如今的模型能够对复杂任务进行推理，但它们并不会自动理解这些任务背后的业务背景。哪份基金报告是当前版本？同一个实体在三个系统中分别如何命名？
这些背景信息存在于文档、数据室、电子表格、电子邮件和内部工具中：分散、未解析，且对智能体不可见。对于金融、保险和房地产领域的团队而言，工作流内的检索准确性不容妥协。
在共同打造了一款被广泛使用的计算机视觉无障碍应用之后，Rizzoli 和 Edwardsson 于 2018 年创立了 V7（在新窗口中打开），帮助企业教会 AI 系统了解其业务如何运作。V7 Go 是一个智能体平台，用于构建关键任务工作流，并将埋没的背景信息整理为智能体可以查询和据以行动的記憶。
V7 Go 使用 GPT‑5.6 Luna 从数百万份文件中提取信息，并将其整理到 Context Graph 中，该图谱连接实体、关系和引用的证据，为 MCP 搜索和可跨越数百个步骤的可重复工作流提供支持。对于 Workflows，V7 Go 使用 GPT‑5.6 Terra 和 Sol 在复杂的多步骤指令中进行推理和工具使用，这些指令人类需要数十小时才能完成。V7 还开始在最严苛的 Context Graph 查询上使用 GPT‑6 Astra，包括跨数千份文件的财务分析。
通过背景信息、模型和工具协同工作，V7 表示智能体可在数分钟内完成 50–100 步的工作流，达到 99.9% 的准确率，同时保留每项决策的可审计轨迹。
“要解决金融和保险领域的艰难企业用例，AI 需要像从互联网学习一样，学会你的业务如何运作。”
——Alberto Rizzoli，V7 联合创始人兼 CEO
为智能体提供理解整个业务的背景信息
Context Graph 解决了一个具体问题。智能体必须在每次请求时重新发现背景信息，导致数十次搜索，耗费时间和 token，并且常常遗漏埋藏在关系中的关键信息。
当数据到达时，V7 Go 连接到 SharePoint 和 Google Drive 等存储库，扫描其中的实体、关系、事实、属性和指标，并填充一个图谱，其遍历成本和时间比长上下文方法低一个数量级。
Context Graph 为智能体提供了一份结构化、最新的记录，可直接查询。当新文件到达时，V7 Go 识别本体中的公司、基金、人员或任何实体，然后将每个事实连接到新记录或现有记录，并保留对原始来源的引用证据。如果图谱中没有足够的信息，V7 Go 仍可通过 RAG 搜索底层文档。
V7 还测试了这种上下文结构的重要性。在 HERB 这一用于查找和连接分散在企业系统中的信息的基准上，V7 仅检索系统比官方基线高出 69%，并将无法回答的查询上的幻觉减少了 38%。V7 Go 使用这种来源关联的上下文，使复杂工作流扎根于每家公司自己的信息中。
V7 Go 在私募股权交易筛选和保险承保等工作流中使用这种整理后的上下文。在下面的演示中，一个工作流从名为保密信息备忘录（CIM）的交易文件中提取信息，输入关键财务数据、交易条款、管理层详情，并引用风险字段，然后 V7 Go 生成一份筛选说明。
Context Graph 使模型能够利用公司的历史记录，而无需每次都重新学习。对于长时间运行的智能体，V7 Go 将最近的交互保留在模型的活跃上下文中，并将较旧的材料存储在图谱中，以便在需要时检索。
这种共享上下文已经在加速 V7 客户中大量涉及文档的工作：
资产管理公司筛选交易的速度比之前快 21 倍，将一整天的工作缩短到仅 15 分钟
一个金融服务团队将审查时间从 100 多小时缩短到 10 小时以内，每项任务节省 12,000 美元的专家成本
保险团队在让智能体获得所有既往索赔和现有保单的历史知识后，将理赔处理中的错误相比人工基线减少了 13.5%
“借助 GPT-5.6 Terra，我们得以移除许多中间工作流阶段，这些阶段此前只是为了简化模型的任务而存在。这为我们节省了数天的交付工作，而且由于模型更强大且能访问更多上下文，往往在工作流的首次构建中就能做对。”
——Simon Edwardsson，V7 联合创始人兼 CTO
选择 OpenAI 让复杂工作流保持正轨
复杂的多步骤工作流依赖于模型可靠地遵循冗长指令、运行工具、解释结果，并完成一长串步骤。单个上游错误可能导致高昂后果，并破坏对 AI 系统的信任。V7 Go 引导模型完成跨越确定性代码、移交给较小模型、文件生成步骤和集成的长周期任务，并保留每次运行的可审计轨迹。
在 AI 生成的工作流中，V7 Go 将每个步骤映射到快速、中等和智能层级。GPT‑5.6 Luna 处理结构化提取和其他高吞吐量工作，GPT‑5.6 Terra 或 Sol 为聊天、Go Agent 路径以及需要更多推理或工具使用的步骤提供支持。
V7 针对一套持续维护的基准测试套件测试新模型，涵盖引用准确性、数百种文档类型的提取质量、答案正确性、指令遵循、延迟、成本以及真实企业工作流。OpenAI 在 V7 最关心的行为上优于大多数模型。OpenAI 还在数小时内批准并实施了 V7 的容量增加需求，而 V7 使用的其他提供商则需要数周。
“我们选择 OpenAI 作为默认选项，是因为它在 V7 Go 所依赖的多步骤工具工作流上表现最佳。在我们的 Context Graph 基准测试中，GPT-5.6 Sol 将工具调用错误率从 GPT-5.5 的 2.7% 降至 0.2%。”
——Simon Edwardsson，V7 联合创始人兼 CTO
在 V7 最新的测试框架中，包含多次外部调用的关键工作流现在完成速度最高提升 50%。V7 还用 GPT‑5.6 Luna 测得了另一项效率提升：每份文档的成本比 GPT‑5.4 mini 低 78%。V7 还将其文档密集型的 V7 Go 工作负载从 Chat Completions API 迁移到 Responses API。在其测试中，这一变化使某些 PDF 密集型工作流的 token 使用量减少约 5%，并提高了缓存可靠性。
V7 还在其最困难的查询上测试了 GPT‑6 Astra。GPT‑5.6 Sol 已经使 V7 的许多现有基准达到饱和，因此该公司使用跨数千份文档的更杂乱的真实世界数据，创建了一套更具挑战性的图谱查询问题。该测试的数据集涵盖四个难度级别。在极难级别上，V7 报告 GPT‑5.6 Sol 得分为 78%，而 GPT‑6 Astra 的准确率为 89%。两个模型在简单、中等和困难级别上的得分都接近 100%。
将业务所知带入 ChatGPT 和 Codex
V7 Go 已通过其 MCP 服务器公开了 Context Graph 查询和摄取功能，因此客户可以在 ChatGPT 和其他兼容客户端中使用它。他们还可以通过 Codex 中的 MCP 创建 V7 Go 工作流。再加上更简单的工作流设计，这将创建中等长度工作流所需的时间从大约一小时缩短到了约 20 分钟。
V7 的长期目标是让这种共享记忆更具主动性。该团队正在努力实现这样的工作流：当 Context Graph 中的事实发生变化时启动、标记不一致之处，并向人们显示哪些分析需要重新审视。例如，一份重述的基金报告可能会促使 V7 Go 标记仍然依赖旧数据的工作。
“我们的目标是帮助企业为 AI 时代重新配置工具，通过解决关键任务的工作流，以及超越我们人类记忆的记忆，”Rizzoli 说。“从 AI 中获得真正价值的金融公司不会是拥有最多代理的公司。它们将是拥有最佳上下文的公司。”
Today’s models can reason through complex tasks, but they don’t automatically understand the underlying business context of those tasks. Which fund report is current? How is the same entity named across three systems?
That context lives in documents, data rooms, spreadsheets, emails, and internal tools: scattered, unresolved, and invisible to agents. For teams in finance, insurance, and real estate, retrieval accuracy within workflows is non-negotiable.
After building a widely used computer vision accessibility app together, Rizzoli and Edwardsson started V7(opens in a new window) in 2018 to help companies teach AI systems how their businesses work. V7 Go is an agentic platform to build mission critical workflows, and organize buried context into memory that agents can query and act on.
V7 Go uses GPT‑5.6 Luna to extract information from millions of files and organize it in the Context Graph, which connects entities, relationships, and cited evidence, powering MCP search and repeatable workflows that can span hundreds of steps. For Workflows, V7 Go uses GPT‑5.6 Terra and Sol for reasoning and tool use across complex, multi-step instructions that take humans dozens of hours to complete. V7 is also starting to use GPT‑6 Astra on the most demanding Context Graph queries, including financial analysis across thousands of documents.
With context, models, and tools working together, V7 says agents complete 50–100 step workflows in minutes, reaching 99.9% accuracy, while maintaining an auditable trail of every decision made.
“To solve hard enterprise use cases across finance and insurance, AI needs to learn how your business operates just as well as it learned from the Internet.”
—Alberto Rizzoli, Co-Founder and CEO at V7
Giving agents the context to understand the whole business
The Context Graph solves a specific problem. Agents have to rediscover context on every request, leading to dozens of searches costing time and tokens, and often missing key information buried in relationships.
When data arrives, V7 Go connects to repositories such as SharePoint and Google Drive, scans them for entities, relationships, facts, attributes, and metrics, and populates a graph that’s an order of magnitude cheaper and faster to traverse than long-context approaches.
The Context Graph gives agents a structured, up-to-date record they can query directly. When a new file arrives, V7 Go identifies the companies, funds, people, or any entity in an ontology, then connects each fact to a new or existing record, and preserves cited evidence to the original source. If the graph does not contain enough information, V7 Go can still search the underlying documents with RAG.
V7 has also tested how much the structure of that context matters. On HERB, a benchmark for finding and connecting information spread across enterprise systems, V7’s retrieval-only system outperformed the official baseline by 69% and reduced hallucinations on un-answerable queries by 38%. V7 Go uses that source-linked context to keep complex workflows grounded in each company’s own information.
V7 Go uses that organized context in workflows such as private equity deal screening and insurance underwriting. In the demo below, a workflow extracts information from a deal document called a Confidential Information Memorandum (CIM) feeds key financials, deal terms, management details, and cites risk fields before V7 Go produces a screening note.
The Context Graph makes it so that a model can work with a firm’s history without relearning it each time. For long-running agents, V7 Go keeps recent exchanges in the model’s active context and stores older material in the graph to be retrieved when needed.
That shared context is already speeding up document-heavy work across V7’s customers:
Asset managers can screen deals 21x faster than before, reducing a full-day process to just 15 minutes
A financial services team cut review time from more than 100 hours to under 10, saving $12,000 in expert costs per task
Insurance teams reduced errors in claims processing by 13.5% compared to a manual baseline, after granting their agents historical knowledge of all previous claims and existing policies
“With GPT-5.6 Terra, we have been able to remove many intermediate workflow stages that previously existed only to simplify the task for the model. It’s saved us days of delivery work and often gets things right on the first build of a workflow, thanks to a stronger model and access to more context.”
—Simon Edwardsson, Co-Founder and CTO at V7
Choosing OpenAI to keep complex workflows on track
Complex, multi-step workflows depend on a model reliably following lengthy instructions, running tools, interpreting results, and navigating a long series of steps. A single upstream error can lead to expensive consequences and broken trust in AI systems. V7 Go guides models across long horizon tasks spanning deterministic code, handovers to smaller models, file generation steps, and integrations, with an auditable trace of every run.
In AI-generated workflows, V7 Go maps each step to fast, medium, and smart tiers. GPT‑5.6 Luna handles structured extraction and other high-volume work, and GPT‑5.6 Terra or Sol power chat, the Go Agent path, and steps that require more reasoning or tool use.
V7 tests new models against a continuously maintained benchmark suite covering citation accuracy, extraction quality across hundreds of document types, answer correctness, instruction following, latency, cost, and real-world enterprise workflows. OpenAI outperforms most models on the behaviors V7 cares about most. OpenAI also approved and implemented V7’s capacity increase needs within hours, compared with weeks for other providers V7 uses.
“We chose OpenAI as our default because it performs best on the multi-step tool workflows V7 Go depends on. In our Context Graph benchmark, GPT-5.6 Sol reduced the tool-call error rate from 2.7% with GPT-5.5, to 0.2%”
—Simon Edwardsson, Co-Founder and CTO at V7
In V7’s latest harness, key workflows with several external calls now finish up to 50% faster. V7 measured another efficiency gain with GPT‑5.6 Luna: a 78% lower cost per document than with GPT‑5.4 mini. V7 also moved its document-heavy V7 Go workloads from the Chat Completions API to the Responses API. In its testing, the change reduced token use by roughly 5% for some PDF-heavy workflows and improved caching reliability.
V7 also tested GPT‑6 Astra on its most difficult queries. GPT‑5.6 Sol had saturated many of V7’s existing benchmarks, so the company created a more challenging set of graph-query questions using messier, real-world data across thousands of documents. The test’s dataset spans four difficulty levels. On the very-hard level, V7 reports that GPT‑5.6 Sol scored 78%, while GPT‑6 Astra scored 89% accuracy. Both models scored close to 100% on the easy, medium, and hard levels.
Bringing what the business knows into ChatGPT and Codex
V7 Go already exposes Context Graph querying and ingestion through its MCP server, so customers can use it from ChatGPT and other compatible clients. They can also create V7 Go workflows through MCP in Codex. Together with simpler workflow design, this has reduced the time required to create a medium-length workflow from around one hour to about 20 minutes.
V7’s longer-term goal is to make that shared memory more proactive. The team is working toward workflows that start when facts in the Context Graph change, flag inconsistencies, and show people which analyses need another look. A restated fund report, for example, could prompt V7 Go to flag work that still relies on the old figures.
“Our goal is to help enterprises re-tool for the age of AI, with workflows that solve mission critical tasks, and memory that outperforms us humans” says Rizzoli. “Finance firms getting real value from AI will not be the ones with the most agents. They will be the ones with the best context.”
本文内容采集自官方网站，排版和翻译可能与原页面存在差异。
阅读官方全文