlier this year when DataHub's context layer push first landed.企业不太可能将控制权交给单一供应商的发现，是VentureBeat今年一直报道的主题。Constellation Research的分析师Michael Ni在今年早些时候DataHub的上下文层推动计划首次落地时，直言不讳地指出：

 "Whoever controls runtime context, controls the AI decision layer for enterprise data," Ni said.“谁控制了运行时上下文，谁就控制了企业数据的AI决策层，”Ni说。