公司指南

葛萊恩

Glean 是一家位於帕洛阿爾托的公司,成立於 2019 年,銷售基於公司自有應用程式權限感知索引的 AI 搜尋、聊天助理和代理工具。

聆聽此指南AI 語音敘述 · ~8 min

本頁閱讀時間 9 分鐘
  1. 概述
  2. 重點摘要
  3. 深入探討
  4. 追蹤一個權限感知的回答
  5. 現實世界的實施
  6. 葛莱恩的未来
  7. 付諸實踐
  8. 資料來源與延伸閱讀
  9. 不斷探索
  10. 常見問題

概述

這之所以重要,是因為它展示了職場 AI 的主要模式:檢索員工有權查看的文件,然後讓語言模型根據這些文件並附上引用來源來回答。

重點摘要

  1. Glean 於 2019 年在帕洛阿爾托成立,銷售企業搜尋、Glean Assistant 和 Glean Agents 平台。
  2. 其連接器會複製每個應用程式的內容、中繼資料和存取控制清單,因此結果僅包含使用者已經可以開啟的項目。
  3. Glean Assistant 使用檢索增強生成(RAG),從檢索到的文件中回答問題並引用來源,而不是依賴微調模型。
  4. Glean 在 2025 年 6 月完成 1.5 億美元的 F 輪融資後,估值達到 72 億美元。
  5. 《財富》雜誌於 2025 年 12 月報導,Glean 的年經常性收入達到 2.0 億美元,是九個月前的兩倍。

深入探討

Glean is an enterprise software company that makes the information scattered across a company's apps searchable and answerable in one place. It was founded in 2019 in Palo Alto, California, by Arvind Jain, who is its CEO, with Piyush Prahladka, Tony Gentilcore and T.R. Vishwanath. Its products are Glean Search, a conversational tool called Glean Assistant, and Glean Agents, a platform for building and running AI agents, meaning software that carries out multi-step tasks rather than only answering a question. All three sit on the same foundation: an index of the customer's own documents, messages, tickets and people.

The first step is connection. Glean's documentation describes connectors, small integrations for each app, that sync content and metadata into the customer's search index: titles, bodies, comments, attachments, owners, timestamps and app-specific fields. Connectors also copy each app's access control lists, the records of who may open which item, and fetch people and group data so the same person can be matched across systems. Where an app supports it, they collect activity signals such as views, edits and shares. Sources are kept current with incremental crawls and, in some cases, webhooks or push APIs, while fast-changing sources such as email or calendar can be fetched live at query time instead of being indexed.

The second step is ranking. In a 2023 engineering post, Glean's authors argued that vector search alone, which matches the meaning of a query to the meaning of a document using numeric embeddings, is not enough for workplace content. They described a hybrid approach that combines classic keyword retrieval with neural embeddings, followed by a reranking step that blends dozens of signals, including keyword match, semantic similarity, freshness and personalization, into one relevance score. Personalization comes from what Glean now calls the Enterprise Graph, a knowledge graph whose nodes are content, people and activity, and whose edges include links between documents, people who work together, and who created, edited or shared what.

The third step is generation. Glean Assistant uses retrieval-augmented generation (RAG): it retrieves the most relevant items the user is allowed to see, passes them to a large language model, and asks the model to answer from that text. The same 2023 post explains why Glean prefers this to fine-tuning, which means further training a model on company data. Fine-tuned knowledge goes stale, cannot respect per-user permissions, cannot point to its sources, and can raise the rate of hallucination, the model stating things that are not true. With RAG, the index can be updated continuously, permissions are enforced before the model sees anything, and the cited documents can be inspected. The post also describes using a language model for query planning, turning one request into several searches, such as GitHub pull requests plus Slack messages.

The company's milestones are well documented. Glean raised a $15 million Series A in March 2019, co-led by Kleiner Perkins and Lightspeed, and launched its search product in September 2021. A $100 million Series C led by Sequoia Capital in May 2022 valued it at $1 billion. Valuations then rose quickly: $2.2 billion in February 2024, $4.6 billion after a Series E of more than $260 million in September 2024, and $7.2 billion after a $150 million Series F led by Wellington Management on June 10, 2025, according to TechCrunch. Glean Agents first appeared in February 2025 and became generally available on May 20, 2025, alongside a model hub giving agents access to 15 large language models through Amazon Bedrock, Google Vertex AI and Azure OpenAI, and a server for the Model Context Protocol (MCP), an open standard for connecting AI agents to tools. On December 8, 2025, Fortune reported that Glean had reached $200 million in annual recurring revenue (ARR), double the $100 million it reported nine months earlier, counting only software subscriptions.

Glean competes in a crowded field. Large productivity suites build assistants that work best on their own content, such as documents and mail stored in one vendor's cloud. Glean's pitch is the opposite: a neutral layer across many vendors' apps. Companies can also build their own RAG systems with open-source vector databases and a model API, which gives full control but leaves them to solve connectors, permission syncing, identity matching and ranking themselves, the parts Glean's documentation spends most of its effort on. The trade-off is cost and dependence on one vendor against the engineering time of building and maintaining the same pipeline in-house.

The limitations follow from the design. Answers can only be as good as what is connected and indexed, so a missing connector or a stale crawl means a missing or outdated answer. Permission mirroring is only as accurate as the source app's own sharing settings: if a sensitive file is shared too widely in the source, it will be searchable for everyone who has access, which is why Glean's documentation tells administrators that opening a result may trigger a second check in the source system and points them to governance tools. Activity signals and available permissions differ by connector. RAG reduces hallucination but does not remove it, so a generated answer can still misread or misstate a correct source, which is why citations matter.

In practice, Glean is sold to organizations rather than individuals. Fortune reported that its contracts run one to three years. Its documentation offers two cloud deployment models. In Glean Hosted, Glean runs a single-tenant instance, isolated from other customers, on Google Cloud. In Customer Hosted, formerly called Cloud-Prem, Glean deploys and operates the instance inside the customer's own Google Cloud or AWS account, and the customer pays the hosting costs. SiliconANGLE reported in May 2025 that a partnership with Dell Technologies also lets enterprises run the platform on their own premises. A rollout typically involves an administrator authorizing each connector, checking that identities and groups map correctly, and testing permission behavior with test accounts before opening the tool to all employees.

04工作範例

追蹤一個權限感知的回答

  1. 某位管理者連接了 Confluence 與 Slack;這些連接器會將頁面、訊息、擁有者以及每個項目的存取清單同步到公司的索引中。

  2. 兩名員工(一人在工程部門,另一人在業務部門)提出了相同的問題:行動應用程式目前發布日期是什麼時候。

  3. 對於每位員工,系統首先會移除該人員無法在來源應用程式中開啟的所有已索引項目。

  4. 關鍵字與嵌入檢索會尋找候選頁面與訊息,而排序則會提升近期項目以及每位使用者合作對象的項目的權重。

  5. 最前面的結果會傳遞給語言模型,由其撰寫答案並列出所使用的頁面與訊息。

  6. 每個員工都會開啟引用的來源來確認日期,並檢查銷售使用者是否看到了任何受限制的工程頻道。

它顯示了什麼

這兩位員工可能會得到不同的答案,因為他們看到的來源集合不同,這是設計好的預期行為。正確的推出結果應該不會出現使用者無法直接開啟的引用,且每一個陳述的日期都與引用的頁面相符。

現實世界的實施

職場搜尋:員工輸入一次問題,就能從所連結的工具(例如 Google Drive、Confluence、Jira、Slack、GitHub 與 Microsoft Teams)中取得排序後的結果,並會過濾掉該人員無法開啟的項目。

引用的答案:Glean Assistant 會從檢索到的文件中撰寫回應,並列出它所使用的來源,因此讀者可以開啟底層頁面並檢查答案是否有憑有據。

客服自動化:當 Glean Agents 於 2025 年 5 月正式全面推出時,Glean 所提供的 30 多個預先建置的代理程式中,就包含了用於處理技術支援單的代理程式。

以日常語言詢問資料問題:根據 SiliconANGLE 的發表報導,2025 年 5 月宣布推出的一個結構化查詢代理程式,可以根據自然語言提示,對儲存在 Snowflake 中的資料執行分析。

受管制的部署:必須將資料保留在自家雲端的公司可以選擇「客戶託管」(Customer Hosted)模型,在此模型中,Glean 會在客戶自己的 Google Cloud 或 AWS 帳戶內執行單一租戶執行個體。

葛莱恩的未来

Glean's direction since 2025 has been from search toward agents. The May 2025 release made Glean Agents generally available, added a model hub with 15 language models from three cloud providers, and introduced an MCP server so outside agents can call Glean Search and Assistant. Reporting in 2026 describes the company positioning itself as the layer that connects AI models to enterprise systems and data, rather than primarily as a search box. Several problems remain open for Glean and for enterprise RAG generally. Measuring answer quality inside a private company is hard, because there is no public benchmark of a firm's own documents and questions. Agents that write back to systems such as ticketing tools raise questions about approval, auditing and how to stop an agent whose scope has changed, which Glean addresses with admin controls but which the field has not settled. Permission accuracy depends on how carefully each source app is configured, and oversharing in the source becomes oversharing in search. The competitive picture is also unsettled. Productivity-suite vendors, model companies and in-house teams all offer ways to put a language model on top of company data, and Glean's MCP server is designed to let outside agents draw on its index rather than replace them. How customers split work between a neutral cross-app layer and their main suite's built-in assistant is a question that adoption data, not announcements, will answer.

付諸實踐

為什麼這很重要

  • 供應商策略. 供應商路線圖會影響您的團隊接下來可以建立的功能。
  • 成本與預算. 商業條款和部署選項會影響長期成本和風險。
  • 風險與安全. 公司激勵措施塑造了產品預設、安全態勢和開放性。

留意

  • 發佈公告可能會超過實際生產工作流程的穩定性。
  • API 定價或政策轉變可能會在一夜之間打破假設。
  • 單一供應商依賴性增加了鎖定和遷移成本。

後續步驟

  1. 使用您自己的任務和資料集評估提供者。
  2. 在整合之前查看隱私、安全和法律條款。
  3. 維護跨模型或供應商的後備計劃。
  4. 監控發行說明,以便路線圖的變更不會讓團隊感到意外。

資料來源與延伸閱讀

  1. TechCrunch企業 AI 新創公司 Glean 估值達到 72 億美元
  2. Fortune獨家:Glean 的 ARR(年度經常性收入)達到 2.08 億美元,高於九個月前的 1 億美元
  3. SiliconANGLEGlean 推出升級版的 Glean Agents 工具組與全新開發工具
  4. Glean如何為企業打造 AI 助理
  5. Glean Documentation連線器驅動 Glean
  6. Glean DocumentationGlean 部署模型
  7. WikipediaGlean Technologies

不斷探索

免費電子報

獲取每日 AI 簡報

每個工作日上午提供三則經過驗證的 AI 新聞,以淺顯易懂的英文撰寫。永久免費,無廣告。

每個工作日一封電子郵件。一鍵取消訂閱。我們絕不出售或分享您的地址。

測試一下自己

參加 Glean 測驗

每個答案皆有即時回饋,通過課程後可獲得具備可驗證 ID 的可分享證書。

開始測驗

支持免費的 AI 教育。AI Understanding 是一個 501(c)(3) 非營利組織——絕無廣告,絕無付費牆。 捐款

常見問題

什麼是葛萊恩?

Glean 是一家位於巴洛阿圖(Palo Alto)的公司,成立於 2019 年,其銷售的 AI 搜尋、聊天助理與代理程式工具,是建立在公司自身應用程式的權限感知索引之上。這之所以重要,是因為它顯示了職場 AI 的主要模式:檢索員工被允許查看的文件,然後讓語言模型根據這些文件並附上引用來回答。

Glean旨在為企業解決什麼核心問題?

Glean 統一了 Slack、Drive 和 Jira 等工具的搜索,以便員工可以快速找到分散的內部知識。

Glean 建構了什麼來捕捉人、專案和內容之間的關係?

Glean 在互聯繫統中建立了公司特定的知識圖譜和搜尋索引。

Glean 如何描述具備權限感知的答案?

Glean 文件記錄了來自連線應用程式的權限感知檢索;管理員仍需設定與驗證連線器。

誰是 Glean 的主要共同創辦人,帶來了 Google 和 Rubrik 的先前經驗?

Arvind Jain 是前 Google 工程師和 Rubrik 聯合創始人,並於 2019 年協助創立了 Glean。

哪種檢索方法可以為 Glean Assistant 的答案提供來源段落?

Glean 描述使用檢索增強生成(retrieval-augmented generation)來檢索被允許的來源素材並產生附引用的答案。檢索可以提供依據,但它無法保證回應絕不包含不受支援的主張。