在 101 家企业中，为 AI 代理提供业务上下文的基础设施正以快于信任建立的速度构建。检索增强生成（RAG）已是默认的上下文来源，提供者原生检索悄然超越了定义该品类的专用向量数据库——然而，大多数企业已经目睹其代理因缺失或不一致的上下文而给出自信却错误的答案。一个受控语义层正作为修复方案浮现，但大多数仍在构建中；领域正汇聚于混合检索；即便提供者原生工具在实践中领先，多数受访者仍表示打算保留最佳组合工具。其结果便是一个“上下文缺口”——代理听起来权威十足，却运行在所有者尚未完全信任的基础之上。

VentureBeat 本次 Pulse Research 聚焦企业 RAG 与上下文层：什么为 AI 代理提供业务上下文，企业运行哪些检索系统，如何采购和衡量它们，架构走向何方，以及——最具揭示性的是——这种上下文已经在多大程度上辜负了他们。

核心发现正是上下文缺口——即企业代理回答时的自信程度与其底层上下文可靠性之间的距离。大多数企业（57%）报告称，在过去六个月内，其 AI 代理曾产生过自信而错误的答案，并追溯至缺失或不一致的业务上下文，其中超半数的企业表示不止一次发生。这并非边缘失败：检索是 38% 企业的主要上下文来源，领先于任何其他方法，因此当检索单薄或不一致时，它所导致的错误就披上了代理的权威外衣。修复这一问题的设施正在构建——58% 的企业已在运行或正在构建受控语义层——但对多数企业而言，它尚未投产。

在此之下，市场正朝着令人意外的方向整合。提供者原生检索——OpenAI 文件搜索（40%）和 Google Vertex AI 搜索（38%）——已经领先于所有专用向量数据库，企业预期到 2026 年底混合检索将占据主导（34%）。然而，多数（36%）表示打算保留最佳组合的独立工具，而非整合到单一提供者的原生上下文栈上，同时绝大多数（57%）计划在一年内切换或增加提供者。声称的偏好与实际行动正背道而驰——市场一边购买提供者原生方案，一边坚称希望保持独立性。

调查方法

VentureBeat 本次调查是其持续进行的 Pulse Research 系列的一部分。本调查聚焦企业 RAG 基础设施和上下文层——为 AI 代理提供数据的检索系统、语义层和上下文来源。回复筛选自员工数超过 100 人的组织（n=101）；调查未收到 100 人及以下组织的回复，因此全量样本均符合条件。所有回复均来自 2026 年第二季度的单次调查（6 月），因此报告为横截面读数，不推断逐月趋势。部分问题允许多选，其比例之和可能超过 100%。

按组织规模，样本集中于中端市场：251–1,000 名员工（31%）和 101–250 名员工（31%）占比最高，之上为 1,001–5,000 人（20%）、5,001–10,000 人（12%）及 10,001 人以上（7%）。按角色涵盖经理（39%）、个人贡献者（27%）、高管层（16%）以及副总裁和总监（14%）；在采购权限方面具有买方可信度，46% 为最终决策者，另有 26% 为推荐者或影响者。技术/软件是最大的行业（20%），其次是医疗/生命科学（11%），然后广泛分布于零售、运输、金融服务、制造和教育等领域。

样本量为 101，属中等规模，应被解读为方向性信号而非精确测量；此为自选样本，并非概率样本。最好将其理解为来自积极搭建 RAG 和上下文基础设施的组织的视角，而非来自最大规模的运营方。

发现 1：自信而错误

超过半数已将代理错误追溯到不良上下文

我们询问企业是否在过去六个月内，将代理自信但错误的答案追溯到缺失或不一致的业务上下文。大多数企业回答是。

发现 1 —— 自信而错误

31% 的受访者表示，其 AI 代理曾给出自信但错误的答案并追溯到不良上下文，且不止一次——一种反复发生的故障

28% 的受访者报告未发现此类故障

10% 的受访者未在业务数据上运行代理；另有 5% 不追溯该层面的根本原因

这是本报告的决定性数字。大多数企业（57%）已经遇到过 AI 代理给出自信但错误的答案，并将其追溯到不良上下文——错误指标、过时定义或缺失文档——其中超半数的企业不止一次遭遇。仅 28% 报告无此类故障，一小部分要么未在业务数据上运行代理，要么未细致追踪根本原因。

这种故障模式具体且危险：模型并非明显产生幻觉；它之所以自信出错，是因为供给它的上下文单薄或不一致。本报告中的其他所有内容——企业检索什么、如何治理以及计划构建什么——均由此问题衍生。

发现 2：RAG 已是默认上下文来源

检索为代理提供数据的方式远超其他方法

我们询问企业 AI 代理主要使用什么来理解其数据。检索以明显优势领先。

发现 2 —— RAG 已是默认上下文来源

38% 依赖对文档或向量索引的检索（RAG）——占据主导地位的来源

21% 使用受控语义层或本体——共享的业务定义和关系

14% 采用因使用场景而异的混合方式

10% 使用对实时系统的直接查询（SQL、API、MCP）；6% 使用长上下文加载，2% 则依赖模型通用知识

10% 尚未让代理作用于企业数据

检索是企业上下文的骨干。对 38% 的组织而言，基于文档或向量索引的 RAG 是代理理解业务的主要方式——几乎是下一个方式（受控语义层或本体，21%）的两倍。混合方法（14%）、直接实时系统查询（10%）和长上下文加载（6%）填补了其余部分，仅 2% 让代理仅依赖模型通用知识运行。结合发现 1，这种集中度意义重大：因为如此之多的企业上下文流经检索，检索的质量就是答案的质量。当 RAG 成为默认来源，单薄的检索并非边缘案例——而是主要故障面。

值得注意的是，这些回答中缺少一种方法：定制模型权重，即微调。当前所有主流业务上下文来源均在运行时注入。我们最近一次对微调的直接度量来自 4–5 月的调查波次（一项独立调查，n=136），其中微调能力在模型选择的六个因素中排名末位，仅占 5%——即便该样本中仍有 26% 将微调和定制列为他们预期增长的投资。微调已退出主要选择对话；上下文注入是企业让代理了解其业务的方式。

发现 3：提供者原生检索已领先向量数据库

OpenAI 文件搜索与 Vertex AI 搜索超越专用工具

我们询问企业当前在生产环境中运行哪些检索系统。答案有利于模型提供者和超大规模云商，而非专业厂商。

发现 3 —— 提供者原生检索已领先向量数据库

40% 使用 OpenAI 检索或文件搜索；38% 使用 Google Vertex AI 搜索——使用最多的两个系统

20% 使用 Elasticsearch 或 OpenSearch；12% 使用基于 Postgres 的 pgvector

各有 12% 使用 Weaviate，领先于 Qdrant（10%）、Pinecone（9%）和 Milvus（6%）——纯向量数据库

10% 运行定制的内部检索栈

13% 完全没有在生产中运行 RAG 系统

专用向量数据库已不再是 RAG 栈的中心。OpenAI 文件搜索（40%）和 Google Vertex AI 搜索（38%）领先——提供者原生和超大规模云商原生检索——超越所有专用向量数据库。在专业厂商中，使用最多的乃是企业因其他原因已在运行的方案（Elasticsearch/OpenSearch，20%）以及开源嵌入式选项（pgvector，12%）；定义该品类的纯向量数据库——Weaviate、Qdrant、Pinecone、Milvus——各自处于个位数至低两位数。值得注意的是，13% 的企业表示仍完全未在生产中运行 RAG。与并行基础设施浪潮中的平台类似，企业正倾向于使用与其已购工具捆绑的检索方案。

这一发现形态在第二季度两次调查波次中保持一致。在 4–5 月（n=161），提供者内置检索同样在用量上领先，而所有专用向量数据库依然边缘化——使用最多的独立向量数据库在该样本中峰值仅为 8%——混合、多元的未来已是共识预期（34% 预期混合检索将主导，另有 29% 预期按使用场景采用多种架构）。两次波次，一致的图景：创造“向量数据库”这一术语的品类正被企业已购平台所吸纳。

发现 4：但他们声称想保留最佳组合

多数抗拒整合到提供者原生栈上

我们询问，随着模型提供者将检索、记忆和编排捆绑到其平台中，企业将如何应对。他们声称的意图与当前使用情况相悖。

发现 4 —— 但他们声称想保留最佳组合

36% 计划保留最佳组合的独立工具——独立的向量数据库、评估、编排

21% 计划整合到单一模型提供者的原生上下文栈上

21% 预期混合——部分工作负载使用提供者原生运行时，其他使用独立工具

14% 尚无明确方向

9% 计划自建并掌控自己的上下文层

这便是栈的核心张力所在。即便提供者原生检索在实践上领先（发现 3），仍有相对多数的企业（36%）表示打算保留最佳组合的独立工具，而非整合到提供者原生上下文栈上——远高于计划整合的 21%。另有 21% 预期混合模式，9% 打算自建并拥有该层。企业实际运行的内容与其声称想要的之间的差距，是该品类的战略问题：他们正因便利而采用捆绑检索，同时声称将保持独立性。哪种冲动会胜出——提供者捆绑包的吸引力还是对模块化控制的声称偏好——将比任何单一工具更能塑造检索市场。

发现 5：混合检索是共识性赌注

纯向量检索已被视为不足

我们询问企业预期到 2026 年底哪种检索架构将主导其生产 RAG 系统。领域正在汇聚——但仍有大量份额不确定。

发现 5 —— 混合检索是共识性赌注

34% 预期到 2026 年底，混合检索——嵌入结合重排序和访问控制——将占主导

14% 预期以工具优先或长上下文检索，不再使用专用向量层

13% 预期按使用场景选择多种架构

12% 不预期大规模 RAG 部署；11% 预期纯向量检索

架构正稳定于混合形态。三分之一（34%）预期到 2026 年底，混合检索——嵌入结合重排序和访问控制——将主导其生产系统，是预期纯向量检索胜出者（11%）的三倍。这是一个显著信号：开启该品类的纯向量搜索方法已单独被视为不足，被添加重排序以提升准确性、添加访问控制以提升治理的管道所取代——正是缺乏这些访问控制导致了发现 1 中的故障。很能说明问题的是，第二大的答案是不确定：17% 直接不知道，另有 14% 预期完全超越专用向量层，转向工具优先或长上下文检索。共识不在于单一工具，而在于分层管道——且尚未完全成型。

发现 6：受控上下文层正在构建中

大多数正在运行或构建语义层——很少投产

我们询问企业是否使用受控语义或上下文层，为代理和 BI 提供对数据的共享理解。多数正在路上，到位者更少。

发现 6 —— 受控上下文层正在构建中

34% 正在试点或构建受控语义层

25% 已在生产环境中运行

17% 尚未使用，但正在积极评估

15% 尚无当前计划

上下文缺口的修复方案正在建造中。远超过半数企业（58%）要么已在生产中运行受控语义层（25%），要么正在试点和构建（34%），另有 17% 正在积极评估——这意味着四分之三的企业以某种形式涉足这一概念。但比例说明问题：正在构建的比已交付的更多，因此对多数企业而言，能阻止发现 1 中“自信但错误”故障的共享、受控定义层仍是未竟之工。语义层是行业对不一致上下文的回应；本次调查恰好捕捉到其中途建造的状态，雄心远在生产之前。

发现 7：购买时看重摄取和简洁性，运行时监控看重正确性

选择看重可操作性；监控看重正确性和安全性

我们询问企业在选择检索系统时最看重什么，以及系统运行后他们跟踪什么。两个答案都偏向实用。

发现 7 —— 购买时看重摄取和简洁性，运行时监控看重正确性

Across 101 enterprises, the infrastructure that feeds AI agents their business context is being built faster than it can be trusted. Retrieval-augmented generation is already the default context source, and provider-native retrieval has quietly overtaken the dedicated vector databases that define the category — yet a majority of enterprises have already watched their agents produce confident, wrong answers traced to missing or inconsistent context. A governed semantic layer is emerging as the fix, but most are still building it; the field is converging on hybrid retrieval; and even as provider-native tools lead in practice, a plurality say they intend to keep best-of-breed. The result is a context gap — agents that sound authoritative running on a foundation their owners do not yet fully trust.

This wave of VentureBeat Pulse Research examines the enterprise RAG and context layer: what feeds AI agents their business context, which retrieval systems enterprises run, how they buy and measure them, where the architecture is heading, and — most revealingly — how often that context is already failing them.

The central finding is a context gap — the distance between how confidently enterprise agents answer and how reliable the context beneath them actually is. A majority of enterprises (57%) report that in the past six months their AI agents produced confident but wrong answers they traced to missing or inconsistent business context, and more than half of those said it happened more than once. This is not a fringe failure: retrieval is the primary context source for 38% of enterprises, more than any other approach, so when retrieval is thin or inconsistent, the errors it produces are wearing the agent’s authority. The infrastructure to fix it is being built — 58% already run or are building a governed semantic layer — but for most it is not yet in production.

Underneath, the market is consolidating in a direction that surprises. Provider-native retrieval — OpenAI’s file search (40%) and Google’s Vertex AI Search (38%) — already leads every dedicated vector database, and enterprises expect hybrid retrieval to dominate by the end of 2026 (34%). Yet a plurality (36%) say they intend to keep best-of-breed standalone tools rather than consolidate onto a provider’s native context stack, and a majority (57%) plan to switch or add a provider within the year. Stated preference and actual usage are pulling in opposite directions — the market is buying provider-native while insisting it wants independence.

Methodology

VentureBeat fielded this survey as part of its ongoing Pulse Research series. This survey focused on enterprise RAG infrastructure and the context layer — the retrieval systems, semantic layers, and context sources that feed AI agents. Responses are filtered to organizations with more than 100 employees (n=101); the survey drew no responses from organizations of 100 or fewer, so the full sample qualifies. All responses are from a single Q2 2026 (June) wave, so the report reads cross-sectionally and does not infer month-over-month trends. Several questions were multiple-select, so those shares can sum to more than 100%.

By organization size the sample concentrates in the mid-market: 251–1,000 employees (31%) and 101–250 (31%) lead, with 1,001–5,000 (20%), 5,001–10,000 (12%), and 10,001+ (7%) above them. By role it spans managers (39%), individual contributors (27%), the C-suite (16%), and VPs and directors (14%); on purchasing authority it is buyer-credible, with 46% final decision-makers and another 26% recommenders or influencers. Technology/Software is the largest industry at 20%, followed by Healthcare/Life Sciences (11%) and a broad spread across retail, transportation, financial services, manufacturing, and education.

At 101 respondents this is a modest sample and should be read as a directional signal rather than a precise measurement; it is self-selected and is not a probability sample. It is best read as the view from organizations actively standing up RAG and context infrastructure rather than from the largest operators.

Finding 1: Confident and wrong

More than half have traced agent errors to bad context

We asked whether, in the past six months, enterprises had traced a confident but wrong agent answer to missing or inconsistent business context. Most had.

Finding 1 — Confident and wrong

31%

say their AI agents produced a confident, wrong answer traced to bad context more than once — a recurring failure

28%

report no such failure identified

10%

don’t run agents on enterprise data; a further 5% don’t track root cause at that level

This is the report’s defining number. A majority of enterprises (57%) have already had an AI agent produce a confident, wrong answer they traced to bad context — wrong metrics, stale definitions, or missing documents — and more than half of those have seen it happen more than once. Only 28% report no such failure, and a small remainder either don’t run agents on enterprise data or don’t trace root cause closely enough to know.

The failure mode is specific and dangerous: the model is not obviously hallucinating; it is confidently wrong because the context feeding it was thin or inconsistent. Everything else in this report — what enterprises retrieve, how they govern it, and what they plan to build — is downstream of this problem.

Finding 2: RAG is the default context source

Retrieval feeds more agents than any other method

We asked what an enterprise’s AI agents primarily use to understand its data. Retrieval leads by a wide margin.

Finding 2 — RAG is the default context source

38%

rely on retrieval (RAG) over documents or a vector index — the dominant source

21%

use a governed semantic layer or ontology — shared business definitions and relationships

14%

use a mix that varies by use case

10%

use direct queries to live systems (SQL, APIs, MCP); 6% use long-context loading, and 2% rely on the model’s general knowledge

10%

don’t yet have agents working on enterprise data

Retrieval is the backbone of enterprise context. For 38% of organizations, RAG over documents or a vector index is the primary way agents understand the business — nearly twice the share of the next approach, a governed semantic layer or ontology (21%). Mixed approaches (14%), direct live-system queries (10%), and long-context loading (6%) fill out the rest, and only 2% let agents run on the model’s general knowledge alone. The concentration matters in light of Finding 1: because so much enterprise context flows through retrieval, the quality of that retrieval is the quality of the answer. When RAG is the default source, thin retrieval is not an edge case — it is the main failure surface.

One approach is notable for its absence from these answers: customizing model weights, also known as fine-tuning. Every leading source of business context is injected at run time. Our most recent direct measurement of fine-tuning comes from our April–May survey wave (a separate survey, n=136), where fine-tuning capabilities ranked last of six factors in model selection at 5% — even as 26% of that sample still named fine-tuning and customization an investment they expect to grow. Fine-tuning has fallen out of the primary selection conversation; context injection is how enterprises make agents knowledgeable about their business.

Finding 3: Provider-native retrieval already leads the vector databases

OpenAI file search and vertex AI search top the dedicated tools

We asked which retrieval systems enterprises run in production today. The answer favors the model providers and hyperscalers over the specialists.

Finding 3 — Provider-native retrieval already leads the vector databases

40%

use OpenAI retrieval or file search; 38% use Google Vertex AI Search — the two most-used systems

20%

use Elasticsearch or OpenSearch; 12% use Postgres-based pgvector

12%

each use Weaviate, ahead of Qdrant (10%), Pinecone (9%) and Milvus (6%) — the pure-play vector databases

10%

run a custom in-house retrieval stack

13%

run no production RAG systems at all

The dedicated vector database is no longer the center of the RAG stack. OpenAI’s file search (40%) and Google’s Vertex AI Search (38%) lead — provider-native and hyperscaler-native retrieval — ahead of every purpose-built vector database. Among the specialists, the most-used is the one enterprises already run for other reasons (Elasticsearch/OpenSearch, 20%) and the open, embedded option (pgvector, 12%); the pure-play vector databases that define the category — Weaviate, Qdrant, Pinecone, Milvus — each sit in single digits to low double digits. Notably, 13% of enterprises say they still run no production RAG at all. As with the platforms in the parallel infrastructure wave, enterprises are gravitating to retrieval that comes bundled with tools they already buy.

The shape of this finding held across both Q2 waves. In April–May (n=161), provider-built retrieval led usage there too, while every dedicated vector database remained marginal — the most-used standalone vector database peaked at 8% of that sample — and the hybrid, pluralistic future was already the consensus expectation (34% expected hybrid retrieval to dominate, with another 29% expecting multiple architectures by use case). Two waves, consistent picture: the category that coined the “vector database” term is being collected by the platforms enterprises already buy from.

Finding 4: But they say they want to keep best-of-breed

A plurality resist consolidating onto a provider’s native stack

We asked how enterprises will respond as model providers bundle retrieval, memory, and orchestration into their platforms. Their stated intent cuts against their current usage.

Finding 4 — But they say they want to keep best-of-breed

36%

plan to keep best-of-breed standalone tools — separate vector database, evaluation, orchestration

21%

plan to consolidate onto a single model provider’s native context stack

21%

expect a mix — provider-native runtime for some workloads, standalone tools for others

14%

have no clear direction yet

9%

plan to build and own their context layer in-house

Here is the tension at the heart of the stack. Even as provider-native retrieval leads in practice (Finding 3), a plurality of enterprises (36%) say they intend to keep best-of-breed standalone tools rather than consolidate onto a provider’s native context stack — well ahead of the 21% who plan to consolidate. Another 21% expect a mix, and 9% intend to build and own the layer themselves. The gap between what enterprises run and what they say they want is the strategic question of the category: they are adopting bundled retrieval for convenience while asserting they will preserve independence. Which impulse wins — the pull of the provider bundle or the stated preference for modular control — will shape the retrieval market more than any single tool.

Finding 5: Hybrid retrieval is the consensus bet

Vector-only retrieval is already seen as insufficient

We asked which retrieval architecture enterprises expect to dominate their production RAG systems by the end of 2026. The field is converging — with a large share still unsure.

Finding 5 — Hybrid retrieval is the consensus bet

34%

expect hybrid retrieval — embeddings plus reranking plus access controls — to dominate by the end of 2026

14%

expect tool-first or long-context retrieval, without a dedicated vector layer

13%

expect multiple architectures, chosen by use case

12%

do not expect large-scale RAG deployments; 11% expect vector-only retrieval

The architecture is settling on hybrid. A third (34%) expect hybrid retrieval — embeddings combined with reranking and access controls — to dominate their production systems by the end of 2026, three times the 11% who expect vector-only retrieval to prevail. That is a notable signal: the pure vector-search approach that launched the category is already viewed as insufficient on its own, superseded by pipelines that add reranking for accuracy and access controls for governance — the very access controls whose absence produces the failures in Finding 1. Tellingly, the second-largest answer is uncertainty: 17% simply don’t know, and another 14% expect to move beyond a dedicated vector layer entirely toward tool-first or long-context retrieval. The consensus is not a single tool but a layered pipeline — and it is not yet fully formed.

Finding 6: The governed context layer is being built now

Most run or are building a semantic layer — few in production

We asked whether enterprises use a governed semantic or context layer to give agents and BI a shared understanding of their data. Most are on the path; fewer have arrived.

Finding 6 — The governed context layer is being built now

34%

are piloting or building a governed semantic layer

25%

already run one in production

17%

aren’t using one but are actively evaluating

15%

have no current plans

The fix for the context gap is under construction. Well over half of enterprises (58%) either run a governed semantic layer in production (25%) or are piloting and building one (34%), and a further 17% are actively evaluating — meaning three-quarters are engaged with the idea in some form. But the balance is telling: more are building than have shipped, so for most enterprises the shared, governed definition layer that would prevent the "confident but wrong" failures of Finding 1 is still a work in progress. The semantic layer is the industry’s answer to inconsistent context; this wave catches it mid-construction, ambition well ahead of production.

Finding 7: Bought on ingestion and simplicity, watched for correctness

Selection favors operability; monitoring favors correctness and security

We asked what matters most when enterprises choose a retrieval system, and what they track once it is running. Both answers lean practical.

Finding 7 — Bought on ingestion and simplicity, watched for correctness

36%

cite ease of data ingestion as the top selection factor

32%

cite latency and performance

29%

cite operational simplicity

23%

each cite retrieval accuracy and access control / permissions

10%

cite native integration with the cloud ecosystem

Enterprises choose retrieval systems on operability. Ease of data ingestion (36%), latency and performance (32%), and operational simplicity (29%) lead the selection criteria — ahead of retrieval accuracy and access control (23% each), the two factors most directly tied to the failures in Finding 1. Once systems are running, the emphasis shifts toward trust: the most-tracked metrics are response correctness (42%) and security and access control (38%), ahead of latency (28%), operational stability (27%), and answer relevance (23%).

Satisfaction with current systems is moderately positive but not enthusiastic — on a five-point scale, overall satisfaction averages 4.0, with ease of implementation and value for money both near 3.9. Enterprises buy for how easily a system runs and watch it for whether it can be trusted.

Finding 8: A retrieval reshuffle is coming

A majority plan to change providers — and the vector specialists are gaining interest

We asked whether enterprises plan to change or add a retrieval provider, and which they are considering. The consideration set differs from today’s stack.

Finding 8 — A retrieval reshuffle is coming

43%

have no plans to change providers

26%

plan to change within the next 0–3 months

21%

plan to change within 3–6 months

15%

plan to change within 6–12 months

The retrieval stack is not settled. While 43% have no plans to change, a small majority (57%) intend to switch or add a provider within twelve months, and a quarter (26%) within the next quarter. The consideration set is where it gets interesting: provider-native retrieval still leads what enterprises are evaluating (OpenAI 22%, Vertex AI Search 21%), but the open-source vector specialists punch above their current footprint — Qdrant (14%) and Milvus (13%) draw more switching interest than their present usage (10% and 6%) would suggest. Read with Finding 4, the picture is a market in flux: enterprises run provider-native today, are evaluating a broader field, and say they want to keep their options open. The reshuffle ahead will test whether best-of-breed intent survives contact with the convenience of the bundle.

The bottom line: A context gap that more retrieval alone won’t close

Organizations with more than 100 employees are wiring agents into their business faster than they can guarantee the context those agents run on. Retrieval is the default source of enterprise context, and it increasingly comes from the model providers and hyperscalers rather than the dedicated vector databases — yet a majority of enterprises have already watched agents answer confidently and wrongly because that context was thin or inconsistent. The failure is not exotic; it is the predictable result of pointing authoritative-sounding agents at an unreliable foundation.

The industry’s answer — a governed semantic layer, hybrid retrieval with reranking and access controls — is being built but is mostly not yet in production, and enterprises are pulled between the convenience of provider-native bundles and a stated preference for best-of-breed independence. At 101 respondents in a single Q2 wave this is a directional read, skewed toward the mid-market — but the direction is clear: the context layer is the next contested tier of the AI stack, and right now agents are running ahead of it. The context gap is not a retrieval-volume problem that more documents or bigger indexes will solve on their own; it is a problem of governed, consistent, access-aware context. The open question for later waves is whether enterprises finish building that layer before the confident-but-wrong failures move from the lab into decisions that matter.

---

Based on survey responses from 101 qualified enterprise respondents (100+ employees), drawn from a single Q2 2026 (June) wave. At this sample size the results should be read as a directional signal rather than a precise measurement — it's a self-selected sample, not a probability sample, and skews toward the mid-market. Respondents include managers, individual contributors, VPs/directors, and the C-suite, with strong purchasing authority, across technology, healthcare, retail, transportation, financial services, manufacturing, and education.