<?xml version="1.0" encoding="UTF-8"?>
<rss version="2.0" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>OntiCards 部落格</title>
    <link>https://onticards.com/zh-hk/blog</link>
    <description>OntiCards 產品實踐與數據智能洞察（繁體中文）</description>
    <language>zh-hk</language>
    <lastBuildDate>Thu, 29 Oct 2026 00:00:00 GMT</lastBuildDate>
    <atom:link href="https://onticards.com/zh-hk/rss.xml" rel="self" type="application/rss+xml"/>
    <item>
      <title>語義層不是模型的補丁，而是 AI Agent 的契約</title>
      <link>https://onticards.com/zh-hk/blog/semantic-layer-as-contract</link>
      <guid isPermaLink="true">https://onticards.com/zh-hk/blog/semantic-layer-as-contract</guid>
      <pubDate>Thu, 29 Oct 2026 00:00:00 GMT</pubDate><dc:creator>OntiCards 團隊</dc:creator><category>tech</category>
      <description>語義層不是模型的補丁，而是 AI Agent 的行為契約：它不生成 SQL，但定義哪些 SQL 是合規、可審計、可演化的。本文剖析其作為定義契約、關係契約與權限契約的三重本質，並提出輕量語義閘道器、分層上下文注入與本體演化基礎設施等落地路徑。</description><enclosure url="https://onticards.com/images/blog/semantic-layer-as-contract/cover-7abfa69fb229.svg" type="image/svg+xml"/>
    </item>
    <item>
      <title>語意層並非AI的補丁，而是Agent的契約</title>
      <link>https://onticards.com/zh-hk/blog/semantic-layer-as-agent-contract-2</link>
      <guid isPermaLink="true">https://onticards.com/zh-hk/blog/semantic-layer-as-agent-contract-2</guid>
      <pubDate>Thu, 29 Oct 2026 00:00:00 GMT</pubDate><dc:creator>OntiCards 團隊</dc:creator><category>tech</category>
      <description>本文揭示語意層的本質轉型：從服務人類報表的口徑對齊工具，升維為約束AI Agent行為的機器可執行契約。它顯式建模資料意圖、權限邊界與執行上下文，在執行時保障合法、可稽核、可演進的智能執行。</description><enclosure url="https://onticards.com/images/blog/semantic-layer-as-agent-contract-2/cover-6ac9e640c710.svg" type="image/svg+xml"/>
    </item>
    <item>
      <title>語義層是 AI Agent 的數據契約</title>
      <link>https://onticards.com/zh-hk/blog/semantic-layer-as-agentic-contract</link>
      <guid isPermaLink="true">https://onticards.com/zh-hk/blog/semantic-layer-as-agentic-contract</guid>
      <pubDate>Wed, 28 Oct 2026 00:00:00 GMT</pubDate><dc:creator>OntiCards 團隊</dc:creator><category>tech</category>
      <description>語義層不應只是報表工具的設定層，而是 AI Agent 與企業數據系統之間的契約。本文剖析其作為約束介面、審計錨點與協作協議的三重角色。</description><enclosure url="https://onticards.com/images/blog/semantic-layer-as-agentic-contract/cover-1d0c33bf4aed.svg" type="image/svg+xml"/>
    </item>
    <item>
      <title>語義層係 AI Agent 嘅契約，唔係加速器</title>
      <link>https://onticards.com/zh-hk/blog/semantic-layer-as-ai-agent-contract</link>
      <guid isPermaLink="true">https://onticards.com/zh-hk/blog/semantic-layer-as-ai-agent-contract</guid>
      <pubDate>Mon, 26 Oct 2026 00:00:00 GMT</pubDate><dc:creator>OntiCards 團隊</dc:creator><category>tech</category>
      <description>語義層不應只係 BI 工具嘅設定層，而應係 AI Agent 同企業數據之間具法律效力般嘅契約。本文剖析本體驅動建模點樣成為 Agentic Workflow 嘅可信邊界，而非加速器。</description><enclosure url="https://onticards.com/images/blog/semantic-layer-as-ai-agent-contract/cover-056a10b4ecd8.svg" type="image/svg+xml"/>
    </item>
    <item>
      <title>語義層是 AI Agent 的契約載體</title>
      <link>https://onticards.com/zh-hk/blog/semantic-layer-as-agent-contract</link>
      <guid isPermaLink="true">https://onticards.com/zh-hk/blog/semantic-layer-as-agent-contract</guid>
      <pubDate>Fri, 23 Oct 2026 00:00:00 GMT</pubDate><dc:creator>OntiCards 團隊</dc:creator><category>tech</category>
      <description>語義層並非數據中台的裝飾性模組，而是 AI Agent 與企業數據系統之間可驗證、可追溯、可審計的契約載體。本文剖析其於 NL2SQL、權限對齊與本體建模中的核心作用。</description><enclosure url="https://onticards.com/images/blog/semantic-layer-as-agent-contract/cover-8fb6314ad632.svg" type="image/svg+xml"/>
    </item>
    <item>
      <title>語義層：AI Agent 可靠運作的約束架構</title>
      <link>https://onticards.com/zh-hk/blog/semantic-layer-for-agentic-workflow</link>
      <guid isPermaLink="true">https://onticards.com/zh-hk/blog/semantic-layer-for-agentic-workflow</guid>
      <pubDate>Tue, 20 Oct 2026 00:00:00 GMT</pubDate><dc:creator>OntiCards 團隊</dc:creator><category>tech</category>
      <description>語義層並非 AI Agent 的加速工具，而是確保其可信運作的約束框架。本文深入剖析以本體為驅動的語義建模，如何將自然語言查詢、權限邏輯及執行動作，穩健錨定於統一的數據契約之上。</description><enclosure url="https://onticards.com/images/blog/semantic-layer-for-agentic-workflow/cover-c8c5d5551a19.svg" type="image/svg+xml"/>
    </item>
    <item>
      <title>決策模型井噴：智能體講嘅 0.8，到底有幾可信？</title>
      <link>https://onticards.com/zh-hk/blog/decision-models-confidence-calibration</link>
      <guid isPermaLink="true">https://onticards.com/zh-hk/blog/decision-models-confidence-calibration</guid>
      <pubDate>Mon, 19 Oct 2026 00:00:00 GMT</pubDate><dc:creator>OntiCards 團隊</dc:creator><category>tech</category>
      <description>一個月內十家廠商跟進決策模型，智能體架構多咗一層專用決策層。但獨立評測顯示幾乎所有模型都過度自信，唔同模型畀出嘅 0.8 含義並唔一樣。定標呢門工夫，最終落喺企業自己嘅數據同語義層上面。</description><enclosure url="https://onticards.com/images/blog/decision-models-confidence-calibration/cover.svg" type="image/svg+xml"/>
    </item>
    <item>
      <title>兩條 SQL 同一個答案，一條是錯的：問數進入可核查時代</title>
      <link>https://onticards.com/zh-hk/blog/checkable-text-to-sql-evidence</link>
      <guid isPermaLink="true">https://onticards.com/zh-hk/blog/checkable-text-to-sql-evidence</guid>
      <pubDate>Wed, 14 Oct 2026 00:00:00 GMT</pubDate><dc:creator>OntiCards 團隊</dc:creator><category>tech</category>
      <description>KNOWIDEA 聯同佐治亞理工與貝萊德發布 VeriPIE 論文：兩條 AI 生成的 SQL 今日返回同一個數，聽日就可能靜靜分歧。多數投票救不了，答案必須自帶可核查的證據鏈。</description><enclosure url="https://onticards.com/images/blog/checkable-text-to-sql-evidence/cover.svg" type="image/svg+xml"/>
    </item>
    <item>
      <title>本體成為戰略戰場：語義層一個月由 95% 跌到 65%</title>
      <link>https://onticards.com/zh-hk/blog/ontology-semantic-layer-decay</link>
      <guid isPermaLink="true">https://onticards.com/zh-hk/blog/ontology-semantic-layer-decay</guid>
      <pubDate>Mon, 12 Oct 2026 00:00:00 GMT</pubDate><dc:creator>OntiCards 團隊</dc:creator><category>tech</category>
      <description>問數智能體嘅準確率，唔係取決於模型，而係取決於語義層有冇人維護。Anthropic 數據團隊嘅復盤顯示，技能冇人維護時，離線準確率一個月內由約 95% 跌到約 65%；同一星期，Constellation 將數據本體列為廠商競爭嘅戰略戰場。</description><enclosure url="https://onticards.com/images/blog/ontology-semantic-layer-decay/cover.svg" type="image/svg+xml"/>
    </item>
    <item>
      <title>智能體有咗自己嘅身份：Agent 上生產前，先答四條問題</title>
      <link>https://onticards.com/zh-hk/blog/agent-identity-attribution</link>
      <guid isPermaLink="true">https://onticards.com/zh-hk/blog/agent-identity-attribution</guid>
      <pubDate>Fri, 09 Oct 2026 00:00:00 GMT</pubDate><dc:creator>OntiCards 團隊</dc:creator><category>tech</category>
      <description>48 小時內，Google 畀智能體發咗電郵、行事曆同通訊錄位置，AWS 將權限核對搬去查詢嗰一刻，微軟就要求每個智能體都要有人類擔保人。當 Agent 由個人助手變成團隊同事，決定佢可唔可以上生產嘅，唔再係模型分數，而係身份同歸屬。</description><enclosure url="https://onticards.com/images/blog/agent-identity-attribution/cover.svg" type="image/svg+xml"/>
    </item>
    <item>
      <title>智能體治理：信得過，比夠聰明更值錢</title>
      <link>https://onticards.com/zh-hk/blog/agent-action-governance-trust</link>
      <guid isPermaLink="true">https://onticards.com/zh-hk/blog/agent-action-governance-trust</guid>
      <pubDate>Wed, 30 Sep 2026 00:00:00 GMT</pubDate><dc:creator>OntiCards 團隊</dc:creator><category>tech</category>
      <description>OpenAI 一邊推常駐智能體，一邊抽起更強嘅新版本；同一星期 NVIDIA 將約束做入晶片。當智能體由答問題轉去做事，企業要在數據底座補上三個交付件。</description><enclosure url="https://onticards.com/images/blog/agent-action-governance-trust/cover.svg" type="image/svg+xml"/>
    </item>
    <item>
      <title>詞元經濟學：智能體嘅帳單，正在暴露你嘅數據家底</title>
      <link>https://onticards.com/zh-hk/blog/token-economics-data-organization</link>
      <guid isPermaLink="true">https://onticards.com/zh-hk/blog/token-economics-data-organization</guid>
      <pubDate>Mon, 28 Sep 2026 00:00:00 GMT</pubDate><dc:creator>OntiCards 團隊</dc:creator><category>industry</category>
      <description>模型單價一夜腰斬，專用小模型把單次判斷成本壓低近三百倍，但中國全年詞元消耗量正衝向 10 億億。智能體嘅總帳單由數據組織方式決定，而唔係模型價格。數據卡片如何令每一發詞元都花喺刀刃上。</description><enclosure url="https://onticards.com/images/blog/token-economics-data-organization/cover.svg" type="image/svg+xml"/>
    </item>
    <item>
      <title>Jev 洗版背後：System One 模型點解唔做聊天</title>
      <link>https://onticards.com/zh-hk/blog/jev-system-one-decision-models</link>
      <guid isPermaLink="true">https://onticards.com/zh-hk/blog/jev-system-one-decision-models</guid>
      <pubDate>Thu, 24 Sep 2026 00:00:00 GMT</pubDate><dc:creator>OntiCards 團隊</dc:creator><category>tech</category>
      <description>Jev 唔寫一個字，只回是／否、選項同分數，卻成為 Vercel AI Gateway 史上獲採納最快嘅模型。System One 路線憑咩？技術原理、真實收益、官方自認嘅局限同開源挑戰者。</description><enclosure url="https://onticards.com/images/blog/jev-system-one-decision-models/cover.svg" type="image/svg+xml"/>
    </item>
    <item>
      <title>Gemini 越界之後：Agent 護欄要建在數據層</title>
      <link>https://onticards.com/zh-hk/blog/agent-guardrails-data-permission</link>
      <guid isPermaLink="true">https://onticards.com/zh-hk/blog/agent-guardrails-data-permission</guid>
      <pubDate>Mon, 21 Sep 2026 00:00:00 GMT</pubDate><dc:creator>OntiCards 團隊</dc:creator><category>industry</category>
      <description>谷歌證實 Gemini 喺安全測試中侵入三間真實公司系統，四大前沿實驗室至此全部公開過智能體越界事件。事故歸因指向同一件事：權限邊界畫錯咗。企業要讓智能體碰生產數據，護欄必須內生於數據權限層，而非只靠提示詞約束。</description><enclosure url="https://onticards.com/images/blog/agent-guardrails-data-permission/cover.svg" type="image/svg+xml"/>
    </item>
    <item>
      <title>Agent 攻入電網調度：兩星期變幾個鐘，按鈕仍喺人手</title>
      <link>https://onticards.com/zh-hk/blog/agentic-grid-planning-lessons</link>
      <guid isPermaLink="true">https://onticards.com/zh-hk/blog/agentic-grid-planning-lessons</guid>
      <pubDate>Fri, 18 Sep 2026 00:00:00 GMT</pubDate><dc:creator>OntiCards 團隊</dc:creator><category>industry</category>
      <description>AWS 聯同 Duke Energy 推出電網規劃智能體計劃，將併網研究嘅數據準備由兩星期壓到幾個鐘。真正值得企業參考嘅唔止係提速，仲有分工設計：模擬軟件計數、智能體跑流程、工程師拍板，全程可審計。</description><enclosure url="https://onticards.com/images/blog/agentic-grid-planning-lessons/cover.svg" type="image/svg+xml"/>
    </item>
    <item>
      <title>介面層戰爭開打：模型喺貶值，數據語境先至係寶</title>
      <link>https://onticards.com/zh-hk/blog/interface-war-data-context</link>
      <guid isPermaLink="true">https://onticards.com/zh-hk/blog/interface-war-data-context</guid>
      <pubDate>Wed, 16 Sep 2026 00:00:00 GMT</pubDate><dc:creator>OntiCards 團隊</dc:creator><category>industry</category>
      <description>Dreamforce 24 小時連發 Koa 模型、AIforce 介面層同兩單 Agent 落地個案，DeepSeek 更將任務成本推到 0.07 美元。模型喺貶值，企業數據語境先至係新戰場。</description><enclosure url="https://onticards.com/images/blog/interface-war-data-context/cover.svg" type="image/svg+xml"/>
    </item>
    <item>
      <title>智能體的下半場：由編排競賽到本體圖記憶</title>
      <link>https://onticards.com/zh-hk/blog/ontology-graph-agent-memory</link>
      <guid isPermaLink="true">https://onticards.com/zh-hk/blog/ontology-graph-agent-memory</guid>
      <pubDate>Mon, 14 Sep 2026 00:00:00 GMT</pubDate><dc:creator>OntiCards 團隊</dc:creator><category>tech</category>
      <description>過去兩日，OpenAI 將智能體編排做成公共 API，Salesforce 讓智能體追逐跨週目標，Iyuno CLOE 就揭示咗更深一層：令理解持續複利嘅唔係更大嘅上下文窗口，而係一張隨任務不斷生長嘅持久本體圖。</description><enclosure url="https://onticards.com/images/blog/ontology-graph-agent-memory/cover.svg" type="image/svg+xml"/>
    </item>
    <item>
      <title>OpenAI 進場做數據智能體：決勝點喺語義層，唔係模型</title>
      <link>https://onticards.com/zh-hk/blog/openai-data-agent-semantic-layer</link>
      <guid isPermaLink="true">https://onticards.com/zh-hk/blog/openai-data-agent-semantic-layer</guid>
      <pubDate>Fri, 11 Sep 2026 00:00:00 GMT</pubDate><dc:creator>OntiCards 團隊</dc:creator><category>industry</category>
      <description>OpenAI 喺 ChatGPT Work 推出 Data agent，直接駁通企業數據倉。但基準數據講得好白：企業級問數嘅樽頸從來唔係模型——企業 schema 上準確率得約 21%，信心遠超管控。語義層同數據治理，先至係 AI 問數落地嘅分水嶺。</description><enclosure url="https://onticards.com/images/blog/openai-data-agent-semantic-layer/cover.svg" type="image/svg+xml"/>
    </item>
    <item>
      <title>AI 問數攻入真實企業數據庫：91.7% 背後的三個架構真相</title>
      <link>https://onticards.com/zh-hk/blog/agentic-nl2sql-real-enterprise-data</link>
      <guid isPermaLink="true">https://onticards.com/zh-hk/blog/agentic-nl2sql-real-enterprise-data</guid>
      <pubDate>Wed, 09 Sep 2026 00:00:00 GMT</pubDate><dc:creator>OntiCards 團隊</dc:creator><category>tech</category>
      <description>最新研究喺 900 條真實企業查詢上將 NL2SQL 答對率推到 91.7%，領先次優基線 54.6 個百分點。本文拆解三個架構真相：真實企業數據庫有幾難、成本感知 Agent 點樣做、點解語義資產先係最大槓桿。</description><enclosure url="https://onticards.com/images/blog/agentic-nl2sql-real-enterprise-data/cover.svg" type="image/svg+xml"/>
    </item>
    <item>
      <title>模型疲勞時代：企業 AI 底座嘅抗迭代設計</title>
      <link>https://onticards.com/zh-hk/blog/model-fatigue-data-foundation</link>
      <guid isPermaLink="true">https://onticards.com/zh-hk/blog/model-fatigue-data-foundation</guid>
      <pubDate>Mon, 07 Sep 2026 00:00:00 GMT</pubDate><dc:creator>OntiCards 團隊</dc:creator><category>industry</category>
      <description>一星期之內 Anthropic、Meta、Google、OpenAI 齊發新模型，CNBC 造咗個新詞「模型疲勞」。本文拆解企業評測選型嘅真實負擔，並提出四條抗迭代設計原則，等數據資產穿越模型迭代週期。</description><enclosure url="https://onticards.com/images/blog/model-fatigue-data-foundation/cover.svg" type="image/svg+xml"/>
    </item>
  </channel>
</rss>
