<p>之前將他們的直播視頻初創公司 Periscope 出售給 Twitter 的創始人們又回來了，這次他們創辦了一家新的初創公司，毫無疑問，這是一家專注於人工智能的公司。</p>
<p>週三，前 Twitter 產品負責人 Kayvon Beykpour 宣佈推出 Macroscope，這是一款面向開發者和產品領導者的人工智能系統，旨在總結代碼庫的更新並捕捉錯誤等。</p>
<p>這家初創公司由 Beykpour（現任 Macroscope 首席執行官）於 2023 年 7 月與童年好友 Joe Bernstein 共同創辦，Bernstein 也曾在 Periscope 和他們之前的企業初創公司 Terriblyclever 工作，該公司於 2009 年出售給 Blackboard。他們的聯合創始人 Rob Bishop 也加入了他，他在 2016 年將他的計算機視覺和機器學習公司 Magic Pony Technology 出售給 Twitter。</p>
<p>該公司將其產品描述為 “人工智能驅動的理解引擎”，旨在為工程師節省時間。Beykpour 表示，今天的工程師使用各種工具來跟蹤工作，如 JIRA、Linear 和電子表格，並且在會議上花費了太多時間，而不是進行實際的構建。Macroscope 旨在解決這個問題。</p>
<p><img src="https://imageproxy.pbkrs.com/https://techcrunch.com/wp-content/uploads/2025/09/Productivity-Stats.jpg/query-dz02ODA?x-oss-process=image/auto-orient,1/interlace,1/resize,w_1440,h_1440/quality,q_95/format,jpg" alt="" original-src="https://imageproxy.pbkrs.com/https://techcrunch.com/wp-content/uploads/2025/09/Productivity-Stats.jpg/query-dz02ODA"/></p>
<p><strong>圖片來源：</strong> Macroscope</p>
<p>“我覺得我經歷過這種痛苦……在我工作的每家公司，無論是我們自己建立的初創公司，還是像 Twitter 這樣的大型上市公司，我們都以艱難的方式經歷了這個問題，” Beykpour 在接受 TechCrunch 採訪時説道。</p>
<p>“試圖瞭解每個人在做什麼，尤其是當你有像 Twitter 這樣擁有數千名工程師的組織時，這幾乎是我工作的全部內容——也是我在 Twitter 擔任產品負責人的時候最不喜歡的部分，” 他説。</p>
<p><img src="https://imageproxy.pbkrs.com/https://techcrunch.com/wp-content/uploads/2025/09/Project-Summaries.jpg/query-dz02ODA?x-oss-process=image/auto-orient,1/interlace,1/resize,w_1440,h_1440/quality,q_95/format,jpg" alt="" original-src="https://imageproxy.pbkrs.com/https://techcrunch.com/wp-content/uploads/2025/09/Project-Summaries.jpg/query-dz02ODA"/></p>
<p><strong>圖片來源：</strong> Macroscope</p>
<p>為了解決這個問題和其他問題，Macroscope 的客户首先安裝其 GitHub 應用，這使得公司可以訪問代碼庫。然後，他們可以選擇安裝其他集成，如 Slack 應用、Linear 應用和 JIRA 應用。軟件隨後通過分析代碼並記錄變化來完成其餘工作。</p>
<p>Techcrunch 事件</p>
<p>舊金山 |2025 年 10 月 27-29 日</p>
<p>這涉及一個稱為代碼漫遊的過程，它使用抽象語法樹（AST）——編程代碼的結構表示——來收集有關客户代碼庫如何工作的關鍵信息。這些知識隨後與大型語言模型（LLMs）結合使用。</p>
<p><img src="https://imageproxy.pbkrs.com/https://techcrunch.com/wp-content/uploads/2025/09/Pull-request-Descriptions.jpg/query-dz02ODA?x-oss-process=image/auto-orient,1/interlace,1/resize,w_1440,h_1440/quality,q_95/format,jpg" alt="" original-src="https://imageproxy.pbkrs.com/https://techcrunch.com/wp-content/uploads/2025/09/Pull-request-Descriptions.jpg/query-dz02ODA"/></p>
<p><strong>圖片來源：</strong> Macroscope</p>
<p>一旦啓動，工程師可以使用 Macroscope 發現需要修復的 PR（拉取請求）中的錯誤，總結他們的 PR，獲取代碼庫變化的摘要，並提出基於代碼研究的問題。同時，產品領導者可以使用該軟件實時獲取產品更新的摘要、生產力洞察、關於產品、代碼或開發活動的自然語言問題的答案等。這可以幫助他們確定團隊在工程分配方面的優先事項。</p>
<p><img src="https://imageproxy.pbkrs.com/https://techcrunch.com/wp-content/uploads/2025/09/Ask-Macroscope-Anything.jpg/query-dz02ODA?x-oss-process=image/auto-orient,1/interlace,1/resize,w_1440,h_1440/quality,q_95/format,jpg" alt="" original-src="https://imageproxy.pbkrs.com/https://techcrunch.com/wp-content/uploads/2025/09/Ask-Macroscope-Anything.jpg/query-dz02ODA"/></p>
<p><strong>圖片來源：</strong> Macroscope</p>
<p>“你可以提出自然語言問題，無論你的技術能力如何，” Beykpour 指出。“如果你想了解代碼庫而不打擾團隊中的高級工程師，這可能非常有用。非常有價值。如果你是 CEO，想要了解 ‘我們這周完成了什麼？’，你的選擇要麼是問 Macroscope，要麼去打擾一些隊友，” 他補充道。“一個的成本遠高於另一個。”</p>
<p><img src="https://imageproxy.pbkrs.com/https://techcrunch.com/wp-content/uploads/2025/09/Bug-Finding-and-Fixing.jpg/query-dz02ODA?x-oss-process=image/auto-orient,1/interlace,1/resize,w_1440,h_1440/quality,q_95/format,jpg" alt="" original-src="https://imageproxy.pbkrs.com/https://techcrunch.com/wp-content/uploads/2025/09/Bug-Finding-and-Fixing.jpg/query-dz02ODA"/></p>
<p><strong>圖片來源：</strong> Macroscope</p>
<p>雖然沒有產品直接與 Macroscope 提供的所有功能競爭，但它在代碼審查領域與 CodeRabbit、Cursor Bugbot、Graphite Diamond、Greptile 等工具競爭，開發者在實施之前會檢查和測試代碼更改。然而，該公司表示，在對 100 多個真實世界的錯誤進行內部基準測試時，其產品捕獲的錯誤比下一個最佳工具多出 5%。它還生成了 75% 更少的評論。（它在一篇博客文章中公開分享了其基準測試結果。）</p>
<p><img src="https://imageproxy.pbkrs.com/https://techcrunch.com/wp-content/uploads/2025/09/macroscope-benchmark-2025-09-17-at-3.06.46PM.jpg/query-dz02ODA?x-oss-process=image/auto-orient,1/interlace,1/resize,w_1440,h_1440/quality,q_95/format,jpg" alt="" original-src="https://imageproxy.pbkrs.com/https://techcrunch.com/wp-content/uploads/2025/09/macroscope-benchmark-2025-09-17-at-3.06.46PM.jpg/query-dz02ODA"/></p>
<p><strong>圖片來源：</strong> Macroscope</p>
<p><img src="https://imageproxy.pbkrs.com/https://techcrunch.com/wp-content/uploads/2025/09/macroscope-benchmark-2025-09-17-at-3.06.57PM.jpg/query-dz02ODA?x-oss-process=image/auto-orient,1/interlace,1/resize,w_1440,h_1440/quality,q_95/format,jpg" alt="" original-src="https://imageproxy.pbkrs.com/https://techcrunch.com/wp-content/uploads/2025/09/macroscope-benchmark-2025-09-17-at-3.06.57PM.jpg/query-dz02ODA"/></p>
<p><strong>圖片來源：</strong> Macroscope</p>
<p>該軟件的費用為每位活躍開發者每月 30 美元，起始為五個席位，併為大型企業提供企業定價和定製集成。在推出之前，一些初創公司和大型企業已經在使用該產品，包括 XMTP、Things、United Masters、Bilt、Class.com、Seed.com、ParkHub、A24 Labs 等。</p>
<p>這家位於舊金山的初創公司擁有 20 人的團隊，並獲得了 3000 萬美元的 A 輪融資，該輪融資於 7 月完成，由 Lightspeed 的 Michael Mignano 領導。其他投資者包括 Adverb、Thrive Capital 和 Google Ventures。到目前為止，Macroscope 總共籌集了 4000 萬美元。</p>

<p>Macroscope 是一款由前 Twitter 產品負責人 Kayvon Beykpour 和聯合創始人 Joe Bernstein 及 Rob Bishop 推出的 AI 工具。該工具總結代碼庫更新並識別錯誤，旨在簡化工程流程。它與 GitHub 及其他工具集成，允許用户用自然語言提問關於他們代碼的問題。Macroscope 的定價為每位開發者每月 30 美元，已籌集 4000 萬美元的資金，並已被多家初創公司和企業使用</p>

<p>The founders who previously sold their livestreaming video startup Periscope to Twitter are back with a new startup — and no surprise, it’s an AI-focused company this time around.</p>
<div class="lb-trans"><p>之前將他們的直播視頻初創公司 Periscope 出售給 Twitter 的創始人們又回來了，這次他們創辦了一家新的初創公司，毫無疑問，這是一家專注於人工智能的公司。</p>
</div><p>On Wednesday, former Twitter head of product Kayvon Beykpour announced the launch of Macroscope, an AI system aimed at developers and product leaders that summarizes updates to a codebase and catches bugs, among other things.</p>
<div class="lb-trans"><p>週三，前 Twitter 產品負責人 Kayvon Beykpour 宣佈推出 Macroscope，這是一款面向開發者和產品領導者的人工智能系統，旨在總結代碼庫的更新並捕捉錯誤等。</p>
</div><p>The startup was co-founded by Beykpour, now Macroscope CEO, in July 2023, along with childhood friend Joe Bernstein, also previously of Periscope and their prior enterprise startup, Terriblyclever, which was sold to Blackboard in 2009. They’re joined by co-founder Rob Bishop, who sold his computer vision and machine learning company, Magic Pony Technology, to Twitter in 2016.</p>
<div class="lb-trans"><p>這家初創公司由 Beykpour（現任 Macroscope 首席執行官）於 2023 年 7 月與童年好友 Joe Bernstein 共同創辦，Bernstein 也曾在 Periscope 和他們之前的企業初創公司 Terriblyclever 工作，該公司於 2009 年出售給 Blackboard。他們的聯合創始人 Rob Bishop 也加入了他，他在 2016 年將他的計算機視覺和機器學習公司 Magic Pony Technology 出售給 Twitter。</p>
</div><p>The company describes its product as an “AI-powered understanding engine” that’s designed to save engineers time. Today, engineers use a variety of tools to keep track of work, like JIRA, Linear, and spreadsheets, and spend too much time in meetings instead of building, Beykpour says. Macroscope is designed to fix this.</p>
<div class="lb-trans"><p>該公司將其產品描述為 “人工智能驅動的理解引擎”，旨在為工程師節省時間。Beykpour 表示，今天的工程師使用各種工具來跟蹤工作，如 JIRA、Linear 和電子表格，並且在會議上花費了太多時間，而不是進行實際的構建。Macroscope 旨在解決這個問題。</p>
</div><p><img src="https://imageproxy.pbkrs.com/https://techcrunch.com/wp-content/uploads/2025/09/Productivity-Stats.jpg/query-dz02ODA" alt="" original-src="https://techcrunch.com/wp-content/uploads/2025/09/Productivity-Stats.jpg?w=680"/></p>
<p><strong>Image Credits:</strong> Macroscope</p>
<div class="lb-trans"><p><strong>圖片來源：</strong> Macroscope</p>
</div><p>“I feel like I lived this pain…at every company I worked at, whether it was the startups that we built ourselves, or whether it was enormous public companies like Twitter, we sort of lived this problem the hard way,” Beykpour told TechCrunch in an interview.</p>
<div class="lb-trans"><p>“我覺得我經歷過這種痛苦……在我工作的每家公司，無論是我們自己建立的初創公司，還是像 Twitter 這樣的大型上市公司，我們都以艱難的方式經歷了這個問題，” Beykpour 在接受 TechCrunch 採訪時説道。</p>
</div><p>“Trying to get a sense for what everyone was doing, especially when you have an organization like Twitter with thousands of engineers, it was literally most of my job — and my least favorite part of my job as the head of product at Twitter,” he said.</p>
<div class="lb-trans"><p>“試圖瞭解每個人在做什麼，尤其是當你有像 Twitter 這樣擁有數千名工程師的組織時，這幾乎是我工作的全部內容——也是我在 Twitter 擔任產品負責人的時候最不喜歡的部分，” 他説。</p>
</div><p><img src="https://imageproxy.pbkrs.com/https://techcrunch.com/wp-content/uploads/2025/09/Project-Summaries.jpg/query-dz02ODA" alt="" original-src="https://techcrunch.com/wp-content/uploads/2025/09/Project-Summaries.jpg?w=680"/></p>
<p><strong>Image Credits:</strong> Macroscope</p>
<div class="lb-trans"><p><strong>圖片來源：</strong> Macroscope</p>
</div><p>To address this issue and others, Macroscope’s customers first install its GitHub app, which gives the company access to the code base. They can then optionally install other integrations, like a Slack app, Linear app, and JIRA app. The software then does the rest of the work by analyzing the code and noting what’s changing.</p>
<div class="lb-trans"><p>為了解決這個問題和其他問題，Macroscope 的客户首先安裝其 GitHub 應用，這使得公司可以訪問代碼庫。然後，他們可以選擇安裝其他集成，如 Slack 應用、Linear 應用和 JIRA 應用。軟件隨後通過分析代碼並記錄變化來完成其餘工作。</p>
</div><p>Techcrunch event</p>
<div class="lb-trans"><p>Techcrunch 事件</p>
</div><p>San Francisco|October 27-29, 2025</p>
<div class="lb-trans"><p>舊金山 |2025 年 10 月 27-29 日</p>
</div><p>This involves a process called code walking, which uses the Abstract Syntax Tree (AST) — a structural representation of programming code — to gather important context about how the customer’s code base works. That knowledge is then used in conjunction with large language models (LLMs).</p>
<div class="lb-trans"><p>這涉及一個稱為代碼漫遊的過程，它使用抽象語法樹（AST）——編程代碼的結構表示——來收集有關客户代碼庫如何工作的關鍵信息。這些知識隨後與大型語言模型（LLMs）結合使用。</p>
</div><p><img src="https://imageproxy.pbkrs.com/https://techcrunch.com/wp-content/uploads/2025/09/Pull-request-Descriptions.jpg/query-dz02ODA" alt="" original-src="https://techcrunch.com/wp-content/uploads/2025/09/Pull-request-Descriptions.jpg?w=680"/></p>
<p><strong>Image Credits:</strong> Macroscope</p>
<div class="lb-trans"><p><strong>圖片來源：</strong> Macroscope</p>
</div><p>Once up and running, engineers can use Macroscope to discover bugs to fix in their PRs (pull requests), summarize their PRs, get a summary of how the codebase is changing, and ask code research-based questions. Meanwhile, product leaders could use the software to get real-time summaries of product updates, productivity insights, answers to natural language questions about the product, code, or development activity, and more. This can help them determine what teams are prioritizing in terms of engineering allocation.</p>
<div class="lb-trans"><p>一旦啓動，工程師可以使用 Macroscope 發現需要修復的 PR（拉取請求）中的錯誤，總結他們的 PR，獲取代碼庫變化的摘要，並提出基於代碼研究的問題。同時，產品領導者可以使用該軟件實時獲取產品更新的摘要、生產力洞察、關於產品、代碼或開發活動的自然語言問題的答案等。這可以幫助他們確定團隊在工程分配方面的優先事項。</p>
</div><p><img src="https://imageproxy.pbkrs.com/https://techcrunch.com/wp-content/uploads/2025/09/Ask-Macroscope-Anything.jpg/query-dz02ODA" alt="" original-src="https://techcrunch.com/wp-content/uploads/2025/09/Ask-Macroscope-Anything.jpg?w=680"/></p>
<p><strong>Image Credits:</strong> Macroscope</p>
<div class="lb-trans"><p><strong>圖片來源：</strong> Macroscope</p>
</div><p>“You can ask natural language questions, regardless of what your technical ability is,” notes Beykpour. “This might be very useful if you’re trying to learn about the code base without distracting a senior engineer on your team. Very valuable. If you’re a CEO and you want to understand literally, ‘what did we get done this week?’, your options are either ask Macroscope or go distract some teammates,” he adds. “One is a lot more expensive than the other.”</p>
<div class="lb-trans"><p>“你可以提出自然語言問題，無論你的技術能力如何，” Beykpour 指出。“如果你想了解代碼庫而不打擾團隊中的高級工程師，這可能非常有用。非常有價值。如果你是 CEO，想要了解 ‘我們這周完成了什麼？’，你的選擇要麼是問 Macroscope，要麼去打擾一些隊友，” 他補充道。“一個的成本遠高於另一個。”</p>
</div><p><img src="https://imageproxy.pbkrs.com/https://techcrunch.com/wp-content/uploads/2025/09/Bug-Finding-and-Fixing.jpg/query-dz02ODA" alt="" original-src="https://techcrunch.com/wp-content/uploads/2025/09/Bug-Finding-and-Fixing.jpg?w=680"/></p>
<p><strong>Image Credits:</strong> Macroscope</p>
<div class="lb-trans"><p><strong>圖片來源：</strong> Macroscope</p>
</div><p>While there isn’t a product that offers a direct competitor to all that Macroscope offers, it does compete in the code review space — where developers examine and test code changes before they’re implemented — with tools like CodeRabbit, Cursor Bugbot, Graphite Diamond, Greptile, and others. However, the company said when it ran its own internal benchmark of over 100 real-world bugs, its product caught 5% more bugs than the next-best tool. It also generated 75% fewer comments. (It shared its benchmark publicly in a blog post.)</p>
<div class="lb-trans"><p>雖然沒有產品直接與 Macroscope 提供的所有功能競爭，但它在代碼審查領域與 CodeRabbit、Cursor Bugbot、Graphite Diamond、Greptile 等工具競爭，開發者在實施之前會檢查和測試代碼更改。然而，該公司表示，在對 100 多個真實世界的錯誤進行內部基準測試時，其產品捕獲的錯誤比下一個最佳工具多出 5%。它還生成了 75% 更少的評論。（它在一篇博客文章中公開分享了其基準測試結果。）</p>
</div><p><img src="https://imageproxy.pbkrs.com/https://techcrunch.com/wp-content/uploads/2025/09/macroscope-benchmark-2025-09-17-at-3.06.46PM.jpg/query-dz02ODA" alt="" original-src="https://techcrunch.com/wp-content/uploads/2025/09/macroscope-benchmark-2025-09-17-at-3.06.46PM.jpg?w=680"/></p>
<p><strong>Image Credits:</strong> Macroscope</p>
<div class="lb-trans"><p><strong>圖片來源：</strong> Macroscope</p>
</div><p><img src="https://imageproxy.pbkrs.com/https://techcrunch.com/wp-content/uploads/2025/09/macroscope-benchmark-2025-09-17-at-3.06.57PM.jpg/query-dz02ODA" alt="" original-src="https://techcrunch.com/wp-content/uploads/2025/09/macroscope-benchmark-2025-09-17-at-3.06.57PM.jpg?w=680"/></p>
<p><strong>Image Credits:</strong> Macroscope</p>
<div class="lb-trans"><p><strong>圖片來源：</strong> Macroscope</p>
</div><p>The software costs $30 per active developer per month, starting at five seats, and offers enterprise pricing and custom integrations for larger businesses. It requires the use of GitHub Cloud. Ahead of its launch, a number of startups and larger firms have been using the product, including XMTP, Things, United Masters, Bilt, Class.com, Seed.com, ParkHub, A24 Labs, and others.</p>
<div class="lb-trans"><p>該軟件的費用為每位活躍開發者每月 30 美元，起始為五個席位，併為大型企業提供企業定價和定製集成。在推出之前，一些初創公司和大型企業已經在使用該產品，包括 XMTP、Things、United Masters、Bilt、Class.com、Seed.com、ParkHub、A24 Labs 等。</p>
</div><p>The San Francisco-based startup has a team of 20 and is backed by $30 million in Series A funding, which was closed in July and led by Michael Mignano at Lightspeed. Other investors include Adverb, Thrive Capital, and Google Ventures. To date, Macroscope has raised $40 million total.</p>
<div class="lb-trans"><p>這家位於舊金山的初創公司擁有 20 人的團隊，並獲得了 3000 萬美元的 A 輪融資，該輪融資於 7 月完成，由 Lightspeed 的 Michael Mignano 領導。其他投資者包括 Adverb、Thrive Capital 和 Google Ventures。到目前為止，Macroscope 總共籌集了 4000 萬美元。</p>
</div>

認識 Macroscope：一種用於理解代碼庫並修復錯誤的 AI 工具